@inproceedings{dhar-van-der-plas-2019-learning,
title = "Learning to Predict Novel Noun-Noun Compounds",
author = "Dhar, Prajit and
van der Plas, Lonneke",
editor = "Savary, Agata and
Escart{\'\i}n, Carla Parra and
Bond, Francis and
Mitrovi{\'c}, Jelena and
Mititelu, Verginica Barbu",
booktitle = "Proceedings of the Joint Workshop on Multiword Expressions and WordNet (MWE-WN 2019)",
month = aug,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-5105",
doi = "10.18653/v1/W19-5105",
pages = "30--39",
abstract = "We introduce temporally and contextually-aware models for the novel task of predicting unseen but plausible concepts, as conveyed by noun-noun compounds in a time-stamped corpus. We train compositional models on observed compounds, more specifically the composed distributed representations of their constituents across a time-stamped corpus, while giving it corrupted instances (where head or modifier are replaced by a random constituent) as negative evidence. The model captures generalisations over this data and learns what combinations give rise to plausible compounds and which ones do not. After training, we query the model for the plausibility of automatically generated novel combinations and verify whether the classifications are accurate. For our best model, we find that in around 85{\%} of the cases, the novel compounds generated are attested in previously unseen data. An additional estimated 5{\%} are plausible despite not being attested in the recent corpus, based on judgments from independent human raters.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dhar-van-der-plas-2019-learning">
<titleInfo>
<title>Learning to Predict Novel Noun-Noun Compounds</title>
</titleInfo>
<name type="personal">
<namePart type="given">Prajit</namePart>
<namePart type="family">Dhar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lonneke</namePart>
<namePart type="family">van der Plas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Joint Workshop on Multiword Expressions and WordNet (MWE-WN 2019)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Agata</namePart>
<namePart type="family">Savary</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carla</namePart>
<namePart type="given">Parra</namePart>
<namePart type="family">Escartín</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francis</namePart>
<namePart type="family">Bond</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jelena</namePart>
<namePart type="family">Mitrović</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Verginica</namePart>
<namePart type="given">Barbu</namePart>
<namePart type="family">Mititelu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Florence, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We introduce temporally and contextually-aware models for the novel task of predicting unseen but plausible concepts, as conveyed by noun-noun compounds in a time-stamped corpus. We train compositional models on observed compounds, more specifically the composed distributed representations of their constituents across a time-stamped corpus, while giving it corrupted instances (where head or modifier are replaced by a random constituent) as negative evidence. The model captures generalisations over this data and learns what combinations give rise to plausible compounds and which ones do not. After training, we query the model for the plausibility of automatically generated novel combinations and verify whether the classifications are accurate. For our best model, we find that in around 85% of the cases, the novel compounds generated are attested in previously unseen data. An additional estimated 5% are plausible despite not being attested in the recent corpus, based on judgments from independent human raters.</abstract>
<identifier type="citekey">dhar-van-der-plas-2019-learning</identifier>
<identifier type="doi">10.18653/v1/W19-5105</identifier>
<location>
<url>https://aclanthology.org/W19-5105</url>
</location>
<part>
<date>2019-08</date>
<extent unit="page">
<start>30</start>
<end>39</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Learning to Predict Novel Noun-Noun Compounds
%A Dhar, Prajit
%A van der Plas, Lonneke
%Y Savary, Agata
%Y Escartín, Carla Parra
%Y Bond, Francis
%Y Mitrović, Jelena
%Y Mititelu, Verginica Barbu
%S Proceedings of the Joint Workshop on Multiword Expressions and WordNet (MWE-WN 2019)
%D 2019
%8 August
%I Association for Computational Linguistics
%C Florence, Italy
%F dhar-van-der-plas-2019-learning
%X We introduce temporally and contextually-aware models for the novel task of predicting unseen but plausible concepts, as conveyed by noun-noun compounds in a time-stamped corpus. We train compositional models on observed compounds, more specifically the composed distributed representations of their constituents across a time-stamped corpus, while giving it corrupted instances (where head or modifier are replaced by a random constituent) as negative evidence. The model captures generalisations over this data and learns what combinations give rise to plausible compounds and which ones do not. After training, we query the model for the plausibility of automatically generated novel combinations and verify whether the classifications are accurate. For our best model, we find that in around 85% of the cases, the novel compounds generated are attested in previously unseen data. An additional estimated 5% are plausible despite not being attested in the recent corpus, based on judgments from independent human raters.
%R 10.18653/v1/W19-5105
%U https://aclanthology.org/W19-5105
%U https://doi.org/10.18653/v1/W19-5105
%P 30-39
Markdown (Informal)
[Learning to Predict Novel Noun-Noun Compounds](https://aclanthology.org/W19-5105) (Dhar & van der Plas, MWE 2019)
ACL
- Prajit Dhar and Lonneke van der Plas. 2019. Learning to Predict Novel Noun-Noun Compounds. In Proceedings of the Joint Workshop on Multiword Expressions and WordNet (MWE-WN 2019), pages 30–39, Florence, Italy. Association for Computational Linguistics.