@inproceedings{maitreyee-2020-beyond,
title = "Beyond Adjacency Pairs: Hierarchical Clustering of Long Sequences for Human-Machine Dialogues",
author = "Maitreyee, Maitreyee",
editor = "Braud, Chlo{\'e} and
Hardmeier, Christian and
Li, Junyi Jessy and
Louis, Annie and
Strube, Michael",
booktitle = "Proceedings of the First Workshop on Computational Approaches to Discourse",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.codi-1.2",
doi = "10.18653/v1/2020.codi-1.2",
pages = "11--19",
abstract = "This work proposes a framework to predict sequences in dialogues, using turn based syntactic features and dialogue control functions. Syntactic features were extracted using dependency parsing, while dialogue control functions were manually labelled. These features were transformed using tf-idf and word embedding; feature selection was done using Principal Component Analysis (PCA). We ran experiments on six combinations of features to predict sequences with Hierarchical Agglomerative Clustering. An analysis of the clustering results indicate that using word embeddings and syntactic features, significantly improved the results.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="maitreyee-2020-beyond">
<titleInfo>
<title>Beyond Adjacency Pairs: Hierarchical Clustering of Long Sequences for Human-Machine Dialogues</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maitreyee</namePart>
<namePart type="family">Maitreyee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Workshop on Computational Approaches to Discourse</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chloé</namePart>
<namePart type="family">Braud</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christian</namePart>
<namePart type="family">Hardmeier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junyi</namePart>
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Annie</namePart>
<namePart type="family">Louis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Strube</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This work proposes a framework to predict sequences in dialogues, using turn based syntactic features and dialogue control functions. Syntactic features were extracted using dependency parsing, while dialogue control functions were manually labelled. These features were transformed using tf-idf and word embedding; feature selection was done using Principal Component Analysis (PCA). We ran experiments on six combinations of features to predict sequences with Hierarchical Agglomerative Clustering. An analysis of the clustering results indicate that using word embeddings and syntactic features, significantly improved the results.</abstract>
<identifier type="citekey">maitreyee-2020-beyond</identifier>
<identifier type="doi">10.18653/v1/2020.codi-1.2</identifier>
<location>
<url>https://aclanthology.org/2020.codi-1.2</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>11</start>
<end>19</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Beyond Adjacency Pairs: Hierarchical Clustering of Long Sequences for Human-Machine Dialogues
%A Maitreyee, Maitreyee
%Y Braud, Chloé
%Y Hardmeier, Christian
%Y Li, Junyi Jessy
%Y Louis, Annie
%Y Strube, Michael
%S Proceedings of the First Workshop on Computational Approaches to Discourse
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F maitreyee-2020-beyond
%X This work proposes a framework to predict sequences in dialogues, using turn based syntactic features and dialogue control functions. Syntactic features were extracted using dependency parsing, while dialogue control functions were manually labelled. These features were transformed using tf-idf and word embedding; feature selection was done using Principal Component Analysis (PCA). We ran experiments on six combinations of features to predict sequences with Hierarchical Agglomerative Clustering. An analysis of the clustering results indicate that using word embeddings and syntactic features, significantly improved the results.
%R 10.18653/v1/2020.codi-1.2
%U https://aclanthology.org/2020.codi-1.2
%U https://doi.org/10.18653/v1/2020.codi-1.2
%P 11-19
Markdown (Informal)
[Beyond Adjacency Pairs: Hierarchical Clustering of Long Sequences for Human-Machine Dialogues](https://aclanthology.org/2020.codi-1.2) (Maitreyee, CODI 2020)
ACL