@inproceedings{fancellu-etal-2020-accurate,
title = "Accurate polyglot semantic parsing with {DAG} grammars",
author = "Fancellu, Federico and
K{\'a}d{\'a}r, {\'A}kos and
Zhang, Ran and
Fazly, Afsaneh",
editor = "Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2020",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.findings-emnlp.320",
doi = "10.18653/v1/2020.findings-emnlp.320",
pages = "3567--3580",
abstract = "Semantic parses are directed acyclic graphs (DAGs), but in practice most parsers treat them as strings or trees, mainly because models that predict graphs are far less understood. This simplification, however, comes at a cost: there is no guarantee that the output is a well-formed graph. A recent work by Fancellu et al. (2019) addressed this problem by proposing a graph-aware sequence model that utilizes a DAG grammar to guide graph generation. We significantly improve upon this work, by proposing a simpler architecture as well as more efficient training and inference algorithms that can always guarantee the well-formedness of the generated graphs. Importantly, unlike Fancellu et al., our model does not require language-specific features, and hence can harness the inherent ability of DAG-grammar parsing in multilingual settings. We perform monolingual as well as multilingual experiments on the Parallel Meaning Bank (Abzianidze et al., 2017). Our parser outperforms previous graph-aware models by a large margin, and closes the performance gap between string-based and DAG-grammar parsing.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fancellu-etal-2020-accurate">
<titleInfo>
<title>Accurate polyglot semantic parsing with DAG grammars</title>
</titleInfo>
<name type="personal">
<namePart type="given">Federico</namePart>
<namePart type="family">Fancellu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ákos</namePart>
<namePart type="family">Kádár</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ran</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Afsaneh</namePart>
<namePart type="family">Fazly</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2020</title>
</titleInfo>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Semantic parses are directed acyclic graphs (DAGs), but in practice most parsers treat them as strings or trees, mainly because models that predict graphs are far less understood. This simplification, however, comes at a cost: there is no guarantee that the output is a well-formed graph. A recent work by Fancellu et al. (2019) addressed this problem by proposing a graph-aware sequence model that utilizes a DAG grammar to guide graph generation. We significantly improve upon this work, by proposing a simpler architecture as well as more efficient training and inference algorithms that can always guarantee the well-formedness of the generated graphs. Importantly, unlike Fancellu et al., our model does not require language-specific features, and hence can harness the inherent ability of DAG-grammar parsing in multilingual settings. We perform monolingual as well as multilingual experiments on the Parallel Meaning Bank (Abzianidze et al., 2017). Our parser outperforms previous graph-aware models by a large margin, and closes the performance gap between string-based and DAG-grammar parsing.</abstract>
<identifier type="citekey">fancellu-etal-2020-accurate</identifier>
<identifier type="doi">10.18653/v1/2020.findings-emnlp.320</identifier>
<location>
<url>https://aclanthology.org/2020.findings-emnlp.320</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>3567</start>
<end>3580</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Accurate polyglot semantic parsing with DAG grammars
%A Fancellu, Federico
%A Kádár, Ákos
%A Zhang, Ran
%A Fazly, Afsaneh
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Findings of the Association for Computational Linguistics: EMNLP 2020
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F fancellu-etal-2020-accurate
%X Semantic parses are directed acyclic graphs (DAGs), but in practice most parsers treat them as strings or trees, mainly because models that predict graphs are far less understood. This simplification, however, comes at a cost: there is no guarantee that the output is a well-formed graph. A recent work by Fancellu et al. (2019) addressed this problem by proposing a graph-aware sequence model that utilizes a DAG grammar to guide graph generation. We significantly improve upon this work, by proposing a simpler architecture as well as more efficient training and inference algorithms that can always guarantee the well-formedness of the generated graphs. Importantly, unlike Fancellu et al., our model does not require language-specific features, and hence can harness the inherent ability of DAG-grammar parsing in multilingual settings. We perform monolingual as well as multilingual experiments on the Parallel Meaning Bank (Abzianidze et al., 2017). Our parser outperforms previous graph-aware models by a large margin, and closes the performance gap between string-based and DAG-grammar parsing.
%R 10.18653/v1/2020.findings-emnlp.320
%U https://aclanthology.org/2020.findings-emnlp.320
%U https://doi.org/10.18653/v1/2020.findings-emnlp.320
%P 3567-3580
Markdown (Informal)
[Accurate polyglot semantic parsing with DAG grammars](https://aclanthology.org/2020.findings-emnlp.320) (Fancellu et al., Findings 2020)
ACL
- Federico Fancellu, Ákos Kádár, Ran Zhang, and Afsaneh Fazly. 2020. Accurate polyglot semantic parsing with DAG grammars. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 3567–3580, Online. Association for Computational Linguistics.