Note Named Entities Recognition

Note QA dataset

Note Sentiment analysis

Note Text classification

Note Named Entities Recognition

Note Textual entailment

Note Extractive-QA

Note Cross-lingual-QA, Extractive-QA

Note Text classification

Note Paraphrase

Note Semantic Textual Similarity

Note Textual entailmen

Note Text classification

Note Extractive-QA

Note A 435-million-token web corpus of Catalan mainly intended to pretrain language models and word representations.

Note A 19-million-sentence corpus of Catalan user-generated text built from the forums mainly intended to pretrain language models and word representations.

Note A 39-million-token web corpus of Catalan mainly intended to pretrain language models and word representations.

Note A 1760-million-token web corpus of Catalan mainly intended to pretrain language models and word representations.

Note Conversational QA

Note Summarization

Note Emotion and dynamic stance detection

Note Abusive language detection

Note POS tagging

Note Sentiment analysis

Note Emotion, static stance, and dynamic stance detection.

Note Commonsense reasoning

Note Textual entailment

Note Summarization

Note Summarization

Note Language Modeling

Note Question Answering

Note Instruction Tuning

Note Instruction Tuning

Note Question Answering

Note Paraphrase Identification

Note Intent classification, spans identification and examples generation.

Note Multiple Choice Question Answering

Note Multiple Choice Question Answering

Note Multiple Choice Commonsense Reasoning

Note Multiple Choice Question Answering

Note Instruction Tuning