Exploring Web-based Translation Resources Applied to Hindi-English Cross-Lingual Information Retrieval-Reference-Cited by-同舟云学术

Exploring Web-based Translation Resources Applied to Hindi-English Cross-Lingual Information Retrieval

Published:2022-12-06 Issue: Volume: Page:
ISSN:2375-4699
Container-title:ACM Transactions on Asian and Low-Resource Language Information Processing
language:en
Short-container-title:ACM Trans. Asian Low-Resour. Lang. Inf. Process.

Author:

Sharma Vijay Kumar,Mittal Namita¹,Vidyarthi Ankit²,Gupta Deepak³

Affiliation:

1. Malaviya National Institute of Technology Department of Computer Science & Engineering, India

2. Jaypee Institute of Information Technology Noida Department of CSE&IT, India

3. Maharaja Agrasen Institute of Technology, Delhi and Chandigarh University, Mohali Department of CSE and Reseach Advisor, UCRD, Mohali, India

Abstract

Internet users perceive a multilingual web but are unfamiliar with it due to communication in their regional language called Cross-Lingual Information Retrieval (CLIR). In CLIR, a translation technique is used to translate the user queries into the target documents language. Conventional translation techniques are based on either a manual dictionary or a parallel corpus. While the trending Statistical Machine Translation (SMT) and Neural Machine Translation (NMT) techniques are trained on a parallel corpus. NMT is not so mature for Hindi-English translation, according to the literature, SMT performs better than the NMT. SMT provides a static translation due to the limited vocabularies in the available parallel corpus. It may not provide the translations for missing or unseen words while the web provides a dynamic interface where multiple users are updating information at the same time. The web may provide the translations for missing or unseen words, therefore, the web is effectively used for technically developed languages like English, German, Spanish, Russian, and Chinese. In this paper, different web resources such as Wikipedia, Hindi WordNet & Indo WordNet, ConceptNet, and online dictionary-based translation techniques are proposed and applied to Hindi-English CLIR. Wikipedia-based translation approach incorporates three modules, i.e., exactly matched, partially matched, and disambiguation to address the issues of wrong inter-wiki links, partially matched terms, and ambiguous articles. Hindi WordNet & Indo WorNet attribute ”English synset” and ConceptNet attributes ”Related term” & ”Synonymy” are used for obtaining translations. Further, WordNet path similarity is used to disambiguate translations. Various online dictionaries are available that return multiple relevant and irrelevant translations. The proposed approaches are compared to the SMT where the Wikipedia-based approach achieves approximately similar mean average precision to SMT.

Publisher

Association for Computing Machinery (ACM)

Subject

General Computer Science

Link

https://dl.acm.org/doi/pdf/10.1145/3569010

Reference45 articles.

1. Mustafa Abusalah John Tait and Michael Oakes. 2005. Literature review of cross-language information retrieval. In Transactions on Engineering Computing and Technology ISSN. Citeseer. Mustafa Abusalah John Tait and Michael Oakes. 2005. Literature review of cross-language information retrieval. In Transactions on Engineering Computing and Technology ISSN. Citeseer.

2. Language independent identification of parallel sentences using Wikipedia

3. Paheli Bhattacharya , Pawan Goyal , and Sudeshna Sarkar . 2016. Using word embeddings for query translation for hindi to english cross language information retrieval. Computación y Sistemas 20, 3 ( 2016 ), 435–447. Paheli Bhattacharya, Pawan Goyal, and Sudeshna Sarkar. 2016. Using word embeddings for query translation for hindi to english cross language information retrieval. Computación y Sistemas 20, 3 (2016), 435–447.

4. Pushpak Bhattacharyya and others. 2017. Indowordnets help in Indian Language Machine Translation. arXiv preprint arXiv:1710.02086(2017). Pushpak Bhattacharyya and others. 2017. Indowordnets help in Indian Language Machine Translation. arXiv preprint arXiv:1710.02086(2017).

5. Ondrej Bojar Vojtech Diatka Pavel Rychlỳ Pavel Stranák Vít Suchomel Ales Tamchyna and Daniel Zeman. 2014. HindEnCorp-Hindi-English and Hindi-only Corpus for Machine Translation.. In LREC. 3550–3555. Ondrej Bojar Vojtech Diatka Pavel Rychlỳ Pavel Stranák Vít Suchomel Ales Tamchyna and Daniel Zeman. 2014. HindEnCorp-Hindi-English and Hindi-only Corpus for Machine Translation.. In LREC. 3550–3555.

Cited by 1 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. A System for Language Translation using Sequence-to-sequence Learning based Encoder;2023 International Conference on Emerging Smart Computing and Informatics (ESCI);2023-03-01