<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ziegler-etal-2017-efficiency">
    <titleInfo>
        <title>Efficiency-aware Answering of Compositional Questions using Answer Type Prediction</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">David</namePart>
        <namePart type="family">Ziegler</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Abdalghani</namePart>
        <namePart type="family">Abujabal</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Rishiraj</namePart>
        <namePart type="family">Saha Roy</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Gerhard</namePart>
        <namePart type="family">Weikum</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2017-nov</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 2: Short Papers)</title>
        </titleInfo>
        <originInfo>
            <publisher>Asian Federation of Natural Language Processing</publisher>
            <place>
                <placeTerm type="text">Taipei, Taiwan</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>This paper investigates the problem of answering compositional factoid questions over knowledge bases (KB) under efficiency constraints. The method, called TIPI, (i) decomposes compositional questions, (ii) predicts answer types for individual sub-questions, (iii) reasons over the compatibility of joint types, and finally, (iv) formulates compositional SPARQL queries respecting type constraints. TIPI’s answer type predictor is trained using distant supervision, and exploits lexical, syntactic and embedding-based features to compute context- and hierarchy-aware candidate answer types for an input question. Experiments on a recent benchmark show that TIPI results in state-of-the-art performance under the real-world assumption that only a single SPARQL query can be executed over the KB, and substantial reduction in the number of queries in the more general case.</abstract>
    <identifier type="citekey">ziegler-etal-2017-efficiency</identifier>
    <location>
        <url>https://aclanthology.org/I17-2038</url>
    </location>
    <part>
        <date>2017-nov</date>
        <extent unit="page">
            <start>222</start>
            <end>227</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Efficiency-aware Answering of Compositional Questions using Answer Type Prediction
%A Ziegler, David
%A Abujabal, Abdalghani
%A Saha Roy, Rishiraj
%A Weikum, Gerhard
%S Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 2: Short Papers)
%D 2017
%8 nov
%I Asian Federation of Natural Language Processing
%C Taipei, Taiwan
%F ziegler-etal-2017-efficiency
%X This paper investigates the problem of answering compositional factoid questions over knowledge bases (KB) under efficiency constraints. The method, called TIPI, (i) decomposes compositional questions, (ii) predicts answer types for individual sub-questions, (iii) reasons over the compatibility of joint types, and finally, (iv) formulates compositional SPARQL queries respecting type constraints. TIPI’s answer type predictor is trained using distant supervision, and exploits lexical, syntactic and embedding-based features to compute context- and hierarchy-aware candidate answer types for an input question. Experiments on a recent benchmark show that TIPI results in state-of-the-art performance under the real-world assumption that only a single SPARQL query can be executed over the KB, and substantial reduction in the number of queries in the more general case.
%U https://aclanthology.org/I17-2038
%P 222-227

Markdown (Informal)

[Efficiency-aware Answering of Compositional Questions using Answer Type Prediction](https://aclanthology.org/I17-2038) (Ziegler et al., IJCNLP 2017)

• Efficiency-aware Answering of Compositional Questions using Answer Type Prediction (Ziegler et al., IJCNLP 2017)

ACL

• David Ziegler, Abdalghani Abujabal, Rishiraj Saha Roy, and Gerhard Weikum. 2017. Efficiency-aware Answering of Compositional Questions using Answer Type Prediction. In Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 222–227, Taipei, Taiwan. Asian Federation of Natural Language Processing.