@inproceedings{pandey-etal-2022-mix,
title = "Mix-and-Match: Scalable Dialog Response Retrieval using {G}aussian Mixture Embeddings",
author = "Pandey, Gaurav and
Contractor, Danish and
Joshi, Sachindra",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2022",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-emnlp.239/",
doi = "10.18653/v1/2022.findings-emnlp.239",
pages = "3273--3287",
abstract = "Embedding-based approaches for dialog response retrieval embed the context-response pairs as points in the embedding space. These approaches are scalable, but fail to account for the complex, many-to-many relationships that exist between context-response pairs. On the other end of the spectrum, there are approaches that feed the context-response pairs jointly through multiple layers of neural networks. These approaches can model the complex relationships between context-response pairs, but fail to scale when the set of responses is moderately large ({\ensuremath{>}}1000). In this paper, we propose a scalable model that can learn complex relationships between context-response pairs. Specifically, the model maps the contexts as well as responses to probability distributions over the embedding space. We train the models by optimizing the Kullback-Leibler divergence between the distributions induced by context-response pairs in the training data. We show that the resultant model achieves better performance as compared to other embedding-based approaches on publicly available conversation data."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pandey-etal-2022-mix">
<titleInfo>
<title>Mix-and-Match: Scalable Dialog Response Retrieval using Gaussian Mixture Embeddings</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gaurav</namePart>
<namePart type="family">Pandey</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Danish</namePart>
<namePart type="family">Contractor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sachindra</namePart>
<namePart type="family">Joshi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Embedding-based approaches for dialog response retrieval embed the context-response pairs as points in the embedding space. These approaches are scalable, but fail to account for the complex, many-to-many relationships that exist between context-response pairs. On the other end of the spectrum, there are approaches that feed the context-response pairs jointly through multiple layers of neural networks. These approaches can model the complex relationships between context-response pairs, but fail to scale when the set of responses is moderately large (\ensuremath>1000). In this paper, we propose a scalable model that can learn complex relationships between context-response pairs. Specifically, the model maps the contexts as well as responses to probability distributions over the embedding space. We train the models by optimizing the Kullback-Leibler divergence between the distributions induced by context-response pairs in the training data. We show that the resultant model achieves better performance as compared to other embedding-based approaches on publicly available conversation data.</abstract>
<identifier type="citekey">pandey-etal-2022-mix</identifier>
<identifier type="doi">10.18653/v1/2022.findings-emnlp.239</identifier>
<location>
<url>https://aclanthology.org/2022.findings-emnlp.239/</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>3273</start>
<end>3287</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Mix-and-Match: Scalable Dialog Response Retrieval using Gaussian Mixture Embeddings
%A Pandey, Gaurav
%A Contractor, Danish
%A Joshi, Sachindra
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Findings of the Association for Computational Linguistics: EMNLP 2022
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F pandey-etal-2022-mix
%X Embedding-based approaches for dialog response retrieval embed the context-response pairs as points in the embedding space. These approaches are scalable, but fail to account for the complex, many-to-many relationships that exist between context-response pairs. On the other end of the spectrum, there are approaches that feed the context-response pairs jointly through multiple layers of neural networks. These approaches can model the complex relationships between context-response pairs, but fail to scale when the set of responses is moderately large (\ensuremath>1000). In this paper, we propose a scalable model that can learn complex relationships between context-response pairs. Specifically, the model maps the contexts as well as responses to probability distributions over the embedding space. We train the models by optimizing the Kullback-Leibler divergence between the distributions induced by context-response pairs in the training data. We show that the resultant model achieves better performance as compared to other embedding-based approaches on publicly available conversation data.
%R 10.18653/v1/2022.findings-emnlp.239
%U https://aclanthology.org/2022.findings-emnlp.239/
%U https://doi.org/10.18653/v1/2022.findings-emnlp.239
%P 3273-3287
Markdown (Informal)
[Mix-and-Match: Scalable Dialog Response Retrieval using Gaussian Mixture Embeddings](https://aclanthology.org/2022.findings-emnlp.239/) (Pandey et al., Findings 2022)
ACL