<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hou-2016-incremental">
    <titleInfo>
        <title>Incremental Fine-grained Information Status Classification Using Attention-based LSTMs</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Yufang</namePart>
        <namePart type="family">Hou</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2016-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yuji</namePart>
            <namePart type="family">Matsumoto</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Rashmi</namePart>
            <namePart type="family">Prasad</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>The COLING 2016 Organizing Committee</publisher>
            <place>
                <placeTerm type="text">Osaka, Japan</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Information status plays an important role in discourse processing. According to the hearer’s common sense knowledge and his comprehension of the preceding text, a discourse entity could be old, mediated or new. In this paper, we propose an attention-based LSTM model to address the problem of fine-grained information status classification in an incremental manner. Our approach resembles how human beings process the task, i.e., decide the information status of the current discourse entity based on its preceding context. Experimental results on the ISNotes corpus (Markert et al., 2012) reveal that (1) despite its moderate result, our model with only word embedding features captures the necessary semantic knowledge needed for the task by a large extent; and (2) when incorporating with additional several simple features, our model achieves the competitive results compared to the state-of-the-art approach (Hou et al., 2013) which heavily depends on lots of hand-crafted semantic features.</abstract>
    <identifier type="citekey">hou-2016-incremental</identifier>
    <location>
        <url>https://aclanthology.org/C16-1177</url>
    </location>
    <part>
        <date>2016-12</date>
        <extent unit="page">
            <start>1880</start>
            <end>1890</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Incremental Fine-grained Information Status Classification Using Attention-based LSTMs
%A Hou, Yufang
%Y Matsumoto, Yuji
%Y Prasad, Rashmi
%S Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers
%D 2016
%8 December
%I The COLING 2016 Organizing Committee
%C Osaka, Japan
%F hou-2016-incremental
%X Information status plays an important role in discourse processing. According to the hearer’s common sense knowledge and his comprehension of the preceding text, a discourse entity could be old, mediated or new. In this paper, we propose an attention-based LSTM model to address the problem of fine-grained information status classification in an incremental manner. Our approach resembles how human beings process the task, i.e., decide the information status of the current discourse entity based on its preceding context. Experimental results on the ISNotes corpus (Markert et al., 2012) reveal that (1) despite its moderate result, our model with only word embedding features captures the necessary semantic knowledge needed for the task by a large extent; and (2) when incorporating with additional several simple features, our model achieves the competitive results compared to the state-of-the-art approach (Hou et al., 2013) which heavily depends on lots of hand-crafted semantic features.
%U https://aclanthology.org/C16-1177
%P 1880-1890

Markdown (Informal)

[Incremental Fine-grained Information Status Classification Using Attention-based LSTMs](https://aclanthology.org/C16-1177) (Hou, COLING 2016)

• Incremental Fine-grained Information Status Classification Using Attention-based LSTMs (Hou, COLING 2016)

ACL

• Yufang Hou. 2016. Incremental Fine-grained Information Status Classification Using Attention-based LSTMs. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pages 1880–1890, Osaka, Japan. The COLING 2016 Organizing Committee.