1 |
Rethinking Automatic Evaluation in Sentence Simplification
|
|
|
|
In: https://hal.inria.fr/hal-03199901 ; 2021 (2021)
|
|
BASE
|
|
Show details
|
|
2 |
Synthetic Data Augmentation for Zero-Shot Cross-Lingual Question Answering
|
|
|
|
In: https://hal.inria.fr/hal-03109187 ; 2021 (2021)
|
|
BASE
|
|
Show details
|
|
3 |
QuestEval: Summarization Asks for Fact-based Evaluation
|
|
|
|
In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing ; https://hal.sorbonne-universite.fr/hal-03541895 ; Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, Nov 2021, Punta Cana (en ligne), Dominican Republic. pp.6594-6604, ⟨10.18653/v1/2021.emnlp-main.529⟩ ; https://2021.emnlp.org/ (2021)
|
|
BASE
|
|
Show details
|
|
4 |
MLSUM: The Multilingual Summarization Corpus
|
|
|
|
In: https://hal.sorbonne-universite.fr/hal-02989017 ; 2020 (2020)
|
|
BASE
|
|
Show details
|
|
5 |
MLSUM: The Multilingual Summarization Corpus
|
|
|
|
In: 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) ; https://hal.sorbonne-universite.fr/hal-03364407 ; 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), Nov 2020, Online, France. pp.8051-8067, ⟨10.18653/v1/2020.emnlp-main.647⟩ (2020)
|
|
BASE
|
|
Show details
|
|
7 |
Synthetic Data Augmentation for Zero-Shot Cross-Lingual Question Answering ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Answers Unite! Unsupervised Metrics for Reinforced Summarization Models
|
|
|
|
In: 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) ; https://hal.sorbonne-universite.fr/hal-02350999 ; 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), Nov 2019, Hong Kong, China. pp.3237-3247, ⟨10.18653/v1/D19-1320⟩ (2019)
|
|
Abstract:
International audience ; Abstractive summarization approaches based on Reinforcement Learning (RL) have recently been proposed to overcome classical likelihood maximization. RL enables to consider complex, possibly non differentiable, metrics that globally assess the quality and relevance of the generated outputs. ROUGE, the most used summarization metric, is known to suffer from bias towards lexical similarity as well as from sub-optimal accounting for fluency and readability of the generated abstracts. We thus explore and propose alternative evaluation measures: the reported human-evaluation analysis shows that the proposed metrics, based on Question Answering, favorably compare to ROUGE – with the additional property of not requiring reference summaries. Training a RL-based model on these metrics leads to improvements (both in terms of human or automated metrics) over current approaches that use ROUGE as reward.
|
|
Keyword:
[INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI]; [INFO.INFO-IR]Computer Science [cs]/Information Retrieval [cs.IR]; [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG]; [INFO.INFO-TT]Computer Science [cs]/Document and Text Processing
|
|
URL: https://hal.sorbonne-universite.fr/hal-02350999 https://hal.sorbonne-universite.fr/hal-02350999/file/D19-1320.pdf https://hal.sorbonne-universite.fr/hal-02350999/document https://doi.org/10.18653/v1/D19-1320
|
|
BASE
|
|
Hide details
|
|
9 |
Self-Attention Architectures for Answer-Agnostic Neural Question Generation
|
|
|
|
In: ACL 2019 - Annual Meeting of the Association for Computational Linguistics ; https://hal.sorbonne-universite.fr/hal-02350993 ; ACL 2019 - Annual Meeting of the Association for Computational Linguistics, Jul 2019, Florence, Italy. pp.6027-6032, ⟨10.18653/v1/P19-1604⟩ (2019)
|
|
BASE
|
|
Show details
|
|
10 |
Answers Unite! Unsupervised Metrics for Reinforced Summarization Models ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
DepecheMood++: a Bilingual Emotion Lexicon Built Through Simple Yet Powerful Techniques ...
|
|
|
|
BASE
|
|
Show details
|
|
12 |
Fortia-FBK at SemEval-2017 Task 5: Bullish or Bearish? Inferring Sentiment towards Brands from Financial News Headlines ...
|
|
|
|
BASE
|
|
Show details
|
|
13 |
Deep Feelings: A Massive Cross-Lingual Study on the Relation between Emotions and Virality ...
|
|
|
|
BASE
|
|
Show details
|
|
14 |
DepecheMood: a Lexicon for Emotion Analysis from Crowd-Annotated News ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|