@inproceedings{schulte-im-walde-2010-comparing,
title = "Comparing Computational Models of Selectional Preferences - Second-order Co-Occurrence vs. Latent Semantic Clusters",
author = "Schulte im Walde, Sabine",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Rosner, Mike and
Tapias, Daniel",
booktitle = "Proceedings of the Seventh International Conference on Language Resources and Evaluation ({LREC}`10)",
month = may,
year = "2010",
address = "Valletta, Malta",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L10-1434/",
abstract = "This paper presents a comparison of three computational approaches to selectional preferences: (i) an intuitive distributional approach that uses second-order co-occurrence of predicates and complement properties; (ii) an EM-based clustering approach that models the strengths of predicate--noun relationships by latent semantic clusters (Rooth et al., 1999); and (iii) an extension of the latent semantic clusters by incorporating the MDL principle into the EM training, thus explicitly modelling the predicate--noun selectional preferences by WordNet classes (Schulte im Walde et al., 2008). Concerning the distributional approach, we were interested not only in how well the model describes selectional preferences, but moreover which second-order properties are most salient. For example, a typical direct object of the verb `drink' is usually fluid, might be hot or cold, can be bought, might be bottled, etc. The general question we ask is: what characterises the predicate`s restrictions to the semantic realisation of its complements? Our second interest lies in the actual comparison of the models: How does a very simple distributional model compare to much more complex approaches, and which representation of selectional preferences is more appropriate, using (i) second-order properties, (ii) an implicit generalisation of nouns (by clusters), or (iii) an explicit generalisation of nouns by WordNet classes within clusters? We describe various experiments on German data and two evaluations, and demonstrate that the simple distributional model outperforms the more complex cluster-based models in most cases, but does itself not always beat the powerful frequency baseline."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="schulte-im-walde-2010-comparing">
<titleInfo>
<title>Comparing Computational Models of Selectional Preferences - Second-order Co-Occurrence vs. Latent Semantic Clusters</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sabine</namePart>
<namePart type="family">Schulte im Walde</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2010-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC‘10)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mike</namePart>
<namePart type="family">Rosner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Tapias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Valletta, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents a comparison of three computational approaches to selectional preferences: (i) an intuitive distributional approach that uses second-order co-occurrence of predicates and complement properties; (ii) an EM-based clustering approach that models the strengths of predicate–noun relationships by latent semantic clusters (Rooth et al., 1999); and (iii) an extension of the latent semantic clusters by incorporating the MDL principle into the EM training, thus explicitly modelling the predicate–noun selectional preferences by WordNet classes (Schulte im Walde et al., 2008). Concerning the distributional approach, we were interested not only in how well the model describes selectional preferences, but moreover which second-order properties are most salient. For example, a typical direct object of the verb ‘drink’ is usually fluid, might be hot or cold, can be bought, might be bottled, etc. The general question we ask is: what characterises the predicate‘s restrictions to the semantic realisation of its complements? Our second interest lies in the actual comparison of the models: How does a very simple distributional model compare to much more complex approaches, and which representation of selectional preferences is more appropriate, using (i) second-order properties, (ii) an implicit generalisation of nouns (by clusters), or (iii) an explicit generalisation of nouns by WordNet classes within clusters? We describe various experiments on German data and two evaluations, and demonstrate that the simple distributional model outperforms the more complex cluster-based models in most cases, but does itself not always beat the powerful frequency baseline.</abstract>
<identifier type="citekey">schulte-im-walde-2010-comparing</identifier>
<location>
<url>https://aclanthology.org/L10-1434/</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Comparing Computational Models of Selectional Preferences - Second-order Co-Occurrence vs. Latent Semantic Clusters
%A Schulte im Walde, Sabine
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Rosner, Mike
%Y Tapias, Daniel
%S Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC‘10)
%D 2010
%8 May
%I European Language Resources Association (ELRA)
%C Valletta, Malta
%F schulte-im-walde-2010-comparing
%X This paper presents a comparison of three computational approaches to selectional preferences: (i) an intuitive distributional approach that uses second-order co-occurrence of predicates and complement properties; (ii) an EM-based clustering approach that models the strengths of predicate–noun relationships by latent semantic clusters (Rooth et al., 1999); and (iii) an extension of the latent semantic clusters by incorporating the MDL principle into the EM training, thus explicitly modelling the predicate–noun selectional preferences by WordNet classes (Schulte im Walde et al., 2008). Concerning the distributional approach, we were interested not only in how well the model describes selectional preferences, but moreover which second-order properties are most salient. For example, a typical direct object of the verb ‘drink’ is usually fluid, might be hot or cold, can be bought, might be bottled, etc. The general question we ask is: what characterises the predicate‘s restrictions to the semantic realisation of its complements? Our second interest lies in the actual comparison of the models: How does a very simple distributional model compare to much more complex approaches, and which representation of selectional preferences is more appropriate, using (i) second-order properties, (ii) an implicit generalisation of nouns (by clusters), or (iii) an explicit generalisation of nouns by WordNet classes within clusters? We describe various experiments on German data and two evaluations, and demonstrate that the simple distributional model outperforms the more complex cluster-based models in most cases, but does itself not always beat the powerful frequency baseline.
%U https://aclanthology.org/L10-1434/
Markdown (Informal)
[Comparing Computational Models of Selectional Preferences - Second-order Co-Occurrence vs. Latent Semantic Clusters](https://aclanthology.org/L10-1434/) (Schulte im Walde, LREC 2010)
ACL