<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="oren-etal-2020-improving">
    <titleInfo>
        <title>Improving Compositional Generalization in Semantic Parsing</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Inbar</namePart>
        <namePart type="family">Oren</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jonathan</namePart>
        <namePart type="family">Herzig</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Nitish</namePart>
        <namePart type="family">Gupta</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Matt</namePart>
        <namePart type="family">Gardner</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jonathan</namePart>
        <namePart type="family">Berant</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>Generalization of models to out-of-distribution (OOD) data has captured tremendous attention recently. Specifically, compositional generalization, i.e., whether a model generalizes to new structures built of components observed during training, has sparked substantial interest. In this work, we investigate compositional generalization in semantic parsing, a natural test-bed for compositional generalization, as output programs are constructed from sub-components. We analyze a wide variety of models and propose multiple extensions to the attention module of the semantic parser, aiming to improve compositional generalization. We find that the following factors improve compositional generalization: (a) using contextual representations, such as ELMo and BERT, (b) informing the decoder what input tokens have previously been attended to, (c) training the decoder attention to agree with pre-computed token alignments, and (d) downsampling examples corresponding to frequent program templates. While we substantially reduce the gap between in-distribution and OOD generalization, performance on OOD compositions is still substantially lower.</abstract>
    <identifier type="citekey">oren-etal-2020-improving</identifier>
    <identifier type="doi">10.18653/v1/2020.findings-emnlp.225</identifier>
    <location>
        <url>https://aclanthology.org/2020.findings-emnlp.225/</url>
    </location>
    <part>
        <date>2020-11</date>
        <extent unit="page">
            <start>2482</start>
            <end>2495</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Improving Compositional Generalization in Semantic Parsing
%A Oren, Inbar
%A Herzig, Jonathan
%A Gupta, Nitish
%A Gardner, Matt
%A Berant, Jonathan
%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 oren-etal-2020-improving
%X Generalization of models to out-of-distribution (OOD) data has captured tremendous attention recently. Specifically, compositional generalization, i.e., whether a model generalizes to new structures built of components observed during training, has sparked substantial interest. In this work, we investigate compositional generalization in semantic parsing, a natural test-bed for compositional generalization, as output programs are constructed from sub-components. We analyze a wide variety of models and propose multiple extensions to the attention module of the semantic parser, aiming to improve compositional generalization. We find that the following factors improve compositional generalization: (a) using contextual representations, such as ELMo and BERT, (b) informing the decoder what input tokens have previously been attended to, (c) training the decoder attention to agree with pre-computed token alignments, and (d) downsampling examples corresponding to frequent program templates. While we substantially reduce the gap between in-distribution and OOD generalization, performance on OOD compositions is still substantially lower.
%R 10.18653/v1/2020.findings-emnlp.225
%U https://aclanthology.org/2020.findings-emnlp.225/
%U https://doi.org/10.18653/v1/2020.findings-emnlp.225
%P 2482-2495

Markdown (Informal)

[Improving Compositional Generalization in Semantic Parsing](https://aclanthology.org/2020.findings-emnlp.225/) (Oren et al., Findings 2020)

• Improving Compositional Generalization in Semantic Parsing (Oren et al., Findings 2020)

ACL

• Inbar Oren, Jonathan Herzig, Nitish Gupta, Matt Gardner, and Jonathan Berant. 2020. Improving Compositional Generalization in Semantic Parsing. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 2482–2495, Online. Association for Computational Linguistics.