<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bakhshandeh-allen-2017-apples">
    <titleInfo>
        <title>Apples to Apples: Learning Semantics of Common Entities Through a Novel Comprehension Task</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Omid</namePart>
        <namePart type="family">Bakhshandeh</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">James</namePart>
        <namePart type="family">Allen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2017-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Regina</namePart>
            <namePart type="family">Barzilay</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Min-Yen</namePart>
            <namePart type="family">Kan</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Vancouver, Canada</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Understanding common entities and their attributes is a primary requirement for any system that comprehends natural language. In order to enable learning about common entities, we introduce a novel machine comprehension task, GuessTwo: given a short paragraph comparing different aspects of two real-world semantically-similar entities, a system should guess what those entities are. Accomplishing this task requires deep language understanding which enables inference, connecting each comparison paragraph to different levels of knowledge about world entities and their attributes. So far we have crowdsourced a dataset of more than 14K comparison paragraphs comparing entities from a variety of categories such as fruits and animals. We have designed two schemes for evaluation: open-ended, and binary-choice prediction. For benchmarking further progress in the task, we have collected a set of paragraphs as the test set on which human can accomplish the task with an accuracy of 94.2% on open-ended prediction. We have implemented various models for tackling the task, ranging from semantic-driven to neural models. The semantic-driven approach outperforms the neural models, however, the results indicate that the task is very challenging across the models.</abstract>
    <identifier type="citekey">bakhshandeh-allen-2017-apples</identifier>
    <identifier type="doi">10.18653/v1/P17-1084</identifier>
    <location>
        <url>https://aclanthology.org/P17-1084</url>
    </location>
    <part>
        <date>2017-07</date>
        <extent unit="page">
            <start>906</start>
            <end>916</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Apples to Apples: Learning Semantics of Common Entities Through a Novel Comprehension Task
%A Bakhshandeh, Omid
%A Allen, James
%Y Barzilay, Regina
%Y Kan, Min-Yen
%S Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2017
%8 July
%I Association for Computational Linguistics
%C Vancouver, Canada
%F bakhshandeh-allen-2017-apples
%X Understanding common entities and their attributes is a primary requirement for any system that comprehends natural language. In order to enable learning about common entities, we introduce a novel machine comprehension task, GuessTwo: given a short paragraph comparing different aspects of two real-world semantically-similar entities, a system should guess what those entities are. Accomplishing this task requires deep language understanding which enables inference, connecting each comparison paragraph to different levels of knowledge about world entities and their attributes. So far we have crowdsourced a dataset of more than 14K comparison paragraphs comparing entities from a variety of categories such as fruits and animals. We have designed two schemes for evaluation: open-ended, and binary-choice prediction. For benchmarking further progress in the task, we have collected a set of paragraphs as the test set on which human can accomplish the task with an accuracy of 94.2% on open-ended prediction. We have implemented various models for tackling the task, ranging from semantic-driven to neural models. The semantic-driven approach outperforms the neural models, however, the results indicate that the task is very challenging across the models.
%R 10.18653/v1/P17-1084
%U https://aclanthology.org/P17-1084
%U https://doi.org/10.18653/v1/P17-1084
%P 906-916

Markdown (Informal)

[Apples to Apples: Learning Semantics of Common Entities Through a Novel Comprehension Task](https://aclanthology.org/P17-1084) (Bakhshandeh & Allen, ACL 2017)

• Apples to Apples: Learning Semantics of Common Entities Through a Novel Comprehension Task (Bakhshandeh & Allen, ACL 2017)

ACL

• Omid Bakhshandeh and James Allen. 2017. Apples to Apples: Learning Semantics of Common Entities Through a Novel Comprehension Task. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 906–916, Vancouver, Canada. Association for Computational Linguistics.