@inproceedings{banerjee-etal-2022-generalised,
title = "Generalised Spherical Text Embedding",
author = "Banerjee, Souvik and
Mishra, Bamdev and
Jawanpuria, Pratik and
Shrivastava, Manish Shrivastava",
editor = "Akhtar, Md. Shad and
Chakraborty, Tanmoy",
booktitle = "Proceedings of the 19th International Conference on Natural Language Processing (ICON)",
month = dec,
year = "2022",
address = "New Delhi, India",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.icon-main.11",
pages = "80--85",
abstract = "This paper aims to provide an unsupervised modelling approach that allows for a more flexible representation of text embeddings. It jointly encodes the words and the paragraphs as individual matrices of arbitrary column dimension with unit Frobenius norm. The representation is also linguistically motivated with the introduction of a metric for the ambient space in which we train the embeddings that calculates the similarity between matrices of unequal number of columns. Thus, the proposed modelling and the novel similarity metric exploits the matrix structure of embeddings. We then go on to show that the same matrices can be reshaped into vectors of unit norm and transform our problem into an optimization problem in a spherical manifold for optimization simplicity. Given the total number of matrices we are dealing with, which is equal to the vocab size plus the total number of documents in the corpus, this makes the training of an otherwise expensive non-linear model extremely efficient. We also quantitatively verify the quality of our text embeddings by showing that they demonstrate improved results in document classification, document clustering and semantic textual similarity benchmark tests.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="banerjee-etal-2022-generalised">
<titleInfo>
<title>Generalised Spherical Text Embedding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Souvik</namePart>
<namePart type="family">Banerjee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bamdev</namePart>
<namePart type="family">Mishra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pratik</namePart>
<namePart type="family">Jawanpuria</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manish</namePart>
<namePart type="given">Shrivastava</namePart>
<namePart type="family">Shrivastava</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>Proceedings of the 19th International Conference on Natural Language Processing (ICON)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Md.</namePart>
<namePart type="given">Shad</namePart>
<namePart type="family">Akhtar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">New Delhi, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper aims to provide an unsupervised modelling approach that allows for a more flexible representation of text embeddings. It jointly encodes the words and the paragraphs as individual matrices of arbitrary column dimension with unit Frobenius norm. The representation is also linguistically motivated with the introduction of a metric for the ambient space in which we train the embeddings that calculates the similarity between matrices of unequal number of columns. Thus, the proposed modelling and the novel similarity metric exploits the matrix structure of embeddings. We then go on to show that the same matrices can be reshaped into vectors of unit norm and transform our problem into an optimization problem in a spherical manifold for optimization simplicity. Given the total number of matrices we are dealing with, which is equal to the vocab size plus the total number of documents in the corpus, this makes the training of an otherwise expensive non-linear model extremely efficient. We also quantitatively verify the quality of our text embeddings by showing that they demonstrate improved results in document classification, document clustering and semantic textual similarity benchmark tests.</abstract>
<identifier type="citekey">banerjee-etal-2022-generalised</identifier>
<location>
<url>https://aclanthology.org/2022.icon-main.11</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>80</start>
<end>85</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Generalised Spherical Text Embedding
%A Banerjee, Souvik
%A Mishra, Bamdev
%A Jawanpuria, Pratik
%A Shrivastava, Manish Shrivastava
%Y Akhtar, Md. Shad
%Y Chakraborty, Tanmoy
%S Proceedings of the 19th International Conference on Natural Language Processing (ICON)
%D 2022
%8 December
%I Association for Computational Linguistics
%C New Delhi, India
%F banerjee-etal-2022-generalised
%X This paper aims to provide an unsupervised modelling approach that allows for a more flexible representation of text embeddings. It jointly encodes the words and the paragraphs as individual matrices of arbitrary column dimension with unit Frobenius norm. The representation is also linguistically motivated with the introduction of a metric for the ambient space in which we train the embeddings that calculates the similarity between matrices of unequal number of columns. Thus, the proposed modelling and the novel similarity metric exploits the matrix structure of embeddings. We then go on to show that the same matrices can be reshaped into vectors of unit norm and transform our problem into an optimization problem in a spherical manifold for optimization simplicity. Given the total number of matrices we are dealing with, which is equal to the vocab size plus the total number of documents in the corpus, this makes the training of an otherwise expensive non-linear model extremely efficient. We also quantitatively verify the quality of our text embeddings by showing that they demonstrate improved results in document classification, document clustering and semantic textual similarity benchmark tests.
%U https://aclanthology.org/2022.icon-main.11
%P 80-85
Markdown (Informal)
[Generalised Spherical Text Embedding](https://aclanthology.org/2022.icon-main.11) (Banerjee et al., ICON 2022)
ACL
- Souvik Banerjee, Bamdev Mishra, Pratik Jawanpuria, and Manish Shrivastava Shrivastava. 2022. Generalised Spherical Text Embedding. In Proceedings of the 19th International Conference on Natural Language Processing (ICON), pages 80–85, New Delhi, India. Association for Computational Linguistics.