<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mcshane-nirenburg-2016-extra">
    <titleInfo>
        <title>Extra-Specific Multiword Expressions for Language-Endowed Intelligent Agents</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Marjorie</namePart>
        <namePart type="family">McShane</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sergei</namePart>
        <namePart type="family">Nirenburg</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 the Workshop on Grammar and Lexicon: interactions and interfaces (GramLex)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Eva</namePart>
            <namePart type="family">Hajičová</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Igor</namePart>
            <namePart type="family">Boguslavsky</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>Language-endowed intelligent agents benefit from leveraging lexical knowledge falling at different points along a spectrum of compositionality. This means that robust computational lexicons should include not only the compositional expectations of argument-taking words, but also non-compositional collocations (idioms), semi-compositional collocations that might be difficult for an agent to interpret (e.g., standard metaphors), and even collocations that could be compositionally analyzed but are so frequently encountered that recording their meaning increases the efficiency of interpretation. In this paper we argue that yet another type of string-to-meaning mapping can also be useful to intelligent agents: remembered semantic analyses of actual text inputs. These can be viewed as super-specific multi-word expressions whose recorded interpretations mimic a person’s memories of knowledge previously learned from language input. These differ from typical annotated corpora in two ways. First, they provide a full, context-sensitive semantic interpretation rather than select features. Second, they are are formulated in the ontologically-grounded metalanguage used in a particular agent environment, meaning that the interpretations contribute to the dynamically evolving cognitive capabilites of agents configured in that environment.</abstract>
    <identifier type="citekey">mcshane-nirenburg-2016-extra</identifier>
    <location>
        <url>https://aclanthology.org/W16-3805</url>
    </location>
    <part>
        <date>2016-12</date>
        <extent unit="page">
            <start>28</start>
            <end>37</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Extra-Specific Multiword Expressions for Language-Endowed Intelligent Agents
%A McShane, Marjorie
%A Nirenburg, Sergei
%Y Hajičová, Eva
%Y Boguslavsky, Igor
%S Proceedings of the Workshop on Grammar and Lexicon: interactions and interfaces (GramLex)
%D 2016
%8 December
%I The COLING 2016 Organizing Committee
%C Osaka, Japan
%F mcshane-nirenburg-2016-extra
%X Language-endowed intelligent agents benefit from leveraging lexical knowledge falling at different points along a spectrum of compositionality. This means that robust computational lexicons should include not only the compositional expectations of argument-taking words, but also non-compositional collocations (idioms), semi-compositional collocations that might be difficult for an agent to interpret (e.g., standard metaphors), and even collocations that could be compositionally analyzed but are so frequently encountered that recording their meaning increases the efficiency of interpretation. In this paper we argue that yet another type of string-to-meaning mapping can also be useful to intelligent agents: remembered semantic analyses of actual text inputs. These can be viewed as super-specific multi-word expressions whose recorded interpretations mimic a person’s memories of knowledge previously learned from language input. These differ from typical annotated corpora in two ways. First, they provide a full, context-sensitive semantic interpretation rather than select features. Second, they are are formulated in the ontologically-grounded metalanguage used in a particular agent environment, meaning that the interpretations contribute to the dynamically evolving cognitive capabilites of agents configured in that environment.
%U https://aclanthology.org/W16-3805
%P 28-37

Markdown (Informal)

[Extra-Specific Multiword Expressions for Language-Endowed Intelligent Agents](https://aclanthology.org/W16-3805) (McShane & Nirenburg, GramLex 2016)

• Extra-Specific Multiword Expressions for Language-Endowed Intelligent Agents (McShane & Nirenburg, GramLex 2016)

ACL

• Marjorie McShane and Sergei Nirenburg. 2016. Extra-Specific Multiword Expressions for Language-Endowed Intelligent Agents. In Proceedings of the Workshop on Grammar and Lexicon: interactions and interfaces (GramLex), pages 28–37, Osaka, Japan. The COLING 2016 Organizing Committee.