Abstract
Implicit semantic role labeling (iSRL) is the task of predicting the semantic roles of a predicate that do not appear as explicit arguments, but rather regard common sense knowledge or are mentioned earlier in the discourse. We introduce an approach to iSRL based on a predictive recurrent neural semantic frame model (PRNSFM) that uses a large unannotated corpus to learn the probability of a sequence of semantic arguments given a predicate. We leverage the sequence probabilities predicted by the PRNSFM to estimate selectional preferences for predicates and their arguments. On the NomBank iSRL test set, our approach improves state-of-the-art performance on implicit semantic role labeling with less reliance than prior work on manually constructed language resources.- Anthology ID:
- I17-1010
- Volume:
- Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
- Month:
- November
- Year:
- 2017
- Address:
- Taipei, Taiwan
- Venue:
- IJCNLP
- SIG:
- Publisher:
- Asian Federation of Natural Language Processing
- Note:
- Pages:
- 90–99
- Language:
- URL:
- https://aclanthology.org/I17-1010
- DOI:
- Cite (ACL):
- Quynh Ngoc Thi Do, Steven Bethard, and Marie-Francine Moens. 2017. Improving Implicit Semantic Role Labeling by Predicting Semantic Frame Arguments. In Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 90–99, Taipei, Taiwan. Asian Federation of Natural Language Processing.
- Cite (Informal):
- Improving Implicit Semantic Role Labeling by Predicting Semantic Frame Arguments (Do et al., IJCNLP 2017)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/I17-1010.pdf
- Data
- NomBank