@inproceedings{das-etal-2022-revisiting,
title = "Revisiting Anwesha:Enhancing Personalised and Natural Search in {B}angla",
author = "Das, Arup and
Acharya, Joyojyoti and
Kundu, Bibekananda and
Chakraborti, Sutanu",
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.24/",
pages = "183--193",
abstract = "Bangla is a low-resource, highly agglutinative language. Thus it is challenging to facilitate an effective search of Bangla documents. We have created a gold standard dataset containing query document relevance pairs for evaluation purposes. We utilise Named Entities to improve the retrieval effectiveness of traditional Bangla search algorithms. We suggest a reasonable starting model for leveraging implicit preference feedback based on the user search behaviour to enhance the results retrieved by the Explicit Semantic Analysis (ESA) approach. We use contextual sentence embeddings obtained via Language-agnostic BERT Sentence Embedding (LaBSE) to rerank the candidate documents retrieved by the traditional search algorithms (tf-idf) based on the top sentences that are most relevant to the query. This paper presents our empirical findings across these directions and critically analyses the results."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="das-etal-2022-revisiting">
<titleInfo>
<title>Revisiting Anwesha:Enhancing Personalised and Natural Search in Bangla</title>
</titleInfo>
<name type="personal">
<namePart type="given">Arup</namePart>
<namePart type="family">Das</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyojyoti</namePart>
<namePart type="family">Acharya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bibekananda</namePart>
<namePart type="family">Kundu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sutanu</namePart>
<namePart type="family">Chakraborti</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>Bangla is a low-resource, highly agglutinative language. Thus it is challenging to facilitate an effective search of Bangla documents. We have created a gold standard dataset containing query document relevance pairs for evaluation purposes. We utilise Named Entities to improve the retrieval effectiveness of traditional Bangla search algorithms. We suggest a reasonable starting model for leveraging implicit preference feedback based on the user search behaviour to enhance the results retrieved by the Explicit Semantic Analysis (ESA) approach. We use contextual sentence embeddings obtained via Language-agnostic BERT Sentence Embedding (LaBSE) to rerank the candidate documents retrieved by the traditional search algorithms (tf-idf) based on the top sentences that are most relevant to the query. This paper presents our empirical findings across these directions and critically analyses the results.</abstract>
<identifier type="citekey">das-etal-2022-revisiting</identifier>
<location>
<url>https://aclanthology.org/2022.icon-main.24/</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>183</start>
<end>193</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Revisiting Anwesha:Enhancing Personalised and Natural Search in Bangla
%A Das, Arup
%A Acharya, Joyojyoti
%A Kundu, Bibekananda
%A Chakraborti, Sutanu
%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 das-etal-2022-revisiting
%X Bangla is a low-resource, highly agglutinative language. Thus it is challenging to facilitate an effective search of Bangla documents. We have created a gold standard dataset containing query document relevance pairs for evaluation purposes. We utilise Named Entities to improve the retrieval effectiveness of traditional Bangla search algorithms. We suggest a reasonable starting model for leveraging implicit preference feedback based on the user search behaviour to enhance the results retrieved by the Explicit Semantic Analysis (ESA) approach. We use contextual sentence embeddings obtained via Language-agnostic BERT Sentence Embedding (LaBSE) to rerank the candidate documents retrieved by the traditional search algorithms (tf-idf) based on the top sentences that are most relevant to the query. This paper presents our empirical findings across these directions and critically analyses the results.
%U https://aclanthology.org/2022.icon-main.24/
%P 183-193
Markdown (Informal)
[Revisiting Anwesha:Enhancing Personalised and Natural Search in Bangla](https://aclanthology.org/2022.icon-main.24/) (Das et al., ICON 2022)
ACL