Learning to Make Inferences in a Semantic Parsing Task

Kyle Richardson, Jonas Kuhn


Abstract
We introduce a new approach to training a semantic parser that uses textual entailment judgements as supervision. These judgements are based on high-level inferences about whether the meaning of one sentence follows from another. When applied to an existing semantic parsing task, they prove to be a useful tool for revealing semantic distinctions and background knowledge not captured in the target representations. This information is used to improve the quality of the semantic representations being learned and to acquire generic knowledge for reasoning. Experiments are done on the benchmark Sportscaster corpus (Chen and Mooney, 2008), and a novel RTE-inspired inference dataset is introduced. On this new dataset our method strongly outperforms several strong baselines. Separately, we obtain state-of-the-art results on the original Sportscaster semantic parsing task.
Anthology ID:
Q16-1012
Volume:
Transactions of the Association for Computational Linguistics, Volume 4
Month:
Year:
2016
Address:
Cambridge, MA
Venue:
TACL
SIG:
Publisher:
MIT Press
Note:
Pages:
155–168
Language:
URL:
https://aclanthology.org/Q16-1012
DOI:
10.1162/tacl_a_00090
Bibkey:
Cite (ACL):
Kyle Richardson and Jonas Kuhn. 2016. Learning to Make Inferences in a Semantic Parsing Task. Transactions of the Association for Computational Linguistics, 4:155–168.
Cite (Informal):
Learning to Make Inferences in a Semantic Parsing Task (Richardson & Kuhn, TACL 2016)
Copy Citation:
PDF:
https://preview.aclanthology.org/update-css-js/Q16-1012.pdf
Data
RoboCup