@inproceedings{kathakali-etal-2023-effect,
title = "Effect of Pivot Language and Segment-Based Few-Shot Prompting for Cross-Domain Multi-Intent Identification in Low Resource Languages",
author = "Kathakali, Mitra and
Aditha Venkata Santosh, Ashish and
Soumya, Teotia and
Aruna, Malapati",
editor = "Jyoti, D. Pawar and
Sobha, Lalitha Devi",
booktitle = "Proceedings of the 20th International Conference on Natural Language Processing (ICON)",
month = dec,
year = "2023",
address = "Goa University, Goa, India",
publisher = "NLP Association of India (NLPAI)",
url = "https://aclanthology.org/2023.icon-1.27",
pages = "349--356",
abstract = "NLU (Natural Language Understanding) has considerable difficulties in identifying multiple intentions across different domains in languages with limited resources. Our contributions involve utilizing pivot languages with similar semantics for NLU tasks, creating a vector database for efficient retrieval and indexing of language embeddings in high-resource languages for Retrieval Augmented Generation (RAG) in low-resource languages, and thoroughly investigating the effect of segmentbased strategies on complex user utterances across multiple domains and intents in the development of a Chain of Thought Prompting (COT) combined with Retrieval Augmented Generation. The study investigated recursive approaches to identify the most effective zeroshot instances for segment-based prompting. A comparison analysis was conducted to compare the effectiveness of sentence-based prompting vs segment-based prompting across different domains and multiple intents. This research offers a promising avenue to address the formidable challenges of NLU in low-resource languages, with potential applications in conversational agents and dialogue systems and a broader impact on linguistic understanding and inclusivity.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kathakali-etal-2023-effect">
<titleInfo>
<title>Effect of Pivot Language and Segment-Based Few-Shot Prompting for Cross-Domain Multi-Intent Identification in Low Resource Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mitra</namePart>
<namePart type="family">Kathakali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ashish</namePart>
<namePart type="family">Aditha Venkata Santosh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Teotia</namePart>
<namePart type="family">Soumya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Malapati</namePart>
<namePart type="family">Aruna</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 20th International Conference on Natural Language Processing (ICON)</title>
</titleInfo>
<name type="personal">
<namePart type="given">D</namePart>
<namePart type="given">Pawar</namePart>
<namePart type="family">Jyoti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lalitha</namePart>
<namePart type="given">Devi</namePart>
<namePart type="family">Sobha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>NLP Association of India (NLPAI)</publisher>
<place>
<placeTerm type="text">Goa University, Goa, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>NLU (Natural Language Understanding) has considerable difficulties in identifying multiple intentions across different domains in languages with limited resources. Our contributions involve utilizing pivot languages with similar semantics for NLU tasks, creating a vector database for efficient retrieval and indexing of language embeddings in high-resource languages for Retrieval Augmented Generation (RAG) in low-resource languages, and thoroughly investigating the effect of segmentbased strategies on complex user utterances across multiple domains and intents in the development of a Chain of Thought Prompting (COT) combined with Retrieval Augmented Generation. The study investigated recursive approaches to identify the most effective zeroshot instances for segment-based prompting. A comparison analysis was conducted to compare the effectiveness of sentence-based prompting vs segment-based prompting across different domains and multiple intents. This research offers a promising avenue to address the formidable challenges of NLU in low-resource languages, with potential applications in conversational agents and dialogue systems and a broader impact on linguistic understanding and inclusivity.</abstract>
<identifier type="citekey">kathakali-etal-2023-effect</identifier>
<location>
<url>https://aclanthology.org/2023.icon-1.27</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>349</start>
<end>356</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Effect of Pivot Language and Segment-Based Few-Shot Prompting for Cross-Domain Multi-Intent Identification in Low Resource Languages
%A Kathakali, Mitra
%A Aditha Venkata Santosh, Ashish
%A Soumya, Teotia
%A Aruna, Malapati
%Y Jyoti, D. Pawar
%Y Sobha, Lalitha Devi
%S Proceedings of the 20th International Conference on Natural Language Processing (ICON)
%D 2023
%8 December
%I NLP Association of India (NLPAI)
%C Goa University, Goa, India
%F kathakali-etal-2023-effect
%X NLU (Natural Language Understanding) has considerable difficulties in identifying multiple intentions across different domains in languages with limited resources. Our contributions involve utilizing pivot languages with similar semantics for NLU tasks, creating a vector database for efficient retrieval and indexing of language embeddings in high-resource languages for Retrieval Augmented Generation (RAG) in low-resource languages, and thoroughly investigating the effect of segmentbased strategies on complex user utterances across multiple domains and intents in the development of a Chain of Thought Prompting (COT) combined with Retrieval Augmented Generation. The study investigated recursive approaches to identify the most effective zeroshot instances for segment-based prompting. A comparison analysis was conducted to compare the effectiveness of sentence-based prompting vs segment-based prompting across different domains and multiple intents. This research offers a promising avenue to address the formidable challenges of NLU in low-resource languages, with potential applications in conversational agents and dialogue systems and a broader impact on linguistic understanding and inclusivity.
%U https://aclanthology.org/2023.icon-1.27
%P 349-356
Markdown (Informal)
[Effect of Pivot Language and Segment-Based Few-Shot Prompting for Cross-Domain Multi-Intent Identification in Low Resource Languages](https://aclanthology.org/2023.icon-1.27) (Kathakali et al., ICON 2023)
ACL