@inproceedings{yin-neubig-2019-reranking,
title = "Reranking for Neural Semantic Parsing",
author = "Yin, Pengcheng and
Neubig, Graham",
editor = "Korhonen, Anna and
Traum, David and
M{\`a}rquez, Llu{\'\i}s",
booktitle = "Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics",
month = jul,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/P19-1447",
doi = "10.18653/v1/P19-1447",
pages = "4553--4559",
abstract = "Semantic parsing considers the task of transducing natural language (NL) utterances into machine executable meaning representations (MRs). While neural network-based semantic parsers have achieved impressive improvements over previous methods, results are still far from perfect, and cursory manual inspection can easily identify obvious problems such as lack of adequacy or coherence of the generated MRs. This paper presents a simple approach to quickly iterate and improve the performance of an existing neural semantic parser by reranking an n-best list of predicted MRs, using features that are designed to fix observed problems with baseline models. We implement our reranker in a competitive neural semantic parser and test on four semantic parsing (GEO, ATIS) and Python code generation (Django, CoNaLa) tasks, improving the strong baseline parser by up to 5.7{\%} absolute in BLEU (CoNaLa) and 2.9{\%} in accuracy (Django), outperforming the best published neural parser results on all four datasets.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yin-neubig-2019-reranking">
<titleInfo>
<title>Reranking for Neural Semantic Parsing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pengcheng</namePart>
<namePart type="family">Yin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Graham</namePart>
<namePart type="family">Neubig</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Korhonen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Traum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lluís</namePart>
<namePart type="family">Màrquez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Florence, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Semantic parsing considers the task of transducing natural language (NL) utterances into machine executable meaning representations (MRs). While neural network-based semantic parsers have achieved impressive improvements over previous methods, results are still far from perfect, and cursory manual inspection can easily identify obvious problems such as lack of adequacy or coherence of the generated MRs. This paper presents a simple approach to quickly iterate and improve the performance of an existing neural semantic parser by reranking an n-best list of predicted MRs, using features that are designed to fix observed problems with baseline models. We implement our reranker in a competitive neural semantic parser and test on four semantic parsing (GEO, ATIS) and Python code generation (Django, CoNaLa) tasks, improving the strong baseline parser by up to 5.7% absolute in BLEU (CoNaLa) and 2.9% in accuracy (Django), outperforming the best published neural parser results on all four datasets.</abstract>
<identifier type="citekey">yin-neubig-2019-reranking</identifier>
<identifier type="doi">10.18653/v1/P19-1447</identifier>
<location>
<url>https://aclanthology.org/P19-1447</url>
</location>
<part>
<date>2019-07</date>
<extent unit="page">
<start>4553</start>
<end>4559</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Reranking for Neural Semantic Parsing
%A Yin, Pengcheng
%A Neubig, Graham
%Y Korhonen, Anna
%Y Traum, David
%Y Màrquez, Lluís
%S Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
%D 2019
%8 July
%I Association for Computational Linguistics
%C Florence, Italy
%F yin-neubig-2019-reranking
%X Semantic parsing considers the task of transducing natural language (NL) utterances into machine executable meaning representations (MRs). While neural network-based semantic parsers have achieved impressive improvements over previous methods, results are still far from perfect, and cursory manual inspection can easily identify obvious problems such as lack of adequacy or coherence of the generated MRs. This paper presents a simple approach to quickly iterate and improve the performance of an existing neural semantic parser by reranking an n-best list of predicted MRs, using features that are designed to fix observed problems with baseline models. We implement our reranker in a competitive neural semantic parser and test on four semantic parsing (GEO, ATIS) and Python code generation (Django, CoNaLa) tasks, improving the strong baseline parser by up to 5.7% absolute in BLEU (CoNaLa) and 2.9% in accuracy (Django), outperforming the best published neural parser results on all four datasets.
%R 10.18653/v1/P19-1447
%U https://aclanthology.org/P19-1447
%U https://doi.org/10.18653/v1/P19-1447
%P 4553-4559
Markdown (Informal)
[Reranking for Neural Semantic Parsing](https://aclanthology.org/P19-1447) (Yin & Neubig, ACL 2019)
ACL
- Pengcheng Yin and Graham Neubig. 2019. Reranking for Neural Semantic Parsing. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 4553–4559, Florence, Italy. Association for Computational Linguistics.