Weakly-Supervised Neural Semantic Parsing with a Generative Ranker

Jianpeng Cheng, Mirella Lapata


Abstract
Weakly-supervised semantic parsers are trained on utterance-denotation pairs, treating logical forms as latent. The task is challenging due to the large search space and spuriousness of logical forms. In this paper we introduce a neural parser-ranker system for weakly-supervised semantic parsing. The parser generates candidate tree-structured logical forms from utterances using clues of denotations. These candidates are then ranked based on two criterion: their likelihood of executing to the correct denotation, and their agreement with the utterance semantics. We present a scheduled training procedure to balance the contribution of the two objectives. Furthermore, we propose to use a neurally encoded lexicon to inject prior domain knowledge to the model. Experiments on three Freebase datasets demonstrate the effectiveness of our semantic parser, achieving results within the state-of-the-art range.
Anthology ID:
K18-1035
Volume:
Proceedings of the 22nd Conference on Computational Natural Language Learning
Month:
October
Year:
2018
Address:
Brussels, Belgium
Editors:
Anna Korhonen, Ivan Titov
Venue:
CoNLL
SIG:
SIGNLL
Publisher:
Association for Computational Linguistics
Note:
Pages:
356–367
Language:
URL:
https://aclanthology.org/K18-1035
DOI:
10.18653/v1/K18-1035
Bibkey:
Cite (ACL):
Jianpeng Cheng and Mirella Lapata. 2018. Weakly-Supervised Neural Semantic Parsing with a Generative Ranker. In Proceedings of the 22nd Conference on Computational Natural Language Learning, pages 356–367, Brussels, Belgium. Association for Computational Linguistics.
Cite (Informal):
Weakly-Supervised Neural Semantic Parsing with a Generative Ranker (Cheng & Lapata, CoNLL 2018)
Copy Citation:
PDF:
https://preview.aclanthology.org/dois-2013-emnlp/K18-1035.pdf