Identifying Domain Adjacent Instances for Semantic Parsers
James Ferguson, Janara Christensen, Edward Li, Edgar Gonzàlez
Abstract
When the semantics of a sentence are not representable in a semantic parser’s output schema, parsing will inevitably fail. Detection of these instances is commonly treated as an out-of-domain classification problem. However, there is also a more subtle scenario in which the test data is drawn from the same domain. In addition to formalizing this problem of domain-adjacency, we present a comparison of various baselines that could be used to solve it. We also propose a new simple sentence representation that emphasizes words which are unexpected. This approach improves the performance of a downstream semantic parser run on in-domain and domain-adjacent instances.- Anthology ID:
- D18-1539
- Volume:
- Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
- Month:
- October-November
- Year:
- 2018
- Address:
- Brussels, Belgium
- Editors:
- Ellen Riloff, David Chiang, Julia Hockenmaier, Jun’ichi Tsujii
- Venue:
- EMNLP
- SIG:
- SIGDAT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 4964–4969
- Language:
- URL:
- https://aclanthology.org/D18-1539
- DOI:
- 10.18653/v1/D18-1539
- Cite (ACL):
- James Ferguson, Janara Christensen, Edward Li, and Edgar Gonzàlez. 2018. Identifying Domain Adjacent Instances for Semantic Parsers. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 4964–4969, Brussels, Belgium. Association for Computational Linguistics.
- Cite (Informal):
- Identifying Domain Adjacent Instances for Semantic Parsers (Ferguson et al., EMNLP 2018)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/D18-1539.pdf