HELP: A Dataset for Identifying Shortcomings of Neural Models in Monotonicity Reasoning
Hitomi Yanaka, Koji Mineshima, Daisuke Bekki, Kentaro Inui, Satoshi Sekine, Lasha Abzianidze, Johan Bos
Abstract
Large crowdsourced datasets are widely used for training and evaluating neural models on natural language inference (NLI). Despite these efforts, neural models have a hard time capturing logical inferences, including those licensed by phrase replacements, so-called monotonicity reasoning. Since no large dataset has been developed for monotonicity reasoning, it is still unclear whether the main obstacle is the size of datasets or the model architectures themselves. To investigate this issue, we introduce a new dataset, called HELP, for handling entailments with lexical and logical phenomena. We add it to training data for the state-of-the-art neural models and evaluate them on test sets for monotonicity phenomena. The results showed that our data augmentation improved the overall accuracy. We also find that the improvement is better on monotonicity inferences with lexical replacements than on downward inferences with disjunction and modification. This suggests that some types of inferences can be improved by our data augmentation while others are immune to it.- Anthology ID:
- S19-1027
- Volume:
- Proceedings of the Eighth Joint Conference on Lexical and Computational Semantics (*SEM 2019)
- Month:
- June
- Year:
- 2019
- Address:
- Minneapolis, Minnesota
- Editors:
- Rada Mihalcea, Ekaterina Shutova, Lun-Wei Ku, Kilian Evang, Soujanya Poria
- Venue:
- *SEM
- SIGs:
- SIGLEX | SIGSEM
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 250–255
- Language:
- URL:
- https://aclanthology.org/S19-1027
- DOI:
- 10.18653/v1/S19-1027
- Cite (ACL):
- Hitomi Yanaka, Koji Mineshima, Daisuke Bekki, Kentaro Inui, Satoshi Sekine, Lasha Abzianidze, and Johan Bos. 2019. HELP: A Dataset for Identifying Shortcomings of Neural Models in Monotonicity Reasoning. In Proceedings of the Eighth Joint Conference on Lexical and Computational Semantics (*SEM 2019), pages 250–255, Minneapolis, Minnesota. Association for Computational Linguistics.
- Cite (Informal):
- HELP: A Dataset for Identifying Shortcomings of Neural Models in Monotonicity Reasoning (Yanaka et al., *SEM 2019)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-1/S19-1027.pdf
- Code
- verypluming/HELP
- Data
- HELP, GLUE, MultiNLI, SICK