紙閱讀-Convai
對話AI中的紙質閱讀清單,主要包括對話系統和自然語言的生成。這個存儲庫不斷更新? ...
- 在NLP中深入學習
- 對話系統
- 對話調查
- 會話llms
- 多模式對話
- 積極的對話
- 雜項。主動對話
- 面向目標的對話
- 非授權對話(說服與談判)
- 個性化對話
- 情感對話
- 建議對話和CRS
- 知識接地的對話
- 面向任務的對話
- 開放域對話
- 對話評估
- 對話雜項。
- 自然語言產生
- NLG的調查
- NLG理論和技術
- NLG的擴散模型
- 可控的一代
- 文字計劃
- 解碼算法
- NLG評估
在NLP中深入學習
- INLP :“交互式自然語言處理”。 Arxiv(2023)[紙]
- 數據增強:“ NLP的數據增強方法的調查”。 ACL-findings(2021)[紙]
- 提示:“預訓練,提示和預測:對自然語言處理中提示方法的系統調查”。 Arxiv(2021)[紙]
- NLP世界範圍:“體驗基礎語言”。 EMNLP(2020)[紙]
- Transformer-XL :“ Transformer-XL:超出固定長度上下文的細心語言模型”。 ACL(2019)[紙] [代碼]
- 變形金剛:“注意就是您所需要的”。 Neurips(2017)[Paper] [Code-incial] [Code-TF] [Code-Py]
- VAE :“跨自動編碼器簡介”。 Arxiv(2019)[紙]
- 注意調查:“ NLP問題中註意機制的介紹性調查”。 Arxiv(2018)[紙]
- 加性關注:“通過共同學習對齊和翻譯的神經機器翻譯”。 ICLR(2015)[紙]
- 乘法注意:“基於注意力的神經機器翻譯的有效方法”。 Emnlp(2015)[紙]
- 內存網:“端到端內存網絡”。 Neurips(2015)[紙]
- 複製機制(PGN) :“指點:用指針生成器網絡匯總”。 ACL(2017)[紙] [代碼]
- 複製機制:“將復制機制納入順序到序列學習”。 ACL(2016)[紙]
- Elmo :“深層上下文化的單詞表示”。 NAACL(2018)[紙] [代碼]
- 手套:“手套:單詞表示的全球向量”。 EMNLP(2014)[紙] [代碼]
- Word2Vec教程:“解釋了Word2Vec參數學習”。 Arxiv(2016)[紙]
- 多任務學習:“深神經網絡中的多任務學習概述”。 Arxiv(2017)[紙]
- 梯度下降:“梯度下降優化算法的概述”。 Arxiv(2016)[紙]
?回到頂部
對話系統
對話調查
- 數據生成:“關於對話數據生成的最新進展的調查”。 Arxiv(2024)[紙]
- 主動對話:“主動對話系統的調查:問題,方法和前景”。 IJCAI(2023)[紙]
- 負責任的對話:“朝著安全,負責任和道德對話系統的最新進展:調查”。 Arxiv(2023)[紙]
- 談判對話:“讓我們進行談判!談判對話系統的調查”。 Arxiv(2022)[紙]
- 基於DL的對話:“基於深度學習的對話系統的最新進展:系統調查”。 Arxiv(2021)[紙]
- 開放域對話:“構建智能開放域對話系統的挑戰”。 Tois(2020)[紙]
- 對話系統:“對話系統的調查:最新進步和新的邊界”。 Sigkdd Explorations(2017)[紙]
- 對話公司:“用於構建數據驅動對話系統的可用語料庫的調查”。 Arxiv(2017)[紙] [數據]
?回到頂部
會話llms
- 鸚鵡:“鸚鵡:通過學習提出問題來增強多轉向聊天模型”。 Arxiv(2023)[紙]
- MEMOCHAT :“ Memochat:調整LLMS使用備忘錄進行一致的遠程開放域對話”。 Arxiv(2023)[紙]
- Llama 2-Chat :“ Llama 2:開放基礎和微調的聊天模型”。元(2023)[紙] [代碼]
- chatglm3 :“ chatglm3系列:打開雙語聊天llms”。 Tsinghua(2023)[代碼]
- chatglm2-6b :“ chatglm2-6b:開放的雙語聊天llm”。 Tsinghua(2023)[代碼]
- MPC :“提示LLM作為聊天機器人模塊進行長時間的開放域對話”。 ACL-findings(2023)[紙] [代碼]
- MemoryBank-Siliconfriend :“ MemoryBank:增強具有長期記憶的大語言模型”。 Arxiv(2023)[紙] [代碼]
- Ultrachat :“通過擴展高質量的教學對話來增強聊天語言模型”。 Arxiv(2023)[紙] [數據]
- Chatalpaca :“ Chatalpaca:基於羊駝指示的多轉話語料庫”。 Github(2023)[數據]
- 鳳凰城:“鳳凰:跨語言使chatgpt民主化”。 Arxiv(2023)[紙] [代碼]
- 多莉:“自由多莉:介紹世界上第一個真正的開放指導調節的LLM”。 Databricks(2023)[代碼]
- Baize :“ Baize:一個開源聊天模型,並在自chat數據上進行參數有效調整”。 Arxiv(2023)[紙] [代碼]
- Vicuna :“ Vicuna:一個開源聊天機器人給GPT-4帶來了90%的Chatgpt質量”。 lmsys org(2023)[博客] [代碼]
- 考拉:“考拉:學術研究對話模型”。加州大學伯克利分校(2023)[博客] [代碼]
- 美女:“美女:成為每個人的大型語言模型引擎”。 Lianjiatech(2023)[代碼]
- 羊駝:“羊駝:強大的,可複制的指令遵循模型”。斯坦福大學(2023)[博客] [代碼] [羊駝羊角]
- ChatGLM-6B :“開放的雙語對話語言模型”。 Tsinghua(2023)[代碼]
- 開放式輔助:“開放助理:每個人的對話人工智能”。 Github(2023)[項目] [代碼]
- chatgpt :“ chatgpt:優化對話的語言模型”。 Openai(2022)[博客]
- 麻雀:“通過有針對性的人類判斷提高對話代理的一致性”。 Arxiv(2022)[紙] [數據]
- BlenderBot3 :“ BlenderBot 3:一種部署的對話代理,不斷學習以負責任地參與”。 Arxiv(2022)[紙]
- LAMDA :“ LAMDA:對話框應用程序的語言模型”。 Arxiv(2022)[紙]
- Godel :“ Godel:針對目標導向對話的大規模預訓練”。 Arxiv(2022)[紙] [代碼]
- 擬人化助理V2 :“從人類反饋中學習的強化學習培訓有益且無害的助手”。 Arxiv(2022)[紙]
- 人類助手:“一名通用語言助理作為對齊實驗室的實驗室”。 Arxiv(2021)[紙]
?回到頂部
多模式對話
位置和體現的對話
- SLL :“基於大型語言模型的第二語言學習對話”。 Arxiv(2024)[紙]
- EMB-PLAN :“通過合成體現的對話增強的多模式體現計劃預測”。 EMNLP(2023)[紙]
- WTAG :“基礎模型可以觀看,交談和引導您逐步製作蛋糕嗎?”。 emnlp-findings(2023)[紙] [代碼]
- SIMMC-VR :“ SIMMC-VR:帶有位置和沈浸式VR流的以任務為導向的多模式對話框”。 ACL(2023)[紙]
- 當然:“具有主觀偏好的多模式推薦對話:新的挑戰和基準”。 ACL(2023)[紙] [數據]
- 糖:“用於主動響應選擇的文本數據集”。 ACL(2023)[紙] [數據]
- 思想:“思維:信念動態跟踪,並通過神經對話產生的心態建模”。 Arxiv(2023)[紙]
- HoloAssist :“全力以赴:以現實世界中交互式AI助手為中心的人類互動數據集”。 ICCV(2023)[紙] [數據]
- 合作:“通過對話中的心理建模理論建模邁向協作計劃”。 ijcai(2023)[紙] [代碼]
- Alexa Arena :“ Alexa Arena:一個以用戶為中心的體現AI的交互式平台”。 Arxiv(2023)[紙] [代碼]
- Seagull :“ Seagull:通過位置對話進行指導的體現代理”。 Alexa獎Simbot Challenge(2023)[紙]
- 情景喜劇:“您指的是哪一個?在位置對話中的多模式對象標識”。 EACL-SRW(2023)[紙] [代碼]
- MLR :“通過分步多模式邏輯推理改善定位對話劑”。 DSTC11(2023)[紙]
- SimpleMTOD :“ SimpleMTOD:具有符號場景表示形式的多模式為導向對話的簡單語言模型”。 Arxiv(2023)[紙]
- 春季:“春季:通過從增量佈局圖中鑑定的多模式問題的位置對話代理”。 AAAI(2023)[紙] [代碼]
- Dorothie :“ Dorothie:在交互式自主駕駛代理中處理意外情況的口語對話”。 emnlp-findings(2022)[紙] [代碼]
- 光學課:“通過程序環境產生進行對話學習”。 ACL(2022)[紙]
- Danli :“ Danli:遵循自然語言指示的審議代理”。 EMNLP(2022)[紙] [代碼]
- PRS :“學會介導務實的溝通差異”。 ACL(2022)[紙] [代碼]
- 聯合模型:“學習嵌入位置對話劑的多模式環境”。 naacl-findings(2022)[紙] [代碼]
- Teach_film :“不要復制老師:體現對話中的數據和模型挑戰”。 EMNLP(2022)[紙] [代碼]
- 教導:“教導:任務驅動的體現聊天的代理”。 AAAI(2022)[紙] [數據]
- Mindcraft :“ Mindcraft:在協作任務中對對話的思維理論建模”。 EMNLP(2021)[紙] [代碼]
- 多模式模型:“使用驗證的單峰模型用於SIMMC 2.0的多模式相互作用”。 DSTC10(2022)[紙] [代碼]
- SIMMC 2.0 :“ SIMMC 2.0:面向任務的對話框數據集,用於沉浸式多模式對話” EMNLP(2021)[PAPER] [code]
- MM-DST :“用於多域端到端對話系統的多任務學習”。 Arxiv(2021)[紙]
- SIMMC :“位置和交互式多模式對話”。 Coling(2020)[紙] [代碼]
- Minecraft-bap :“學習在Minecraft對話中執行指令”。 ACL(2020)[紙] [代碼]
- 穀物:“執行指令在所在的協作互動中”。 EMNLP(2019)[紙] [代碼]
- Minecraft對話:“ Minecraft中的協作對話”。 ACL(2019)[紙] [代碼]
- CLG :“協作語言基於人類風光對話的基礎”。 AI雜誌(2016)[紙]
- SHRD :“回到街區世界:通過處於人類機器人對話來學習新動作”。 Sigdial(2014)[紙]
視覺上的對話
- 老虎:“老虎:多模式對話響應生成的統一生成模型框架”。 Coling(2024)。 [紙] [代碼]
- DialOgCC :“ DialoGCC:用於創建高質量多模式對話數據集的自動化管道”。 NAACL(2024)[紙] [數據]
- VLAW-MDM :“多模式對話模型中視覺熱身任務的框架”。 EMNLP(2023)[紙] [代碼]
- Zrigf :“ Zrigf:零資源圖像的對話世代的創新多模式框架”。 ACM MM(2023)[紙] [代碼]
- Vdialogue :“ Vdialogue:視覺上對話的統一評估基準”。 Arxiv(2023)[紙]
- TextBind :“文本鍵:多轉交織的多模式指令在野外遵循”。 Arxiv(2023)[紙] [數據]
- VSTAR :“ VSTAR:視頻接地的對話數據集,用於使用場景和主題過渡的語義理解”。 ACL(2023)[紙] [數據]
- COMSET :“基於多模式角色的漫畫對話的一代”。 ACL(2023)[紙] [代碼]
- MPCHAT :“ MPCHAT:進行多模式角色接地的對話”。 ACL(2023)[紙] [代碼]
- 速度:“速度:統一的多模式對話與進步和作曲專家進行培訓”。 ACL(2023)[紙] [代碼]
- mmdialog :“ mmdialog:大規模的多轉向對話數據集,用於多模式開放式對話”。 ACL(2023)[紙] [數據]
- MDS-S2 :“雙重語義知識組成的多模式對話框系統”。 Sigir(2023)[紙]
- tiktalk :“ tiktalk:現實世界中的一個多模式對話數據集”。 Arxiv(2023)[紙] [代碼]
- 香檳:“香檳:從大型網絡視頻中學習真實的對話”。 Arxiv(2023)[紙] [代碼]
- MMCHAT :“ MMCHAT:社交媒體上的多模式聊天數據集”。 LREC(2022)[紙] [代碼]
- CRVD :“關於視頻接地對話的多模式語義圖的協作推理”。 emnlp-findings(2022)[紙]
- M3ED :“ M3ED:多模式多場景多標籤情感對話數據庫”。 ACL(2022)[紙] [數據]
- MDRG :“多模式對話響應產生”。 ACL(2022)[紙]
- Unitranser :“ Unitranser:多模式面向任務的對話框系統的統一變壓器語義表示框架”。 ACL(2022)[紙]
- 攝影:“攝影:一個人類對話數據集具有聯合圖像文本建模的照片共享行為”。 ACL(2021)[紙] [數據]
- 多模式對話:“通過用語義相關圖像替換文本來構建多模式對話數據集”。 ACL(2021)[紙] [代碼]
- OpenVidial 2.0 :“ OpenVidial 2.0:具有視覺上下文的大型,開放域對話生成數據集”。 Arxiv(2021)[紙] [數據]
- 寶藏:“多模式對話框系統:基於關係圖的上下文感知問題理解”。 ACM MM(2021)[紙] [代碼]
- MMCONV :“ MMCONV:跨多個域的多模式對話搜索的環境”。 Sigir(2021)[紙] [數據]
- 圖像聊天:“圖像聊天:引人入勝的對話”。 ACL(2020)[紙] [數據]
- MTN :“端到端視頻接地對話系統的多模式變壓器網絡”。 ACL(2019)[紙] [代碼]
- MELD :“ MELD:在對話中進行情感識別的多模式多方數據集”。 ACL(2019)[紙] [數據]
- CLEVR-DIALOG :“ CLEVR-DIALOG:用於視覺對話中多輪推理的診斷數據集”。 NAACL(2019)[紙] [數據]
- Visdial-RL :“通過回答各種問題來改善生成視覺對話框”。 EMNLP(2019)[紙] [代碼]
- 魔術:“多模式對話框系統:通過自適應解碼器生成響應”。 ACM MM(2019)[紙] [代碼]
- KMD :“知識感知的多模式對話系統”。 ACM MM(2018)[紙]
- MMD :“建立大型多模式域知覺對話系統”。 AAAI(2018)[紙] [數據]
- 散步:“散步:通過紮根的對話來導航紐約市”。 Arxiv(2018)[紙] [代碼]
- IGC :“圖像接地的對話:自然問題和響應產生的多模式上下文”。 IJCNLP(2017)[紙] [數據]
- Visdial :“視覺對話”。 CVPR(2017)[紙] [數據]
?回到頂部
積極的對話
雜項。主動對話
- DPDP :“像人類一樣計劃:對話計劃的雙過程框架”。 ACL(2024)[紙] [代碼]
- PCA :“朝著以人為本的主動對話代理人”。 Sigir(2024)[紙]
- Procot :“提示和評估大型語言模型以進行主動對話:澄清,目標引導和非合作代理”。 emnlp-findings(2023)[紙] [代碼]
- 教程:“對話式AI的目標意識:積極性,非企業及其他人”。 ACL(2023)[紙]
面向目標的對話
- PAI :“邁向以目標為導向的在線教育中的智能輔導系統”。 Arxiv(2023)[紙]
- topdial :“具有個性化的面向目標的主動對話系統:問題制定和數據集策劃”。 EMNLP(2023)[紙] [代碼]
- RTCP :“增強目標驅動的對話促進”。 EMNLP(2023)[紙] [代碼]
- MTGP :“ MTGP:以柔性轉彎為引導的全球路徑指導的多轉向目標對話”。 ACL-findings(2023)[紙] [代碼]
- 顏色:“通過布朗橋的對話計劃,以實現目標為主動對話的隨機過程”。 ACL-findings(2023)[紙] [代碼]
- TOPKG :“ TopKg:通過全球知識圖表的面向目標的對話框”。 Coling(2022)[紙] [代碼]
- TGCP :“目標引導的開放域對話計劃”。 Coling(2022)[紙] [代碼]
- FOP :“對話生成的長期控制:方法和評估”。 NAACL(2022)[紙] [代碼]
- CODA :“使用常識性和數據增強的目標引導的對話響應生成”。 naacl-findings(2022)[紙] [代碼]
- Otters :“ Otters:開放域對話的一轉主題過渡”。 ACL(2021)[紙] [數據]
- CG-nar :“清楚地思考,快速交談:開放域對話系統的概念引導的非自動回歸產生”。 EMNLP(2021)[紙] [代碼]
- 杜肯夫:“主動人機對話,具有明確的對話目標”。 ACL(2019)[紙] [代碼]
- CKC :“關鍵字引導的神經對話模型”。 AAAI(2021)[紙] [代碼]
- Knowhrl :“知識圖基於開放域對話生成的目標計劃”。 AAAI(2020)[紙]
- DKRN :“目標引導的開放域對話的動態知識路由網絡”。 AAAI(2020)[紙] [代碼]
- TGCONV :“目標引導的開放域對話”。 ACL(2019)[紙] [代碼]
非授權對話(說服與談判)
- 旅行:“力量在於差異!通過量身定制的策略計劃朝著有效的非授權對話邁進。” Arxiv(2024)[紙]
- INA :“ INA:通過基於獎勵的對話系統增強談判策略的綜合方法”。 EMNLP(2023)[紙] [數據]
- I-Pro :“與非合作用戶互動:主動對話策略的新範式”。 Sigir(2022)[紙]
- PAAD :“邁向意識到的自主對話代理人”。 NAACL(2022)[紙] [代碼]
- persrfi :“改進與模仿:通過強化學習和人類示威來減少說服對話的重複和不一致”。 emnlp-findings(2021)[紙] [代碼]
- Resper :“ Resper:在計算上建模有說服力對話中的抵抗策略”。 EACL(2021)[紙] [代碼]
- ARDM :“與大規模預訓練的語言模型交替的複發對話模型”。 EACL(2021)[紙] [代碼]
- 撥號儀:“撥號儀:將可解釋的策略圖網絡納入談判對話”。 ICLR(2021)[紙] [代碼]
- 談判tom :“改善與人格建模談判的對話系統”。 ACL(2021)[紙] [代碼]
- Fehed :“使用明確的語義和戰略對話記錄增強非授權對話系統”。 ICLR(2020)[紙] [代碼]
- CTX-PSA :“學習計劃並分別實現開放式對話系統”。 emnlp-findings(2020)[紙] [代碼]
- 談判教練:“有效談判的動態戰略教練”。 Sigdial(2019)[紙] [代碼]
- 說服力庫氏:“善意:建立一個個性化的有說服力的對話體系,以實現社會善良”。 ACL(2019)[紙] [數據]
- Craigslistbargain :“在談判對話中解耦策略和發電”。 EMNLP(2018)[紙] [數據]
?回到頂部
個性化對話
基於角色的對話
- LLM-WEREWOLF :“探索通信游戲的大型語言模型:關於狼人的實證研究”。 Arxiv(2023)[紙]
- Chatharuhi :“ Chatharuhi:通過大語言模型在現實中恢復動漫角色”。 Arxiv(2023)[報告] [代碼]
- DPCD :“ Hi Sheldon!從電視節目中創建深厚的個性化角色”。 Arxiv(2023)[紙] [數據]
- 康奈爾(Cornell)富裕:“使用豐富的元數據註釋對屏幕字符的個性化語言建模”。 Arxiv(2023)[紙] [數據]
- KNUDGE :“非本體論忠實的非玩家角色對話”。 Arxic(2022)[紙]
- HPD :“大型語言模型與哈利·波特(Harry Potter)結識:雙語數據集,用於使對話代理與角色保持一致”。 Arxiv(2022)[紙] [數據]
- 撥號故事:“理解和在故事中角色之間的對話的基準”。 Arxiv(2022)[紙]
- CAYALL :“建立角色指定的開放域對話系統利用大規模語言模型”。 NAACL(2022)[紙] [數據]
- PDP :“結識您最喜歡的角色:開放域聊天機器人模仿虛構的角色,只有幾句話”。 NAACL(2022)[紙] [代碼]
- RPA :“我是我還是你?最先進的對話模型無法保持身份”。 NAACL-FINDINGS(2022)[紙]
- PrineChat :“ Pranemchat:通過對話和聊天機器人進行漸進的表現來支持虛構人物的創建”。 ACM C&C(2021)[紙]
- 阿羅哈:“阿羅哈:對對話代理人人的人工學習”。 AAAI(2020)[紙] [代碼]
- 光:“學習在幻想文本冒險遊戲中說話和行動”。 EMNLP(2019)[紙] [數據]
人格意識對話
- UBPL :“通過不受歡迎的個性化詞典來定制大語言模型中的人格特徵”。 Arxiv(2023)[紙]
- PraneChat :“ Pranemchat:學習具有個性化社會支持的對話人AI”。 Arxiv(2023)[紙] [代碼]
- CHATGPT-MBTI :“ Chatgpt可以評估人格嗎?一個一般評估框架”。 Arxiv(2023)[紙] [代碼]
- 提示性格:“與零射擊及時的學習對話中的人格風格”。 IWSD(2023)[紙]
- CPED :“ CPED:一個大規模的中國個性化和情感對話數據集,用於對話AI”。 Arxiv(2022)[紙] [數據]
- PELD :“自動選擇情感以通過受人格影響的情緒轉變來響應”。 ACL-findings(2021)[紙] [數據]
- Friendspersona :“使用細心網絡和上下文嵌入的獨白和多方對話的自動基於文本的個性識別”。 AAAI-Student摘要(2020)[紙] [數據]
- APR :“使用多方對話中的重疊動態來識別性格特徵”。 Interspeech(2019)[紙]
- 個人迪拉格:“具有多元化特徵的個性化對話產生”。 Arxiv(2019)[紙] [數據]
- Personagenlg :“通過神經自然語言發生器控制基於人格的風格變化”。 Sigdial(2018)[紙] [數據]
基於角色的對話
- Comperdial :“ Comperdial:常識性角色對話數據集和基準”。 Arxiv(2024)[紙]
- IDL :“”在我們學習的對話中:“通過內部學科學習進行個性化對話,而無需預先定義的個人資料”。 Arxiv(2024)[紙]
- Dialogicl :“制定良好的提示或提供示例性的對話?研究基於角色的對話生成的文本學習的研究”。 Arxiv(2024)[紙]
- Varmi :“建立角色一致的對話代理與離線加強學習”。 EMNLP(2023)[紙] [代碼]
- OPELA :“當人群遇到角色時:創建一個大規模的開放域角色對話語料庫”。 Arxiv(2023)[紙] [數據]
- 原始:“通過對訂單不敏感的代表正規化建立強大的個性化對話生成”。 ACL-findings(2023)[紙] [代碼]
- CLV :“通過對比的潛在變量增強個性化的對話產生:結合稀疏和密集的角色”。 ACL(2023)[紙] [代碼]
- SIMOAP :“ SIMOAP:通過過度採樣和評估來提高基於角色的對話生成的連貫性和一致性”。 ACL(2023)[紙] [代碼]
- LMEDR :“學習為角色一致的對話記憶和話語關係的記憶”。 AAAI(2023)[紙] [代碼]
- 檢索到預測:“通過延伸角色的對話中的人格一致性提高”。 CIKM(2022)[紙] [代碼]
- Intient-Persona :“具有隱式用戶角色檢測的個性化對話生成器”。 Coling(2022)[紙]
- CareCallMemory :“讓我更新!長期對話中的內存管理”。 EMNLP-findings(2022)[紙] [數據]
- PersonadeFense :“您不知道我最喜歡的顏色:防止對話表示揭示說話者的私人角色”。 NAACL(2022)[紙] [代碼]
- 及時調整:“通過及時調整構建個性化對話系統”。 NAACL-SRW(2022)[紙]
- Dulemon :“長時間看不到!長期角色記憶的開放域對話”。 ACL-findings(2022)[紙] [數據]
- 信息:“您真正理解我的需求:知識和友好的對話代理人以知識和角色為基礎”。 emnlp-findings(2022)[紙] [代碼]
- 重點:“呼籲定制對話:自定義對話接地角色和知識”。 AAAI(2022)[紙] [代碼]
- MSP :“更少的是:學習為個性化對話的創造來完善對話歷史的歷史”。 NAACL(2022)[紙]
- GME :“通過接地最小的編輯通過可轉移的角色接地對話”。 EMNLP(2021)[紙] [代碼]
- 鮑勃:“鮑勃:伯特·伯特(Bert Bert of Bert),用於培訓有限個性化數據的基於角色的對話模型”。 ACL(2021)[紙] [代碼]
- PABST :“與背景故事無監督的角色接地對話”。 ACL(2021)[紙] [代碼]
- DHAP :“每人一個聊天機器人:基於隱式用戶配置文件創建個性化的聊天機器人”。 Sigir(2021)[紙]
- PCHATBOT :“ PCHATBOT:個性化聊天機器人的大規模數據集”。 Sigir(2021)[紙] [數據]
- Compac :“喜歡遠足?您可能喜歡自然:與人物的對話和常識性擴展”。 EMNLP(2020)[紙] [代碼]
- 務實的一致性:“我聽起來像我嗎?通過務實的自我意識改善對話中的角色一致性”。 EMNLP(2020)[紙] [代碼]
- Xpersona :“ Xpersona:評估多語言個性化聊天機器人”。 Arxiv(2020)[紙] [數據]
- KVPI :“開放域對話代理的配置文件一致性識別”。 EMNLP(2020)[紙] [代碼]
- GDR :“生成,刪除和重寫:改善對話生成角色一致性的三階段框架”。 ACL(2020)[紙]
- p^2bot :“你給我留下了深刻的印象:通過相互角色感知產生對話”。 ACL(2020)[紙] [代碼]
- RCDG :“通過利用自然語言推論來產生角色一致的對話”。 AAAI(2020)[紙] [代碼]
- Persona-sparse :“具有角色 - 帕斯斯數據的基於培訓的個性化對話生成模型”。 AAAI(2020)[紙]
- Personawae :“通過增強的Wasserstein AutoCoders在連續空間中為響應產生的個性化建模”。 Emnlp(2019)[紙]
- PAML :“通過元學習個性化對話代理”。 ACL(2019)[紙] [代碼]
- 人類法:“個性化對話代理:我有一隻狗,你也有寵物嗎?” ACL(2018)[紙] [數據]
- PCCM :“將個性/個人資料分配給聊天計算機,以產生連貫的對話”。 IJCAI(2018)[紙]
?回到頂部
情感對話
情感支持對話
- 偏好偏見:“大型語言模型能否成為良好的情感支持者?減輕對情感支持對話的偏好偏見”。 ACL(2024)[紙]
- ESCOT :“ ESCOT:朝著可解釋的情感支持對話系統邁進”。 ACL(2024)[紙] [代碼]
- 鬆餅:“鬆餅:通過多方面的AI反饋來減輕情感支持對話中的無濟於事”。 ACL-findings(2024)[紙] [代碼]
- DDRCU :“對情感支持對話的動態演示檢索和認知理解”。 Sigir(2024)[紙] [代碼]
- Kemi :“知識增強的情感支持對話的混合定位對話系統”。 ACL(2023)[紙] [代碼]
- CSCONV :“具有多源知識融合的認知知識融合的認知刺激系統,具有認知障礙的長者”。 ACL(2023)[紙] [代碼]
- Augesc :“ Augesc:與大型語言模型進行對話進行對話,以進行情感支持對話”。 ACL找到(2023)[紙]
- TransESC :“ Transesc:通過轉彎狀態過渡來平滑情感支持對話”。 ACL-findings(2023)[紙] [代碼]
- PAL :“ PAL:角色增強的情感支持對話產生”。 ACL-findings(2023)[紙] [代碼]
- MultiSC :“通過LookAhead策略計劃改善多轉彎情感支持對話的產生”。 EMNLP(2022)[紙] [代碼]
- MISC :“ MISC:一種混合的戰略意識模型,將彗星集成為情感支持對話”。 ACL(2022)[紙] [代碼]
- C3KG :“ C3KG:中國常識對話知識圖”。 ACL-findings(2022)[紙] [數據]
- GLHG :“全球控制,在本地理解:情感支持對話的全球到本地分層圖網絡”。 IJCAI(2022)[紙]
- 埃斯蒂夫:“走向情感支持對話系統”。 ACL(2021)[紙] [數據]
善解人意的對話
- StickerConv :“ StickerConv:從頭開始生成多模式同理反應”。 ACL(2024)[紙] [數據]
- 感知性:“與人類般的代理人交談:通過可感知的聲音接受和反應進行善解人意的對話”。 ACL(2024)[紙] [代碼]
- 電子核心:“電子核:情感相關性增強了同理心對話的產生” EMNLP(2023)[紙]
- empsoa :“不要迷失自己!通過明確的自我意識來產生同情心的響應”。 ACL-findings(2023)[紙] [代碼]
- 案例:“案例:對善解人意的反應產生的粗到精美的認知和感情對齊”。 ACL(2023)[紙] [代碼]
- 護理:“護理:通過有條件圖生成的促進反應的因果關係”。 emnlp-findings(2022)[紙] [代碼]
- EMPGPT-3 :“ GPT-3是否會產生同理心對話?一種新穎的文本示例選擇方法和自動評估指標,用於促進對話的產生”。 Coling(2022)[紙] [代碼]
- posemodial :“以積極的情緒啟發邁向多轉彎的善解人意對話”。 Arxiv(2022)[紙]
- CEM :“ CEM:常識性感知的善解人意反應產生”。 AAAI(2022)[紙] [代碼]
- Gee :“引起情感原因的善解人意反應的觀點和實用主義者”。 EMNLP(2021)[紙] [代碼]
- RECEC :“通過識別對話中的情緒原因改善善解人心的反應產生”。 emnlp-findings(2021)[紙] [代碼]
- COMAE :“ COMAE:善解人意的響應產生的多因素分層框架”。 ACL-findings(2021)[紙] [代碼]
- 護理:“護理:具有潛在概念的共識性情感反應產生”。 AAAI(2021)[紙] [代碼]
- EMPDG :“ EMPDG:多分辨率互動交互式對話產生”。 Coling(2020)[紙] [代碼]
- Mime :“啞劇:模仿情緒,以產生同理心反應的產生”。 EMNLP(2020)[紙] [代碼]
- PEC :“邁向基於角色的移情對話模型”。 EMNLP(2020)[紙] [代碼]
- 穆爾:“穆爾:善解人意的聽眾的混合物”。 EMNLP(2019)[紙] [代碼]
- 善解人意的人:“走向善解人意的開放域對話模型:新的基準和數據集”。 ACL(2019)[紙] [數據]
- EMOD :“在對話中產生特定情緒的響應”。 ACL(2019)[紙]
- Mojitalk :“ Mojitalk:大規模產生情感反應”。 ACL(2018)[紙]
- ECM :“情感聊天機:具有內部和外部記憶的情感對話”。 AAAI(2018)[紙] [代碼]
?回到頂部
建議對話和CRS
- TCP-Dial :“跟隨我:目標驅動的推薦對話系統的對話計劃”。 Arxiv(2022)[紙] [代碼]
- 克斯:“ KERS:具有多個子目標的推薦對話系統的知識增強框架”。 emnlp-findings(2021)[紙] [代碼]
- durecdial2.0 :“ durecdial 2.0:雙語平行語料庫,用於對話推薦”。 EMNLP(2021)[紙] [代碼]
- durecdial :“通過多類對話進行對話建議”。 ACL(2020)[紙] [代碼]
- TG-REDIAL :“針對主題引導的對話推薦系統”。 Coling(2020)[紙] [代碼]
- 啟發:“靈感:邁向社交建議對話系統”。 EMNLP(2020)[紙] [數據]
- Gorecdial :“推薦作為通信游戲:以目標對話進行自我監督的機器人遊戲”。 EMNLP(2019)[紙] [代碼]
- CRS-Survey :“對會話推薦系統的調查”。 ACM計算調查(2021)[紙]
- CRS-Survey :“會話推薦系統的進步和挑戰:調查”。 Arxiv(2021)[紙]
- CRSLAB :“ CRSLAB:用於構建對話推薦系統的開源工具包”。 Arxiv(2021)[紙] [代碼]
- MESE :“通過上下文感知項目元信息提高對話推薦系統的質量”。 NAACL(2022)[紙] [代碼]
- C2-CRS :“ C2-CRS:對會話推薦系統的粗到最細對的對比學習”。 WSDM(2022)[紙] [代碼]
- BotPlay : "Self-Supervised Bot Play for Conversational Recommendation with Justifications". arXiv(2021) [paper]
- RID : "Finetuning Large-Scale Pre-trained Language Models for Conversational Recommendation with Knowledge Graph". arXiv(2021) [paper] [code]
- CRFR : "CRFR: Improving Conversational Recommender Systems via Flexible Fragments Reasoning on Knowledge Graphs". EMNLP(2021) [paper]
- NTRD : "Learning Neural Templates for Recommender Dialogue System". EMNLP(2021) [paper] [code]
- CR-Walker : "CR-Walker: Tree-Structured Graph Reasoning and Dialog Acts for Conversational Recommendation". EMNLP(2021) [paper] [code]
- RevCore : "RevCore: Review-augmented Conversational Recommendation". ACL-Findings(2021) [paper] [code]
- KECRS : "KECRS: Towards Knowledge-Enriched Conversational Recommendation System". arXiv(2021) [paper]
- FPAN : "Adapting User Preference to Online Feedback in Multi-round Conversational Recommendation". WSDM(2021) [paper] [code]
- UNICORN : "Unified Conversational Recommendation Policy Learning via Graph-based Reinforcement Learning". SIGIR(2021) [paper] [code]
- KGSF : "Improving Conversational Recommender Systems via Knowledge Graph based Semantic Fusion". KDD(2020) [paper] [code]
- CPR : "Interactive Path Reasoning on Graph for Conversational Recommendation". KDD(2020) [paper] [code]
- EAR : "Estimation-Action-Reflection: Towards Deep Interaction Between Conversational and Recommender Systems". WSDM(2020) [paper] [code]
- KBRD : "Towards Knowledge-Based Recommender Dialog System". EMNLP(2019) [paper] [code]
- ReDial : "Towards Deep Conversational Recommendations". NeurIPS(2018) [paper] [data]
?回到頂部
Knowledge-grounded Dialogue
- DOCTOR : "Dialogue Chain-of-Thought Distillation for Commonsense-aware Conversational Agents". EMNLP(2023) [paper] [code] [demo]
- GATE : "Well Begun is Half Done: Generator-agnostic Knowledge Pre-Selection for Knowledge-Grounded Dialogue". EMNLP(2023) [paper] [code]
- CONNER : "Beyond Factuality: A Comprehensive Evaluation of Large Language Models as Knowledge Generators". EMNLP(2023) [paper] [code]
- K-DIAL : "Improving Factual Consistency for Knowledge-Grounded Dialogue Systems via Knowledge Enhancement and Alignment". EMNLP-Findings(2023) [paper]
- GLM-Dialog : "GLM-Dialog: Noise-tolerant Pre-training for Knowledge-grounded Dialogue Generation". arXiv(2023) [paper] [code]
- RHO : "RHO (ρ): Reducing Hallucination in Open-domain Dialogues with Knowledge Grounding". ACL-Findings(2023) [paper] [code]
- MultiRefKGC : "There Is No Standard Answer: Knowledge-Grounded Dialogue Generation with Adversarial Activated Multi-Reference Learning". EMNLP(2022) [paper] [code]
- CorefDiffs : "CorefDiffs: Co-referential and Differential Knowledge Flow in Document Grounded Conversations". COLING(2022) [paper] [code]
- DTR : "Stylized Knowledge-Grounded Dialogue Generation via Disentangled Template Rewriting". NAACL(2022) [paper] [code]
- XDAI : "XDAI: A Tuning-free Framework for Exploiting Pre-trained Language Models in Knowledge Grounded Dialogue Generation". KDD(2022) [paper] [code]
- PersonaKGC : "There Are a Thousand Hamlets in a Thousand People's Eyes: Enhancing Knowledge-grounded Dialogue with Personal Memory". ACL(2022) [paper] [code]
- KI : "Lexical Knowledge Internalization for Neural Dialog Generation". ACL(2022) [paper] [code]
- DiffKG : "Towards Large-Scale Interpretable Knowledge Graph Reasoning for Dialogue Systems". ACL-Findings(2022) [paper] [code]
- KSAM : "KSAM: Infusing Multi-Source Knowledge into Dialogue Generation via Knowledge Source Aware Multi-Head Decoding". ACL-Findings(2022) [paper]
- MDSP : "Multi-Stage Prompting for Knowledgeable Dialogue Generation". ACL-Findings(2022) [paper] [code]
- FSB : "Few-Shot Bot: Prompt-Based Learning for Dialogue Systems". arXiv(2021) [paper] [code]
- P-GDG : "Exploring Prompt-based Few-shot Learning for Grounded Dialog Generation". arXiv(2021) [paper]
- KAT-TSLF : "A Three-Stage Learning Framework for Low-Resource Knowledge-Grounded Dialogue Generation". EMNLP(2021) [paper] [code]
- DIALKI : "DIALKI: Knowledge Identification in Conversational Systems through Dialogue-Document Contextualization". EMNLP(2021) [paper] [code]
- CoLV : "CoLV: A Collaborative Latent Variable Model for Knowledge-Grounded Dialogue Generation". EMNLP(2021) [paper]
- SKT-KG : "Augmenting Knowledge-grounded Conversations with Sequential Knowledge Transition". NAACL(2021) [paper]
- MSKE : "More is Better: Enhancing Open-Domain Dialogue Generation via Multi-Source Heterogeneous Knowledge". EMNLP(2021) [paper] [code]
- EARL : "EARL: Informative Knowledge-Grounded Conversation Generation with Entity-Agnostic Representation Learning". EMNLP(2021) [paper] [code]
- KGD-CF : "Increasing Faithfulness in Knowledge-Grounded Dialogue with Controllable Features". ACL(2021) [paper]
- SECE : "Space Efficient Context Encoding for Non-Task-Oriented Dialogue Generation with Graph Attention Transformer". ACL(2021) [paper] [code]
- MIKe : "Initiative-Aware Self-Supervised Learning for Knowledge-Grounded Conversations". SIGIR(2021) [paper] [code]
- GOKC : "Learning to Copy Coherent Knowledge for Response Generation". AAAI(2021) [paper] [code]
- KnowledGPT : "Knowledge-Grounded Dialogue Generation with Pre-trained Language Models". EMNLP(2020) [paper] [code]
- DiffKS : "Difference-aware Knowledge Selection for Knowledge-grounded Conversation Generation". EMNLP-Findings(2020) [paper] [code]
- DukeNet : "DukeNet: A Dual Knowledge Interaction Network for Knowledge-Grounded Conversation". SIGIR(2020) [paper] [code]
- CCN : "Cross Copy Network for Dialogue Generation". EMNLP(2020) [paper] [code]
- PIPM : "Bridging the Gap between Prior and Posterior Knowledge Selection for Knowledge-Grounded Dialogue Generation". EMNLP(2020) [paper]
- ConceptFlow : "Grounded Conversation Generation as Guided Traverses in Commonsense Knowledge Graphs". ACL(2020) [paper] [code]
- ConKADI : "Diverse and Informative Dialogue Generation with Context-Specific Commonsense Knowledge Awareness". ACL(2020) [paper] [code]
- KIC : "Generating Informative Conversational Response using Recurrent Knowledge-Interaction and Knowledge-Copy". ACL(2020) [paper]
- SKT : "Sequential Latent Knowledge Selection for Knowledge-Grounded Dialogue". ICLR(2020) [paper] [code]
- KdConv : "KdConv: A Chinese Multi-domain Dialogue Dataset Towards Multi-turn Knowledge-driven Conversation". ACL(2020) [paper] [data]
- TransDG : "Improving Knowledge-aware Dialogue Generation via Knowledge Base Question Answering". AAAI(2020) [paper] [code]
- RefNet : "RefNet: A Reference-aware Network for Background Based Conversation". AAAI(2020) [paper] [code]
- GLKS : "Thinking Globally, Acting Locally: Distantly Supervised Global-to-Local Knowledge Selection for Background Based Conversation". AAAI(2020) [paper] [code]
- AKGCM : "Knowledge Aware Conversation Generation with Explainable Reasoning over Augmented Graphs". EMNLP(2019) [paper] [code]
- DyKgChat : "DyKgChat: Benchmarking Dialogue Generation Grounding on Dynamic Knowledge Graphs". EMNLP(2019) [paper] [code]
- OpenDialKG : "OpenDialKG: Explainable Conversational Reasoning with Attention-based Walks over Knowledge Graphs". ACL(2019) [paper] [data]
- WoW : "Wizard of Wikipedia: Knowledge-Powered Conversational agents". ICLR(2019) [paper]
- PostKS : "Learning to Select Knowledge for Response Generation in Dialog Systems". IJCAI(2019) [paper] [code-1] [code-2]
- NKD : "Knowledge Diffusion for Neural Dialogue Generation". ACL(2018) [paper] [data]
- Dual Fusion : "Smarter Response with Proactive Suggestion: A New Generative Neural Conversation Paradigm". IJCAI(2018) [paper]
- CCM : "Commonsense Knowledge Aware Conversation Generation with Graph Attention". IJCAI(2018) [paper] [code-tf] [code-py]
- MTask : "A Knowledge-Grounded Neural Conversation Model". AAAI(2018) [paper]
- GenDS : "Flexible End-to-End Dialogue System for Knowledge Grounded Conversation". arXiv(2017) [paper]
?回到頂部
Task-oriented Dialogue
- P-ToD : "Personalizing Task-oriented Dialog Systems via Zero-shot Generalizable Reward Function". CIKM(2022) [paper]
- Dialogic : "Dialogic: Controllable Dialogue Simulation with In-Context Learning". EMNLP-Findings(2022) [paper] [code]
- KB-Adapter : "Injecting Domain Knowledge in Language Models for Task-Oriented Dialogue Systems". EMNLP(2022) [paper] [code]
- TacoBot : "Bootstrapping a User-Centered Task-Oriented Dialogue System". Proceedings of Alexa Prize TaskBot(2021) [paper]
- USDA : "User Satisfaction Estimation with Sequential Dialogue Act Modeling in Goal-oriented Conversational Systems". WWW(2022) [paper] [code]
- USS : "Simulating User Satisfaction for the Evaluation of Task-oriented Dialogue Systems". SIGIR(2021) [paper] [data]
- NS-Dial : "An Interpretable Neuro-Symbolic Reasoning Framework for Task-Oriented Dialogue Generation". ACL(2022) [paper] [code]
- GALAXY : "GALAXY: A Generative Pre-trained Model for Task-Oriented Dialog with Semi-Supervised Learning and Explicit Policy Injection". AAAI(2022) [paper] [code]
- PPTOD : "Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue System". arXiv(2021) [paper] [code]
- ToDCL : "Continual Learning in Task-Oriented Dialogue Systems". EMNLP(2021) [paper] [code]
- IR-Net : "Intention Reasoning Network for Multi-Domain End-to-end Task-Oriented Dialogue". EMNLP(2021) [paper]
- HyKnow : "HyKnow: End-to-End Task-Oriented Dialog Modeling with Hybrid Knowledge Management". ACL-Findings(2021) [paper] [code]
- DDMN : "Dual Dynamic Memory Network for End-to-End Multi-turn Task-oriented Dialog Systems". COLING(2020) [paper] [code]
- ToD-BERT : "ToD-BERT: Pre-trained Natural Language Understanding for Task-Oriented Dialogues". EMNLP(2020) [paper] [code]
- GraphDialog : "GraphDialog: Integrating Graph Knowledge into End-to-End Task-Oriented Dialogue Systems". EMNLP(2020) [paper] [code]
- MARCO : "Multi-Domain Dialogue Acts and Response Co-Generation". ACL(2020) [paper] [code]
- DF-Net : "Dynamic Fusion Network for Multi-Domain End-to-end Task-Oriented Dialog". ACL(2020) [paper] [code]
- MALA : "MALA: Cross-Domain Dialogue Generation with Action Learning". AAAI(2020) [paper]
- SGD : "Towards Scalable Multi-domain Conversational Agents: The Schema-Guided Dialogue Dataset". AAAI(2020) [paper] [data]
- CrossWOZ : "CrossWOZ: A Large-Scale Chinese Cross-Domain Task-Oriented Dialogue Dataset". TACL(2020) [paper] [code]
- MultiWOZ : "MultiWOZ - A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling". EMNLP(2018) [paper] [code]
- Neural Task-Oriented Dialogue : "Learning to Memorize in Neural Task-Oriented Dialogue Systems". MPhil Thesis(2019) [paper]
- GLMP : "Global-to-local Memory Pointer Networks for Task-Oriented Dialogue". ICLR(2019) [paper] [code]
- KB Retriever : "Entity-Consistent End-to-end Task-Oriented Dialogue System with KB Retriever". EMNLP(2019) [paper] [data]
- TRADE : "Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systems". ACL(2019) [paper] [code]
- WMM2Seq : "A Working Memory Model for Task-oriented Dialog Response Generation". ACL(2019) [paper]
- Pretrain-Fine-tune : "Training Neural Response Selection for Task-Oriented Dialogue Systems". ACL(2019) [paper] [data]
- Multi-level Mem : "Multi-Level Memory for Task Oriented Dialogs". NAACL(2019) [paper] [code]
- BossNet : "Disentangling Language and Knowledge in Task-Oriented Dialogs ". NAACL(2019) [paper] [code]
- SDN : "Subgoal Discovery for Hierarchical Dialogue Policy Learning". EMNLP(2018) [paper]
- D3Q : "Discriminative Deep Dyna-Q: Robust Planning for Dialogue Policy Learning". EMNLP(2018) [paper] [code]
- DDQ : "Deep Dyna-Q: Integrating Planning for Task-Completion Dialogue Policy Learning". ACL(2018) [paper] [code]
- MAD : "Memory-augmented Dialogue Management for Task-oriented Dialogue Systems". TOIS(2018) [paper]
- TSCP : "Sequicity: Simplifying Task-oriented Dialogue Systems with Single Sequence-to-Sequence Architectures". ACL(2018) [paper] [code]
- Mem2Seq : "Mem2Seq: Effectively Incorporating Knowledge Bases into End-to-End Task-Oriented Dialog Systems". ACL(2018) [paper] [code]
- Topic-Seg-Label : "A Weakly Supervised Method for Topic Segmentation and Labeling in Goal-oriented Dialogues via Reinforcement Learning". IJCAI(2018) [paper] [code]
- AliMe : "AliMe Chat: A Sequence to Sequence and Rerank based Chatbot Engine". ACL(2017) [paper]
- KVR Net : "Key-Value Retrieval Networks for Task-Oriented Dialogue". SIGDIAL(2017) [paper] [data]
?回到頂部
Open-domain Dialogue
Long-term Dialogue
- THEANINE : "THEANINE: Revisiting Memory Management in Long-term Conversations with Timeline-augmented Response Generation". arXiv(2024) [paper]
- LD-Agent : "Hello Again! LLM-powered Personalized Agent for Long-term Dialogue". arXiv(2024) [paper] [code]
- CPD : "Position Debiasing Fine-Tuning for Causal Perception in Long-Term Dialogue". IJCAI(2024) [paper]
- TemporalMemory : "Toward Conversational Agents with Context and Time Sensitive Long-term Memory". arXiv(2024) [paper] [data]
- LoCoMo : "Evaluating Very Long-Term Conversational Memory of LLM Agents". ACL(2024) [paper] [data]
- Conversation Chronicles : "Conversation Chronicles: Towards Diverse Temporal and Relational Dynamics in Multi-Session Conversations". EMNLP(2023) [paper] [data]
- GapChat : "Mind the Gap Between Conversations for Improved Long-Term Dialogue Generation". EMNLP-Findings(2023) [paper] [data]
- UniMC : "UniMC: A Unified Framework for Long-Term Memory Conversation via Relevance Representation Learning". arXiv(2023) [paper]
- RS : "Recursively Summarizing Enables Long-Term Dialogue Memory in Large Language Models". arXiv(2023) [paper]
- MSC : "Beyond Goldfish Memory: Long-Term Open-Domain Conversation". ACL(2022) [paper] [data]
Response Generation
- Overview : "Open-domain Dialogue Generation: What We Can Do, Cannot Do, And Should Do Next". ACL-NLP4ConvAI(2022) [paper]
- Chirpy Cardinal : "Neural Generation Meets Real People: Building a Social, Informative Open-Domain Dialogue Agent". SIGDIAL(2022) [paper] [code] [project]
- TIL : "Towards Efficient Dialogue Pre-training with Transferable and Interpretable Latent Structure". EMNLP(2022) [paper]
- ProphetChat : "ProphetChat: Enhancing Dialogue Generation with Simulation of Future Conversation". ACL(2022) [paper]
- DialoFlow : "Conversations Are Not Flat: Modeling the Dynamic Information Flow across Dialogue Utterances". ACL(2021) [paper] [code]
- DiSCoL : "DiSCoL: Toward Engaging Dialogue Systems through Conversational Line Guided Response Generation". NAACL(2021) [paper] [code]
- DialogBERT : "DialogBERT: Discourse-Aware Response Generation via Learning to Recover and Rank Utterances". AAAI(2021) [paper]
- BlenderBot : "Recipes for Building an Open-Domain Chatbot". EACL(2021) [paper] [code]
- CDial-GPT : "A Large-Scale Chinese Short-Text Conversation Dataset". NLPCC(2020) [paper] [code]
- DialoGPT : "DialoGPT : Large-Scale Generative Pre-training for Conversational Response Generation". ACL(2020) [paper] [code]
- CG-Policy : "Conversational Graph Grounded Policy Learning for Open-Domain Conversation Generation". ACL(2020) [paper]
- PLATO-XL : "PLATO-XL: Exploring the Large-scale Pre-training of Dialogue Generation". arXiv(2021) [paper] [code]
- PLATO-2 : "PLATO-2: Towards Building an Open-Domain Chatbot via Curriculum Learning". ACL-Findings(2021) [paper] [code]
- PLATO : "PLATO: Pre-trained Dialogue Generation Model with Discrete Latent Variable". ACL(2020) [paper] [code]
- Guyu : "An Empirical Investigation of Pre-Trained Transformer Language Models for Open-Domain Dialogue Generation". arXiv(2020) [paper] [code]
- CL4Dialogue : "Group-wise Contrastive Learning for Neural Dialogue Generation". EMNLP-Findings(2020) [paper] [code]
- Neg-train : "Negative Training for Neural Dialogue Response Generation". ACL(2020) [paper] [code]
- HDSA : "Semantically Conditioned Dialog Response Generation via Hierarchical Disentangled Self-Attention". ACL(2019) [paper] [code]
- CAS : "Skeleton-to-Response: Dialogue Generation Guided by Retrieval Memory". NAACL(2019) [paper] [code]
- Edit-N-Rerank : "Response Generation by Context-aware Prototype Editing". AAAI(2019) [paper] [code]
- HVMN : "Hierarchical Variational Memory Network for Dialogue Generation". WWW(2018) [paper] [code]
- XiaoIce : "The Design and Implementation of XiaoIce, an Empathetic Social Chatbot". arXiv(2018) [paper]
- D2A : "Dialog-to-Action: Conversational Question Answering Over a Large-Scale Knowledge Base". NeurIPS(2018) [paper] [code]
- DAIM : "Generating Informative and Diverse Conversational Responses via Adversarial Information Maximization". NeurIPS(2018) [paper]
- REASON : "Dialog Generation Using Multi-turn Reasoning Neural Networks". NAACL(2018) [paper]
- STD/HTD : "Learning to Ask Questions in Open-domain Conversational Systems with Typed Decoders". ACL(2018) [paper] [code]
- CSF : "Generating Informative Responses with Controlled Sentence Function". ACL(2018) [paper] [code]
- DAWnet : "Chat More: Deepening and Widening the Chatting Topic via A Deep Model". SIGIR(2018) [paper] [code]
- ZSDG : "Zero-Shot Dialog Generation with Cross-Domain Latent Actions". SIGDIAL(2018) [paper] [code]
- DUA : "Modeling Multi-turn Conversation with Deep Utterance Aggregation". COLING(2018) [paper] [code]
- Data-Aug : "Sequence-to-Sequence Data Augmentation for Dialogue Language Understanding". COLING(2018) [paper] [code]
- DC-MMI : "Generating More Interesting Responses in Neural Conversation Models with Distributional Constraints". EMNLP(2018) [paper] [code]
- cVAE-XGate/CGate : "Better Conversations by Modeling, Filtering, and Optimizing for Coherence and Diversity". EMNLP(2018) [paper] [code]
- Retrieval+multi-seq2seq : "An Ensemble of Retrieval-Based and Generation-Based Human-Computer Conversation Systems". IJCAI(2018) [paper]
- DAM : "Multi-Turn Response Selection for Chatbots with Deep Attention Matching Network". ACL(2018) [paper] [code]
- SMN : "Sequential Matching Network: A New Architecture for Multi-turn Response Selection in Retrieval-Based Chatbots". ACL(2017) [paper] [code]
- CVAE/KgCVAE : "Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders". ACL(2017) [paper] [code]
- TA-Seq2Seq : "Topic Aware Neural Response Generation". AAAI(2017) [paper] [code]
- MA : "Mechanism-Aware Neural Machine for Dialogue Response Generation". AAAI(2017) [paper]
- VHRED : "A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues". AAAI(2017) [paper] [code]
- HRED : "Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models". AAAI(2016) [paper] [code]
- RL-Dialogue : "Deep Reinforcement Learning for Dialogue Generation". EMNLP(2016) [paper]
- MMI : "A Diversity-Promoting Objective Function for Neural Conversation Models". NAACL(2016) [paper] [code]
?回到頂部
Dialogue Evaluation
- DialogBench : "DialogBench: Evaluating LLMs as Human-like Dialogue Systems". NAACL(2024) [paper] [code]
- ChatEval : "ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate". arXiv(2023) [paper] [code]
- ACCENT : "ACCENT: An Automatic Event Commonsense Evaluation Metric for Open-Domain Dialogue Systems". ACL(2023) [paper] [code]
- LLMEval : "Understanding the Effectiveness of Very Large Language Models on Dialog Evaluation". IWSDS(2023) [paper]
- ChatEvalPlatform : "Don't Forget Your ABC's: Evaluating the State-of-the-Art in Chat-Oriented Dialogue Systems". arXiv(2022) [paper] [code]
- MDD-Eval : "MDD-Eval: Self-Training on Augmented Data for Multi-Domain Dialogue Evaluation". AAAI(2022) [paper] [code]
- Self-Eval : "SelF-Eval: Self-supervised Fine-grained Dialogue Evaluation". COLING(2022) [paper] [code]
- FineD-Eval : "FineD-Eval: Fine-grained Automatic Dialogue-Level Evaluation". EMNLP(2022) [paper] [code]
- FlowEval : "FlowEval: A Consensus-Based Dialogue Evaluation Framework Using Segment Act Flows". EMNLP(2022) [paper]
- IM2 : "IM^2: an Interpretable and Multi-category Integrated Metric Framework for Automatic Dialogue Evaluation". EMNLP(2022) [paper] [code]
- Q^2 : "$Q^{2}$: Evaluating Factual Consistency in Knowledge-Grounded Dialogues via Question Generation and Question Answering". EMNLP(2021) [paper] [code]
- QuantiDCE : "Towards Quantifiable Dialogue Coherence Evaluation". ACL(2021) [paper] [code]
- DynaEval : "DynaEval: Unifying Turn and Dialogue Level Evaluation". ACL(2021) [paper] [code]
- Review : "How to Evaluate Your Dialogue Models: A Review of Approaches". arXiv(2021) [paper]
- ConvLabEval : "Is Your Goal-Oriented Dialog Model Performing Really Well? Empirical Analysis of System-wise Evaluation". SIGDIAL(2020) [paper]
- FED : "Unsupervised Evaluation of Interactive Dialog with DialoGPT". SIGDIAL(2020) [paper] [code] [data]
- Spot-the-Bot : "Spot The Bot: A Robust and Efficient Framework for the Evaluation of Conversational Dialogue Systems". EMNLP(2020) [paper] [code]
- CMADE : "Beyond User Self-Reported Likert Scale Ratings: A Comparison Model for Automatic Dialog Evaluation". ACL(2020) [paper] [code]
- Coherence : "Dialogue Coherence Assessment Without Explicit Dialogue Act Labels". ACL(2020) [paper] [code]
- MAUDE : "Learning an Unreferenced Metric for Online Dialogue Evaluation". ACL(2020) [paper] [code]
- GRADE : "GRADE: Automatic Graph-Enhanced Coherence Metric for Evaluating Open-Domain Dialogue Systems". ACL(2020) [paper] [code]
- uBLEU : "uBLEU: Uncertainty-Aware Automatic Evaluation Method for Open-Domain Dialogue Systems". ACL(2020) [paper] [code]
- USR : "USR: An Unsupervised and Reference Free Evaluation Metric for Dialog Generation". ACL(2020) [paper] [code]
- ACUTE-EVAL : "ACUTE-EVAL: Improved Dialogue Evaluation with Optimized Questions and Multi-turn Comparisons". NIPS ConvAI Workshop(2019) [paper] [code]
- InteractiveEval : "Approximating Interactive Human Evaluation with Self-Play for Open-Domain Dialog Systems". NeurIPS(2019) [paper] [code]
- ChatEval : "ChatEval: A Tool for Chatbot Evaluation". NAACL(2019) [paper] [project]
- ADVMT : "One
Ruler for All Languages: Multi-Lingual Dialogue Evaluation with Adversarial Multi-Task Learning". IJCAI(2018) [paper]
?回到頂部
Dialogue Misc.
- Signed-dialogue : "Generating Signed Language Instructions in Large-Scale Dialogue Systems". NAACL(2024) [paper] [data]
- Dialogue-KT : "Exploring Knowledge Tracing in Tutor-Student Dialogues". arXiv(2024) [paper] [code]
- MathDial : "MathDial: A Dialogue Tutoring Dataset with Rich Pedagogical Properties Grounded in Math Reasoning Problems". EMNLP-Findings(2023) [paper] [data]
- EduChat : "EduChat: A Large-Scale Language Model-based Chatbot System for Intelligent Education". arXiv(2023) [paper] [code]
- ACT : "Learning to Clarify: Multi-turn Conversations with Action-Based Contrastive Self-Training". arXiv(2024) [paper]
- ReviewMT : "Peer Review as A Multi-Turn and Long-Context Dialogue with Role-Based Interactions". arXiv(2024) [paper] [code]
- WildChat : "WildChat: 1M ChatGPT Interaction Logs in the Wild". ICLR(2024) [paper] [data]
- DialOp : "Decision-Oriented Dialogue for Human-AI Collaboration". arXiv(2023) [paper] [code]
- DialogStudio : "DialogStudio: Towards Richest and Most Diverse Unified Dataset Collection for Conversational AI". arXiv(2023) [paper] [code]
- MPC : "Multi-Party Chat: Conversational Agents in Group Settings with Humans and Models". arXiv(2023) [paper] [code]
- SODA : "SODA: Million-scale Dialogue Distillation with Social Commonsense Contextualization". EMNLP(2023) [paper] [code]
- speaker-adaptation : "Speaking the Language of Your Listener: Audience-Aware Adaptation via Plug-and-Play Theory of Mind". ACL-Findings(2023) [paper] [code]
- SocialDial : "SocialDial: A Benchmark for Socially-Aware Dialogue Systems". SIGIR(2023) [paper] [data]
- BotsTalk : "BotsTalk: Machine-sourced Framework for Automatic Curation of Large-scale Multi-skill Dialogue Datasets". EMNLP(2022) [paper] [code]
- Dialogic : "Dialogic: Controllable Dialogue Simulation with In-Context Learning". EMNLP-Findings(2022) [paper] [code]
- ProsocialDialog : "ProsocialDialog: A Prosocial Backbone for Conversational Agents". EMNLP(2022) [paper] [code]
- MIC : "The Moral Integrity Corpus: A Benchmark for Ethical Dialogue Systems". ACL(2022) [paper] [code]
- MoralDial : "MoralDial: A Framework to Train and Evaluate Moral Dialogue Systems via Constructing Moral Discussions". arXiv(2022) [paper]
- DECODE : "I like fish, especially dolphins: Addressing Contradictions in Dialogue Modeling". ACL(2021) [paper] [code]
?回到頂部
Natural Language Generation
Survey on NLG
- CTG : "A Survey of Controllable Text Generation using Transformer-based Pre-trained Language Models". arXiv(2022) [paper]
- RTG : "A Survey on Retrieval-Augmented Text Generation". arXiv(2022) [paper]
- Hallucination : "Survey of Hallucination in Natural Language Generation". arXiv(2022) [paper]
- Evaluation : "A Survey of Evaluation Metrics Used for NLG Systems". arXiv(2020) [paper]
?回到頂部
NLG Theories and Techniques
- RED : "Decoder-Only or Encoder-Decoder? Interpreting Language Model as a Regularized Encoder-Decoder". arXiv(2023) [paper]
- LaMemo : "LaMemo: Language Modeling with Look-Ahead Memory". NAACL(2022) [paper] [code]
- PTG : "Learning to Transfer Prompts for Text Generation". NAACL(2022) [paper] [code]
- EISL : "Don't Take It Literally: An Edit-Invariant Sequence Loss for Text Generation". NAACL(2022) [paper] [code]
- CT-Loss : "A Simple Contrastive Learning Objective for Alleviating Neural Text Degeneration". arXiv(2022) [paper] [code]
- SimCTG : "A Contrastive Framework for Neural Text Generation". NeurIPS(2022) [paper] [code]
- CoNT : "CoNT: Contrastive Neural Text Generation". NeurIPS(2022) [paper] [code]
- Two-level-CL : "Keywords and Instances: A Hierarchical Contrastive Learning Framework Unifying Hybrid Granularities for Text Generation". ACL(2022) [paper]
- CLAPS : "Contrastive Learning with Adversarial Perturbations for Conditional Text Generation". ICLR(2021) [paper] [code]
- RetGen : "RetGen: A Joint framework for Retrieval and Grounded Text Generation Modeling". AAAI(2022) [paper] [code]
- RAG : "Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks". NeurIPS(2020) [paper] [code]
- TextGAIL : "TextGAIL: Generative Adversarial Imitation Learning for Text Generation". AAAI(2021) [paper] [code]
- Latent-GLAT : " latent -GLAT: Glancing at Latent Variables for Parallel Text Generation". ACL(2022) [paper] [code]
- s2s-ft : "s2s-ft: Fine-Tuning Pretrained Transformer Encoders for Sequence-to-Sequence Learning". arXiv(2021) [paper] [code]
- EBM : "Exposure Bias versus Self-Recovery: Are Distortions Really Incremental for Autoregressive Text Generation?". EMNLP(2021) [paper]
- DiscoDVT : "DiscoDVT: Generating Long Text with Discourse-Aware Discrete Variational Transformer". EMNLP(2021) [paper] [code]
- DATG : "Data Augmentation for Text Generation Without Any Augmented Data". ACL(2021) [paper]
- JointGT : "JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge Graphs". ACL-Findings(2021) [paper] [code]
- Embedding-Transfer : "Bridging Subword Gaps in Pretrain-Finetune Paradigm for Natural Language Generation". ACL(2021) [paper] [code]
- FastSeq : "EL-Attention: Memory Efficient Lossless Attention for Generation". ICML(2021) [paper] [code]
- BERTSeq2Seq : "Leveraging Pre-trained Checkpoints for Sequence Generation Tasks". TACL(2020) [paper] [code-tf] [code-py]
- ERNIE-GEN : "ERNIE-GEN: An Enhanced Multi-Flow Pre-training and Fine-tuning Framework for Natural Language Generation". IJCAI(2020) [paper] [code]
- DITTO : "Learning to Break the Loop: Analyzing and Mitigating Repetitions for Neural Text Generation". NeurIPS(2022) [paper] [code]
- Repetition-Problem : "A Theoretical Analysis of the Repetition Problem in Text Generation". AAAI(2021) [paper] [code]
- ENCONTER : "ENCONTER: Entity Constrained Progressive Sequence Generation via Insertion-based Transformer". EACL(2021) [paper] [code]
- POINTER : "POINTER: Constrained Progressive Text Generation via Insertion-based Generative Pre-training". EMNLP(2020) [paper] [code]
- Cascaded Generation : "Cascaded Text Generation with Markov Transformers". NeurIPS(2020) [paper] [code]
- SFOT : "Improving Text Generation with Student-Forcing Optimal Transport". EMNLP(2020) [paper]
- OT-Seq2Seq : "Improving Sequence-to-Sequence Learning via Optimal Transport". ICLR(2019) [paper] [code]
?回到頂部
Diffusion Models for NLG
- RenderDiffusion : "RenderDiffusion: Text Generation as Image Generation". arXiv(2023) [paper]
- Masked-Diffusion-LM : "A Cheaper and Better Diffusion Language Model with Soft-Masked Noise". arXiv(2023) [paper] [code]
- discrete-diffusion : "A Reparameterized Discrete Diffusion Model for Text Generation". arXiv(2023) [paper] [code]
- Difformer : "Difformer: Empowering Diffusion Models on the Embedding Space for Text Generation". arXiv(2023) [paper]
- GENIE : "Text Generation with Diffusion Language Models: A Pre-training Approach with Continuous Paragraph Denoise". arXiv(2022) [paper] [code]
- SED : "Self-conditioned Embedding Diffusion for Text Generation". arXiv(2022) [paper]
- SSD-LM : "SSD-LM: Semi-autoregressive Simplex-based Diffusion Language Model for Text Generation and Modular Control". arXiv(2022) [paper] [code]
- LD4LG : "Latent Diffusion for Language Generation". arXiv(2022) [paper] [code]
- DiffusionBERT : "DiffusionBERT: Improving Generative Masked Language Models with Diffusion Models". arXiv(2022) [paper] [code]
- DiffusER : "DiffusER: Discrete Diffusion via Edit-based Reconstruction". arXiv(2022) [paper] [code]
- SeqDiffuSeq : "SeqDiffuSeq: Text Diffusion with Encoder-Decoder Transformers". arXiv(2022) [paper] [code]
- DiffuSeq : "DiffuSeq: Sequence to Sequence Text Generation with Diffusion Models". ICLR(2023) [paper] [code]
- Diffusion-LM : "Diffusion-LM Improves Controllable Text Generation". NeurIPS(2022) [paper] [code]
- D3PM : "Structured Denoising Diffusion Models in Discrete State-Spaces". NeurIPS(2021) [paper] [code]
?回到頂部
Controllable Generation
- ConGenBench : "Controllable Text Generation in the Instruction-Tuning Era". arXiv(2024) [paper] [code]
- GeLaTo : "Tractable Control for Autoregressive Language Generation". arXiv(2023) [paper]
- Cognac : "Controllable Text Generation with Language Constraints". arXiv(2022) [paper] [code]
- CriticControl : "Critic-Guided Decoding for Controlled Text Generation". arXiv(2022) [paper]
- LatentOps : "Composable Text Controls in Latent Space with ODEs". arXiv(2022) [paper] [code]
- FAST : "FAST: Improving Controllability for Text Generation with Feedback Aware Self-Training". arXiv(2022) [paper]
- DisCup : "DisCup: Discriminator Cooperative Unlikelihood Prompt-tuning for Controllable Text Generation". EMNLP(2022) [paper] [code]
- MultiControl : "A Distributional Lens for Multi-Aspect Controllable Text Generation". EMNLP(2022) [paper] [code]
- NADO : "Controllable Text Generation with Neurally-Decomposed Oracle". NeurIPS(2022) [paper] [code]
- Mix-Match : "Mix and Match: Learning-free Controllable Text Generation using Energy Language Models". ACL(2022) [paper] [code]
- ControlPrefix : "Controllable Natural Language Generation with Contrastive Prefixes". ACL-Findings(2022) [paper]
- MUCOCO : "Controlled Text Generation as Continuous Optimization with Multiple Constraints". NeurIPS(2021) [paper] [code]
- DExperts : "DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Experts". ACL(2021) [paper] [code]
- FUDGE : "FUDGE: Controlled Text Generation With Future Discriminators". NAACL(2021) [paper] [code]
- GeDi : "GeDi: Generative Discriminator Guided Sequence Generation". EMNLP-Findings(2021) [paper] [code]
- GDC : "A Distributional Approach to Controlled Text Generation". ICLR(2021) [paper] [code]
- CoCon : "CoCon: A Self-Supervised Approach for Controlled Text Generation". ICLR(2021) [paper] [code]
- PPLM : "Plug and Play Language Models: A Simple Approach to Controlled Text Generation". ICLR(2020) [paper] [code]
- CTRL : "CTRL: A Conditional Transformer Language Model for Controllable Generation". arXiv(2019) [paper] [code]
?回到頂部
Text Planning
- CoScript : "Distilling Script Knowledge from Large Language Models for Constrained Language Planning". ACL(2023) [paper] [code]
- RSTGen : "RSTGen: Imbuing Fine-Grained Interpretable Control into Long-FormText Generators". NAACL(2022) [paper]
- Time Control : "Language Modeling via Stochastic Processes". ICLR(2022) [paper] [code]
- PLANET : "PLANET: Dynamic Content Planning in Autoregressive Transformers for Long-form Text Generation". ACL(2022) [paper]
- EventPlan : "Event Transition Planning for Open-ended Text Generation". ACL-Findings(2022) [paper] [code]
- CETP : "Knowledge-based Review Generation by Coherence Enhanced Text Planning". SIGIR(2021) [paper]
- PlanGen : "Plan-then-Generate: Controlled Data-to-Text Generation via Planning". EMNLP-Findings(2021) [paper] [code]
- DYPLOC : "DYPLOC: Dynamic Planning of Content Using Mixed Language Models for Text Generation". ACL(2021) [paper] [code]
- Tree-PLAN : "Infobox-to-text Generation with Tree-like Planning based Attention Network". IJCAI(2020) [paper]
- ProphetNet : "ProphetNet: Predicting Future N-gram for Sequence-to-Sequence Pre-training". EMNLP-Findings(2020) [paper] [code]
- PAIR : "PAIR: Planning and Iterative Refinement in Pre-trained Transformers for Long Text Generation". EMNLP(2020) [paper] [code]
- SentPlan : "Sentence-Level Content Planning and Style Specification for Neural Text Generation". EMNLP(2019) [paper] [code]
- PHVM : "Long and Diverse Text Generation with Planning-based Hierarchical Variational Model". EMNLP(2019) [paper] [code]
- TwinNet : "Twin Networks: Matching the Future for Sequence Generation". ICLR(2018) [paper] [code]
- PAG : "Plan, Attend, Generate: Planning for Sequence-to-Sequence Models". NIPS(2017) [paper]
?回到頂部
Decoding Algorithms
- Speculative Decoding : "Speculative Decoding: Exploiting Speculative Execution for Accelerating Seq2seq Generation". EMNLP-Findings(2023) [paper] [code]
- Medusa : "Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads". Github(2023) [Blog] [code]
- Lookahead Decoding : "Breaking the Sequential Dependency of LLM Inference Using Lookahead Decoding". LMSYS Org(2023) [Blog] [code]
- Speculative Sampling : "Accelerating Large Language Model Decoding with Speculative Sampling". arXiv(2023) [paper]
- Speculative Decoding : "Fast Inference from Transformers via Speculative Decoding". ICML(2023) [paper] [code]
- Parallel Decoding : "Accelerating Transformer Inference for Translation via Parallel Decoding". ACL(2023) [paper] [code]
- EAD : "The Stable Entropy Hypothesis and Entropy-Aware Decoding: An Analysis and Algorithm for Robust Natural Language Generation". arXiv(2023) [paper] [code]
- Contrastive Search : "Contrastive Search Is What You Need For Neural Text Generation". TMLR(2023) [paper] [code] [blog]
- Momentum Decoding : "Momentum Decoding: Open-ended Text Generation As Graph Exploration". arXiv(2022) [paper] [code]
- Crowd Sampling : "Follow the Wisdom of the Crowd: Effective Text Generation via Minimum Bayes Risk Decoding". arXiv(2022) [paper] [code]
- RankGen : "RankGen: Improving Text Generation with Large Ranking Models". EMNLP(2022) [paper] [code]
- Contrastive Decoding : "Contrastive Decoding: Open-ended Text Generation as Optimization". arXiv(2022) [paper] [code]
- COLD : "COLD Decoding: Energy-based Constrained Text Generation with Langevin Dynamics". NeurIPS(2022) [paper] [code]
- Lattice : "Massive-scale Decoding for Text Generation using Lattices". NAACL(2022) [paper] [code]
- KID : "Knowledge Infused Decoding". ICLR(2022) [paper] [code]
- NeuroLogic A*esque : "NeuroLogic A *esque Decoding: Constrained Text Generation with Lookahead Heuristics". NAACL(2022) [paper] [code]
- NeuroLogic : "NeuroLogic Decoding: (Un)supervised Neural Text Generation with Predicate Logic Constraints". NAACL(2021) [paper] [code]
- DeLorean : "Back to the Future: Unsupervised Backprop-based Decoding for Counterfactual and Abductive Commonsense Reasoning". EMNLP(2020) [paper] [code]
- Top-p (Nucleus) Sampling : "The Curious Case of Neural Text Degeneration". ICLR(2020) [paper] [code]
- BP Decoding : "Blockwise Parallel Decoding for Deep Autoregressive Models". NIPS(2018) [paper]
- Disjunctive Constraints : "Guided Generation of Cause and Effect". IJCAI(2020) [paper] [code-huggingface]
- CGMH : "CGMH: Constrained Sentence Generation by Metropolis-Hastings Sampling". AAAI(2019) [paper] [code]
- DBS : "Directed Beam Search: Plug-and-Play Lexically Constrained Language Generation". arXiv(2020) [paper] [code]
- DBA : "Fast Lexically Constrained Decoding with Dynamic Beam Allocation for Neural Machine Translation". NAACL(2018) [paper] [code-official] [code-fairseq]
- GBS : "Lexically Constrained Decoding for Sequence Generation Using Grid Beam Search". ACL(2017) [paper] [code]
?回到頂部
NLG Evaluation
- Survey : "Leveraging Large Language Models for NLG Evaluation: A Survey". arXiv(2024) [paper]
- BBScore : "BBScore: A Brownian Bridge Based Metric for Assessing Text Coherence". AAAI(2024) [paper]
- GPTEval : "GPTEval: NLG Evaluation using GPT-4 with Better Human Alignment". arXiv(2023) [paper]
- GPTScore : "GPTScore: Evaluate as You Desire". arXiv(2023) [paper] [code]
- RoMe : "RoMe: A Robust Metric for Evaluating Natural Language Generation". ACL(2022) [paper] [code]
- EAD : "Rethinking and Refining the Distinct Metric". ACL(2022) [paper] [code]
- MID : "Mutual Information Divergence: A Unified Metric for Multimodal Generative Models". NeurIPS(2022) [paper]
- DiscoScore : "DiscoScore: Evaluating Text Generation with BERT and Discourse Coherence". arXiv(2022) [paper] [code]
- CTC-Score : "Compression, Transduction, and Creation: A Unified Framework for Evaluating Natural Language Generation". EMNLP(2021) [paper] [code]
- BLEURT : "BLEURT: Learning Robust Metrics for Text Generation". ACL(2020) [paper] [code]
?回到頂部