tweetnlp
init
TweetNLP pour tous les amateurs de PNL travaillant sur Twitter et les médias sociaux! La bibliothèque Python tweetnlp fournit une collection d'outils utiles pour analyser / comprendre les tweets tels que l'analyse des sentiments, la prédiction des emoji et la reconnaissance de l'entalité nommée, propulsée par la modélisation de la langue de pointe spécialisée sur les réseaux sociaux.
NOUVELLES (décembre 2022): Nous avons présenté un papier de démonstration TweetNLP ("TweetNLP: Traitement du langage naturel de pointe pour les médias sociaux"), à EMNLP 2022. La version finale peut être trouvée ici.
Tweetnlp Hugging Face Page Tous les principaux modèles TweetNLP peuvent être trouvés ici sur le visage étreint.
Ressources:
Table des matières:
Installez TweetNLP via PIP sur votre console.
pip install tweetnlp Dans cette section, vous apprendrez à obtenir les modèles et les ensembles de données avec tweetnlp . Les modèles suivent le modèle HuggingFace et les ensembles de données sont au format des ensembles de données HuggingFace. Des introductions faciles de modèles et d'ensembles de données HuggingFace doivent être trouvés sur la page Web HuggingFace, alors veuillez les vérifier si vous êtes nouveau dans HuggingFace.
Le module de classification se compose de six tâches différentes (classification des sujets, analyse des sentiments, détection d'ironie, détection de discours de haine, détection de langage offensive, prédiction des emoji et analyse des émotions). Dans chaque exemple, le modèle est instancié par tweetnlp.load_model("task-name") et exécutez la prédiction en passant un texte ou une liste de textes comme argument à la fonction correspondante.
import tweetnlp
# MULTI-LABEL MODEL
model = tweetnlp . load_model ( 'topic_classification' ) # Or `model = tweetnlp.TopicClassification()`
model . topic ( "Jacob Collier is a Grammy-awarded English artist from London." ) # Or `model.predict`
> >> { 'label' : [ 'celebrity_&_pop_culture' , 'music' ]}
# Note: the probability of the multi-label model is the output of sigmoid function on binary prediction whether each topic is positive or negative.
model . topic ( "Jacob Collier is a Grammy-awarded English artist from London." , return_probability = True )
> >> { 'label' : [ 'celebrity_&_pop_culture' , 'music' ],
'probability' : { 'arts_&_culture' : 0.037371691316366196 ,
'business_&_entrepreneurs' : 0.010188567452132702 ,
'celebrity_&_pop_culture' : 0.92448890209198 ,
'diaries_&_daily_life' : 0.03425711765885353 ,
'family' : 0.00796138122677803 ,
'fashion_&_style' : 0.020642118528485298 ,
'film_tv_&_video' : 0.08062587678432465 ,
'fitness_&_health' : 0.006343095097690821 ,
'food_&_dining' : 0.0042883665300905704 ,
'gaming' : 0.004327300935983658 ,
'learning_&_educational' : 0.010652057826519012 ,
'music' : 0.8291937112808228 ,
'news_&_social_concern' : 0.24688217043876648 ,
'other_hobbies' : 0.020671198144555092 ,
'relationships' : 0.020371075719594955 ,
'science_&_technology' : 0.0170074962079525 ,
'sports' : 0.014291072264313698 ,
'travel_&_adventure' : 0.010423899628221989 ,
'youth_&_student_life' : 0.008605164475739002 }}
# SINGLE-LABEL MODEL
model = tweetnlp . load_model ( 'topic_classification' , multi_label = False ) # Or `model = tweetnlp.TopicClassification(multi_label=False)`
model . topic ( "Jacob Collier is a Grammy-awarded English artist from London." )
> >> { 'label' : 'pop_culture' }
# NOTE: the probability of the sinlge-label model the softmax over the label.
model . topic ( "Jacob Collier is a Grammy-awarded English artist from London." , return_probability = True )
> >> { 'label' : 'pop_culture' ,
'probability' : { 'arts_&_culture' : 9.20625461731106e-05 ,
'business_&_entrepreneurs' : 6.916998972883448e-05 ,
'pop_culture' : 0.9995898604393005 ,
'daily_life' : 0.00011083036952186376 ,
'sports_&_gaming' : 8.668467489769682e-05 ,
'science_&_technology' : 5.152115045348182e-05 }}
# GET DATASET
dataset_multi_label , label2id_multi_label = tweetnlp . load_dataset ( 'topic_classification' )
dataset_single_label , label2id_single_label = tweetnlp . load_dataset ( 'topic_classification' , multi_label = False ) import tweetnlp
# ENGLISH MODEL
model = tweetnlp . load_model ( 'sentiment' ) # Or `model = tweetnlp.Sentiment()`
model . sentiment ( "Yes, including Medicare and social security saving?" ) # Or `model.predict`
> >> { 'label' : 'positive' }
model . sentiment ( "Yes, including Medicare and social security saving?" , return_probability = True )
> >> { 'label' : 'positive' , 'probability' : { 'negative' : 0.004584966693073511 , 'neutral' : 0.19360853731632233 , 'positive' : 0.8018065094947815 }}
# MULTILINGUAL MODEL
model = tweetnlp . load_model ( 'sentiment' , multilingual = True ) # Or `model = tweetnlp.Sentiment(multilingual=True)`
model . sentiment ( "天気が良いとやっぱり気持ち良いなあ" )
> >> { 'label' : 'positive' }
model . sentiment ( "天気が良いとやっぱり気持ち良いなあ" , return_probability = True )
> >> { 'label' : 'positive' , 'probability' : { 'negative' : 0.028369612991809845 , 'neutral' : 0.08128828555345535 , 'positive' : 0.8903420567512512 }}
# GET DATASET (ENGLISH)
dataset , label2id = tweetnlp . load_dataset ( 'sentiment' )
# GET DATASET (MULTILINGUAL)
for l in [ 'all' , 'arabic' , 'english' , 'french' , 'german' , 'hindi' , 'italian' , 'portuguese' , 'spanish' ]:
dataset_multilingual , label2id_multilingual = tweetnlp . load_dataset ( 'sentiment' , multilingual = True , task_language = l ) import tweetnlp
# MODEL
model = tweetnlp . load_model ( 'irony' ) # Or `model = tweetnlp.Irony()`
model . irony ( 'If you wanna look like a badass, have drama on social media' ) # Or `model.predict`
> >> { 'label' : 'irony' }
model . irony ( 'If you wanna look like a badass, have drama on social media' , return_probability = True )
> >> { 'label' : 'irony' , 'probability' : { 'non_irony' : 0.08390884101390839 , 'irony' : 0.9160911440849304 }}
# GET DATASET
dataset , label2id = tweetnlp . load_dataset ( 'irony' ) import tweetnlp
# MODEL
model = tweetnlp . load_model ( 'hate' ) # Or `model = tweetnlp.Hate()`
model . hate ( 'Whoever just unfollowed me you a bitch' ) # Or `model.predict`
> >> { 'label' : 'not-hate' }
model . hate ( 'Whoever just unfollowed me you a bitch' , return_probability = True )
> >> { 'label' : 'non-hate' , 'probability' : { 'non-hate' : 0.7263831496238708 , 'hate' : 0.27361682057380676 }}
# GET DATASET
dataset , label2id = tweetnlp . load_dataset ( 'hate' ) import tweetnlp
# MODEL
model = tweetnlp . load_model ( 'offensive' ) # Or `model = tweetnlp.Offensive()`
model . offensive ( "All two of them taste like ass." ) # Or `model.predict`
> >> { 'label' : 'offensive' }
model . offensive ( "All two of them taste like ass." , return_probability = True )
> >> { 'label' : 'offensive' , 'probability' : { 'non-offensive' : 0.16420328617095947 , 'offensive' : 0.8357967734336853 }}
# GET DATASET
dataset , label2id = tweetnlp . load_dataset ( 'offensive' ) import tweetnlp
# MODEL
model = tweetnlp . load_model ( 'emoji' ) # Or `model = tweetnlp.Emoji()`
model . emoji ( 'Beautiful sunset last night from the pontoon @TupperLakeNY' ) # Or `model.predict`
> >> { 'label' : '?' }
model . emoji ( 'Beautiful sunset last night from the pontoon @TupperLakeNY' , return_probability = True )
> >> { 'label' : '?' ,
'probability' : { '❤' : 0.13197319209575653 ,
'?' : 0.11246423423290253 ,
'?' : 0.008415069431066513 ,
'?' : 0.04842926934361458 ,
'' : 0.014528146013617516 ,
'?' : 0.1509675830602646 ,
'?' : 0.08625403046607971 ,
'' : 0.01616635173559189 ,
'?' : 0.07396604865789413 ,
'?' : 0.03033279813826084 ,
'?' : 0.16525287926197052 ,
'??' : 0.020336611196398735 ,
'☀' : 0.00799981877207756 ,
'?' : 0.016111424192786217 ,
'' : 0.012984540313482285 ,
'?' : 0.012557178735733032 ,
'?' : 0.031386848539114 ,
'?' : 0.006829539313912392 ,
'?' : 0.04188741743564606 ,
'?' : 0.011156936176121235 }}
# GET DATASET
dataset , label2id = tweetnlp . load_dataset ( 'emoji' ) import tweetnlp
# MULTI-LABEL MODEL
model = tweetnlp . load_model ( 'emotion' ) # Or `model = tweetnlp.Emotion()`
model . emotion ( 'I love swimming for the same reason I love meditating...the feeling of weightlessness.' ) # Or `model.predict`
> >> { 'label' : 'joy' }
# Note: the probability of the multi-label model is the output of sigmoid function on binary prediction whether each topic is positive or negative.
model . emotion ( 'I love swimming for the same reason I love meditating...the feeling of weightlessness.' , return_probability = True )
> >> { 'label' : 'joy' ,
'probability' : { 'anger' : 0.00025800734874792397 ,
'anticipation' : 0.0005329723935574293 ,
'disgust' : 0.00026112011983059347 ,
'fear' : 0.00027552215033210814 ,
'joy' : 0.7721399068832397 ,
'love' : 0.1806265264749527 ,
'optimism' : 0.04208092764019966 ,
'pessimism' : 0.00025325192837044597 ,
'sadness' : 0.0006160663324408233 ,
'surprise' : 0.0005619609728455544 ,
'trust' : 0.002393839880824089 }}
# SINGLE-LABEL MODEL
model = tweetnlp . load_model ( 'emotion' ) # Or `model = tweetnlp.Emotion()`
model . emotion ( 'I love swimming for the same reason I love meditating...the feeling of weightlessness.' ) # Or `model.predict`
> >> { 'label' : 'joy' }
# NOTE: the probability of the sinlge-label model the softmax over the label.
model . emotion ( 'I love swimming for the same reason I love meditating...the feeling of weightlessness.' , return_probability = True )
> >> { 'label' : 'optimism' , 'probability' : { 'joy' : 0.01367587223649025 , 'optimism' : 0.7345258593559265 , 'anger' : 0.1770714670419693 , 'sadness' : 0.07472680509090424 }}
# GET DATASET
dataset , label2id = tweetnlp . load_dataset ( 'emotion' )AVERTISSEMENT: Le modèle d'émotion unique et multi-étiquettes a un ensemble d'étiquettes diinifent (une seule marque a quatre classes de `` joie '' / `` optimisme '' / 'colère' / 'tristesse', tandis que le multi-étiquette a onze classes de `` joie '' / `` optimisme '' / `` colère '' / 'tristesse' / 'Love' / 'Trust' / 'Fear' / 'surprise' / '/ Anticipation' / Disguster '/ Dégir' / crainte '/' surprise '/' / Anticipation '/ Anticipation' / Disguster '/ Dégir' / PEUSMISME '/ SURPPRIENT' / Anticipation '.
Ce module se compose d'un modèle de reconnaissance de l'entité nommée (NER) spécifiquement formé pour les tweets. Le modèle est instancié par tweetnlp.load_model("ner") et exécute la prédiction en donnant un texte ou une liste de textes comme argument à la fonction ner (vérifiez le document ici, ou la page de jeu de données HuggingFace).
import tweetnlp
# MODEL
model = tweetnlp . load_model ( 'ner' ) # Or `model = tweetnlp.NER()`
model . ner ( 'Jacob Collier is a Grammy-awarded English artist from London.' ) # Or `model.predict`
> >> [{ 'type' : 'person' , 'entity' : 'Jacob Collier' }, { 'type' : 'event' , 'entity' : ' Grammy' }, { 'type' : 'location' , 'entity' : ' London' }]
# Note: the probability for the predicted entity is the mean of the probabilities over the sub-tokens representing the entity.
model . ner ( 'Jacob Collier is a Grammy-awarded English artist from London.' , return_probability = True ) # Or `model.predict`
> >> [
{ 'type' : 'person' , 'entity' : 'Jacob Collier' , 'probability' : 0.9905318220456442 },
{ 'type' : 'event' , 'entity' : ' Grammy' , 'probability' : 0.19164378941059113 },
{ 'type' : 'location' , 'entity' : ' London' , 'probability' : 0.9607000350952148 }
]
# GET DATASET
dataset , label2id = tweetnlp . load_dataset ( 'ner' ) Ce module se compose d'un modèle de réponse à des questions spécifiquement formé pour les tweets. Le modèle est instancié par tweetnlp.load_model("question_answering") , et exécute la prédiction en donnant une question ou une liste de questions avec un contexte ou une liste de contextes comme argument à la fonction question_answering (consultez le document ici, ou la page de jeu de données HUGGINGFFACE).
import tweetnlp
# MODEL
model = tweetnlp . load_model ( 'question_answering' ) # Or `model = tweetnlp.QuestionAnswering()`
model . question_answering (
question = 'who created the post as we know it today?' ,
context = "'So much of The Post is Ben,' Mrs. Graham said in 1994, three years after Bradlee retired as editor. 'He created it as we know it today.'— Ed O'Keefe (@edatpost) October 21, 2014"
) # Or `model.predict`
> >> { 'generated_text' : 'ben' }
# GET DATASET
dataset = tweetnlp . load_dataset ( 'question_answering' ) Ce module se compose d'une génération de paires de questions et de réponses spécialement formée pour les tweets. Le modèle est instancié par tweetnlp.load_model("question_answer_generation") , et exécute la prédiction en donnant un contexte ou une liste de contextes comme argument à la fonction question_answer_generation (vérifiez le document ici, ou la page de jeu de données HuggingFace).
import tweetnlp
# MODEL
model = tweetnlp . load_model ( 'question_answer_generation' ) # Or `model = tweetnlp.QuestionAnswerGeneration()`
model . question_answer_generation (
text = "'So much of The Post is Ben,' Mrs. Graham said in 1994, three years after Bradlee retired as editor. 'He created it as we know it today.'— Ed O'Keefe (@edatpost) October 21, 2014"
) # Or `model.predict`
> >> [
{ 'question' : 'who created the post?' , 'answer' : 'ben' },
{ 'question' : 'what did ben do in 1994?' , 'answer' : 'he retired as editor' }
]
# GET DATASET
dataset = tweetnlp . load_dataset ( 'question_answer_generation' ) Le modèle de langue masquée prédit le jeton masqué dans la phrase donnée. Ceci est instancié par tweetnlp.load_model('language_model') et exécute la prédiction en donnant un texte ou une liste de textes comme argument à la fonction mask_prediction . Veuillez vous assurer que chaque texte a un jeton <mask> , car c'est finalement le suivant par l'objectif du modèle à prévoir.
import tweetnlp
model = tweetnlp . load_model ( 'language_model' ) # Or `model = tweetnlp.LanguageModel()`
model . mask_prediction ( "How many more <mask> until opening day? ?" , best_n = 2 ) # Or `model.predict`
> >> { 'best_tokens' : [ 'days' , 'hours' ],
'best_scores' : [ 5.498564104033932e-11 , 4.906026140893971e-10 ],
'best_sentences' : [ 'How many more days until opening day? ?' ,
'How many more hours until opening day? ?' ]} Le modèle d'intégration de tweet produit une longueur fixe pour un tweet. L'intégration représente la sémantique par le sens du tweet, et cela peut être utilisé pour la recherche sémantique des tweets en utilisant la similitude entre les intérêts. Le modèle est instancié par tweet_nlp.load_model('sentence_embedding') et exécutez la prédiction en passant un texte ou une liste de textes comme argument à la fonction embedding .
import tweetnlp
model = tweetnlp . load_model ( 'sentence_embedding' ) # Or `model = tweetnlp.SentenceEmbedding()`
# Get sentence embedding
tweet = "I will never understand the decision making of the people of Alabama. Their new Senator is a definite downgrade. You have served with honor. Well done."
vectors = model . embedding ( tweet )
vectors . shape
> >> ( 768 ,)
# Get sentence embedding (multiple inputs)
tweet_corpus = [
"Free, fair elections are the lifeblood of our democracy. Charges of unfairness are serious. But calling an election unfair does not make it so. Charges require specific allegations and then proof. We have neither here." ,
"Trump appointed judge Stephanos Bibas " ,
"If your members can go to Puerto Rico they can get their asses back in the classroom. @CTULocal1" ,
"@PolitiBunny @CTULocal1 Political leverage, science said schools could reopen, teachers and unions protested to keep'em closed and made demands for higher wages and benefits, they're usin Covid as a crutch at the expense of life and education." ,
"Congratulations to all the exporters on achieving record exports in Dec 2020 with a growth of 18 % over the previous year. Well done & keep up this trend. A major pillar of our govt's economic policy is export enhancement & we will provide full support to promote export culture." ,
"@ImranKhanPTI Pakistan seems a worst country in term of exporting facilities. I am a small business man and if I have to export a t-shirt having worth of $5 to USA or Europe. Postal cost will be around $30. How can we grow as an exporting country if this situation prevails. Think about it. #PM" ,
"The thing that doesn’t sit right with me about “nothing good happened in 2020” is that it ignores the largest protest movement in our history. The beautiful, powerful Black Lives Matter uprising reached every corner of the country and should be central to our look back at 2020." ,
"@JoshuaPotash I kinda said that in the 2020 look back for @washingtonpost" ,
"Is this a confirmation from Q that Lin is leaking declassified intelligence to the public? I believe so. If @realDonaldTrump didn’t approve of what @LLinWood is doing he would have let us know a lonnnnnng time ago. I’ve always wondered why Lin’s Twitter handle started with “LLin” https://t.co/0G7zClOmi2" ,
"@ice_qued @realDonaldTrump @LLinWood Yeah 100%" ,
"Tomorrow is my last day as Senator from Alabama. I believe our opportunities are boundless when we find common ground. As we swear in a new Congress & a new President, demand from them that they do just that & build a stronger, more just society. It’s been an honor to serve you."
"The mask cult can’t ever admit masks don’t work because their ideology is based on feeling like a “good person” Wearing a mask makes them a “good person” & anyone who disagrees w/them isn’t They can’t tolerate any idea that makes them feel like their self-importance is unearned" ,
"@ianmSC Beyond that, they put such huge confidence in masks so early with no strong evidence that they have any meaningful benefit, they don’t want to backtrack or admit they were wrong. They put the cart before the horse, now desperate to find any results that match their hypothesis." ,
]
vectors = model . embedding ( tweet_corpus , batch_size = 4 )
vectors . shape
> >> ( 12 , 768 ) sims = []
for n , i in enumerate ( tweet_corpus ):
_sim = model . similarity ( tweet , i )
sims . append ([ n , _sim ])
print ( f'anchor tweet: { tweet } n ' )
for m , ( n , s ) in enumerate ( sorted ( sims , key = lambda x : x [ 1 ], reverse = True )[: 3 ]):
print ( f' - top { m } : { tweet_corpus [ n ] } n - similaty: { s } n ' )
> >> anchor tweet : I will never understand the decision making of the people of Alabama . Their new Senator is a definite downgrade . You have served with honor . Well done .
- top 0 : Tomorrow is my last day as Senator from Alabama . I believe our opportunities are boundless when we find common ground . As we swear in a new Congress & amp ; a new President , demand from them that they do just that & amp ; build a stronger , more just society . It ’ s been an honor to serve you . The mask cult can ’ t ever admit masks don ’ t work because their ideology is based on feeling like a “ good person ” Wearing a mask makes them a “ good person ” & amp ; anyone who disagrees w / them isn ’ t They can ’ t tolerate any idea that makes them feel like their self - importance is unearned
- similaty : 0.7480925982953287
- top 1 : Trump appointed judge Stephanos Bibas
- similaty : 0.6289173306344258
- top 2 : Free , fair elections are the lifeblood of our democracy . Charges of unfairness are serious . But calling an election unfair does not make it so . Charges require specific allegations and then proof . We have neither here .
- similaty : 0.6017154109745276Voici un tableau du modèle par défaut utilisé dans chaque tâche.
| Tâche | Modèle | Ensemble de données |
|---|---|---|
| Classification des sujets (étiquette unique) | Cardiffnlp / Twitter-Roberta-Base-Dec2021-tweet-topic-Single-All | cardiffnlp / tweet_topic_single |
| Classification des sujets (multi-étiquettes) | Cardiffnlp / Twitter-Roberta-Base-Dec2021-tweet-topic-multi-all | cardiffnlp / tweet_topic_multi |
| Analyse des sentiments (multilingue) | Cardiffnlp / Twitter-XLM-Roberta-base-Sentiment | cardiffnlp / tweet_sentiment_multilingual |
| Analyse des sentiments | Cardiffnlp / Twitter-Roberta-Base-Sentiment-Latst | tweet_eval |
| Détection d'ironie | Cardiffnlp / Twitter-Roberta-Base-Irony | tweet_eval |
| Détection de haine | Cardiffnlp / Twitter-Roberta-Base-Hate-Latest | tweet_eval |
| Détection offensive | Cardiffnlp / Twitter-Roberta-base-offensive | tweet_eval |
| Prédiction des emoji | Cardiffnlp / Twitter-Roberta-Base-Emoji | tweet_eval |
| Analyse des émotions (un seul étiquette) | Cardiffnlp / Twitter-Roberta-Base-Emotion | tweet_eval |
| Analyse des émotions (multi-étiquettes) | Cardiffnlp / Twitter-Roberta-Base-Emotion-Multilabel-Latest | TBA |
| Reconnaissance d'entité nommée | Tner / Roberta-Large-Tweetner7-All | tner / tweetner7 |
| Question Répondre | LMQG / T5-SMALL-TWEETQA-QA | LMQG / QG_TWEETQA |
| Question Génération de réponses | LMQG / T5-base-tweetqa-qag | LMQG / QAG_TWEETQA |
| Modélisation des langues | Cardiffnlp / Twitter-Roberta-Base-2021-124M | TBA |
| Tweet Incorpore | Cambridgeltl / Tweet-Roberta-Base-Embeddings-V1 | TBA |
Pour utiliser un autre modèle de ModelHub local / HuggingFace, on peut simplement fournir le chemin du modèle / un alias à la fonction load_model . Vous trouverez ci-dessous un exemple pour charger un modèle pour NER.
import tweetnlp
tweetnlp . load_model ( 'ner' , model_name = 'tner/twitter-roberta-base-2019-90m-tweetner7-continuous' )TweetNLP fournit une interface facile pour affiner les modèles de langage sur les ensembles de données pris en charge par HuggingFace pour l'hébergement de modèle / le réglage fin avec Ray Tune pour la recherche de paramètres.
sentiment , offensive , irony , hate , emotion , topic_classification Les résultats des expériences avec le formateur de tweetnlp peuvent être trouvés dans le tableau suivant. Les résultats sont compétitifs et peuvent être utilisés comme référence pour chaque tâche. Voir la page de classement pour en savoir plus sur les résultats.
| tâche | Langue_model | EVAL_F1 | EVAL_F1_MACRO | EVAL_AFFICATION | lien |
|---|---|---|---|---|---|
| emoji | Cardiffnlp / Twitter-Roberta-Base-2021-124M | 0,46 | 0,35 | 0,46 | Cardiffnlp / Twitter-Roberta-Base-2021-124M-Emoji |
| émotion | Cardiffnlp / Twitter-Roberta-Base-2021-124M | 0,83 | 0,79 | 0,83 | Cardiffnlp / Twitter-Roberta-Base-2021-124M-Emotion |
| détester | Cardiffnlp / Twitter-Roberta-Base-2021-124M | 0,56 | 0,53 | 0,56 | Cardiffnlp / Twitter-Roberta-Base-2021-124m-Hate |
| ironie | Cardiffnlp / Twitter-Roberta-Base-2021-124M | 0,79 | 0,78 | 0,79 | Cardiffnlp / Twitter-Roberta-Base-2021-124M-IRONY |
| offensant | Cardiffnlp / Twitter-Roberta-Base-2021-124M | 0,86 | 0,82 | 0,86 | Cardiffnlp / Twitter-Roberta-Base-2021-124m-offensif |
| sentiment | Cardiffnlp / Twitter-Roberta-Base-2021-124M | 0,71 | 0,72 | 0,71 | Cardiffnlp / Twitter-Roberta-Base-2021-124M-Sentiment |
| topic_classification (single) | Cardiffnlp / Twitter-Roberta-Base-2021-124M | 0.9 | 0.8 | 0.9 | Cardiffnlp / Twitter-Roberta-Base-2021-124M-Topic-Single |
| topic_classification (multi) | Cardiffnlp / Twitter-Roberta-Base-2021-124M | 0,75 | 0,56 | 0,54 | Cardiffnlp / Twitter-Roberta-Base-2021-124M-Topic-Multi |
| Sentiment (multilingue) | Cardiffnlp / Twitter-xlm-Roberta-base | 0,69 | 0,69 | 0,69 | cardiffnlp / twitter-xlm-roberta-bas-sentiment-multitilingue |
L'exemple suivant reproduira notre modèle d'ironie Cardiffnlp / Twitter-Roberta-Base-2021-124M-Irony.
import logging
import tweetnlp
logging . basicConfig ( format = '%(asctime)s %(levelname)-8s %(message)s' , level = logging . INFO , datefmt = '%Y-%m-%d %H:%M:%S' )
# load dataset
dataset , label_to_id = tweetnlp . load_dataset ( "irony" )
# load trainer class
trainer_class = tweetnlp . load_trainer ( "irony" )
# setup trainer
trainer = trainer_class (
language_model = 'cardiffnlp/twitter-roberta-base-2021-124m' , # language model to fine-tune
dataset = dataset ,
label_to_id = label_to_id ,
max_length = 128 ,
split_test = 'test' ,
split_train = 'train' ,
split_validation = 'validation' ,
output_dir = 'model_ckpt/irony'
)
# start model fine-tuning with parameter optimization
trainer . train (
eval_step = 50 , # each `eval_step`, models are validated on the validation set
n_trials = 10 , # number of trial at parameter optimization
search_range_lr = [ 1e-6 , 1e-4 ], # define the search space for learning rate (min and max value)
search_range_epoch = [ 1 , 6 ], # define the search space for epoch (min and max value)
search_list_batch = [ 4 , 8 , 16 , 32 , 64 ] # define the search space for batch size (list of integer to test)
)
# evaluate model on the test set
trainer . evaluate ()
> >> {
"eval_loss" : 1.3228046894073486 ,
"eval_f1" : 0.7959183673469388 ,
"eval_f1_macro" : 0.791350632069195 ,
"eval_accuracy" : 0.7959183673469388 ,
"eval_runtime" : 2.2267 ,
"eval_samples_per_second" : 352.084 ,
"eval_steps_per_second" : 44.01
}
# save model locally (saved at `{output_dir}/best_model` as default)
trainer . save_model ()
# run prediction
trainer . predict ( 'If you wanna look like a badass, have drama on social media' )
> >> { 'label' : 'irony' }
# push your model on huggingface hub
trainer . push_to_hub ( hf_organization = 'cardiffnlp' , model_alias = 'twitter-roberta-base-2021-124m-irony' )Le point de contrôle enregistré peut être chargé comme un modèle personnalisé comme ci-dessous.
import tweetnlp
model = tweetnlp . load_model ( 'irony' , model_name = "model_ckpt/irony/best_model" ) Si split_validation n'est pas donné, Trainer effectuera une seule exécution avec des paramètres par défaut sans recherche de paramètres.
Pour plus de détails, veuillez lire le document de référence du TweetNLP qui l'accompagne. Si vous utilisez TweetNLP dans vos recherches, veuillez utiliser l'entrée bib suivante pour citer le document de référence:
@inproceedings{camacho-collados-etal-2022-tweetnlp,
title={{T}weet{NLP}: {C}utting-{E}dge {N}atural {L}anguage {P}rocessing for {S}ocial {M}edia},
author={Camacho-Collados, Jose and Rezaee, Kiamehr and Riahi, Talayeh and Ushio, Asahi and Loureiro, Daniel and Antypas, Dimosthenis and Boisson, Joanne and Espinosa-Anke, Luis and Liu, Fangyu and Mart{'i}nez-C{'a}mara, Eugenio and others},
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: System Demonstrations",
month = nov,
year = "2022",
address = "Abu Dhabi, U.A.E.",
publisher = "Association for Computational Linguistics",
}
