Shefali Saxena
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Shefali Saxena has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Philemon Daniel
National Institute of Technology
11 shared publications - Shweta Chauhan
Indian Institute of Technology Ropar
11 shared publications Philemon Daniel
3 shared publications- Amandeep Kaur
Atal Bihari Vajpayee Indian Institute of Information Technology and Management Gwalior, India
1 shared publication Ayush Gupta
1 shared publication- Ayush Gupta
Department of Electronics and Communication Engineering, National Institute of Technology, Hamirpur, India
1 shared publication
Latest Publications
- 15 January 2024
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 83 (24) , 64255-64269
Efficient Data Augmentation via lexical matching for boosting performance on Statistical Machine Translation for Indic and a Low-resource language
- 15 January 2024
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 83 (24) , 64255-64269
Efficient Data Augmentation via lexical matching for boosting performance on Statistical Machine Translation for Indic and a Low-resource language
- Top Cited Papers
- 2 April 2023
- Published by Taylor & Francis in IETE Journal of Research
- Vol. 70 (4) , 3823-3834
SemSyn: Semantic-Syntactic Similarity Based Automatic Machine Translation Evaluation Metric
Machine translation evaluation is difficult and challenging for natural languages because different languages behave differently for the same dataset. Lexical-based metrics have been poorly represented semantic relationships and impose strict identity matching. However, translation and assessment become difficult for target morphologically rich languages with relatively free word order. Most of the standard evaluation metrics consider word order but do not effectively consider sentence structure. In this paper, we propose a novel machine translation evaluation metric SemSyn which incorporates both semantic and syntactic similarity. We incorporate the term frequency-inverse document frequency with the earth mover’s distance and word embedding to cover the semantic similarity. The part of speech and dependency parsing tags assist in covering syntactic similarity in the sentence structure. Part of speech and dependency parsing tags are extracted from universal dependencies and trained on the SpaCy library. Experimental results show that SemSyn has a higher correlation with human judgment than other evaluation metrics for morphologically rich language and other languages.
- 2 April 2023
- Published by Taylor & Francis in IETE Journal of Research
- Vol. 70 (4) , 3823-3834
Top Cited PapersSemSyn: Semantic-Syntactic Similarity Based Automatic Machine Translation Evaluation Metric
Machine translation evaluation is difficult and challenging for natural languages because different languages behave differently for the same dataset. Lexical-based metrics have been poorly represented semantic relationships and impose strict identity matching. However, translation and assessment become difficult for target morphologically rich languages with relatively free word order. Most of the standard evaluation metrics consider word order but do not effectively consider sentence structure. In this paper, we propose a novel machine translation evaluation metric SemSyn which incorporates both semantic and syntactic similarity. We incorporate the term frequency-inverse document frequency with the earth mover’s distance and word embedding to cover the semantic similarity. The part of speech and dependency parsing tags assist in covering syntactic similarity in the sentence structure. Part of speech and dependency parsing tags are extracted from universal dependencies and trained on the SpaCy library. Experimental results show that SemSyn has a higher correlation with human judgment than other evaluation metrics for morphologically rich language and other languages.
- 1 November 2022
- Published by Taylor & Francis in Journal of Experimental & Theoretical Artificial Intelligence
- Vol. 36 (7) , 1173-1186
Enhanced unsupervised neural machine translation by cross lingual sense embedding and filtered back-translation for morphological and endangered Indic languages
The fast growth of communication technology has brought nations and their cultures closer together, and the demand for cross-language communication has risen tremendously. There is a different learning method to connect the source language to the target language in which unsupervised learning is a blessing for low-resource languages. The unsupervised machine translation is always problematic to those languages which are morphologically rich and low resources languages. Morphologically rich and low-resource language does not provide good results in machine translation if the translation is from morphologically less complex language to morphologically more complex languages. In this paper, we have improved the unsupervised neural machine translation by tackling the ambiguity problem and the quality of pseudo-parallel sentence pairs generated through back-translation for morphologically rich languages. The ambiguity problem is solved by taking the cross-lingual sense embedding at the source side instead of cross-lingual word embedding. By giving more weight to better pseudo-parallel sentence pairs in the back-translation step, the quality of pseudo-parallel sentences is increased. Different evaluation metrics have been used to check the robustness of the model and compared with different baseline models. The experiment is performed on different morphologically rich languages English-Hindi, English-Tamil, English-Telegu, and one low-resource endangered kangri language.
- 1 November 2022
- Published by Taylor & Francis in Journal of Experimental & Theoretical Artificial Intelligence
- Vol. 36 (7) , 1173-1186
Enhanced unsupervised neural machine translation by cross lingual sense embedding and filtered back-translation for morphological and endangered Indic languages
The fast growth of communication technology has brought nations and their cultures closer together, and the demand for cross-language communication has risen tremendously. There is a different learning method to connect the source language to the target language in which unsupervised learning is a blessing for low-resource languages. The unsupervised machine translation is always problematic to those languages which are morphologically rich and low resources languages. Morphologically rich and low-resource language does not provide good results in machine translation if the translation is from morphologically less complex language to morphologically more complex languages. In this paper, we have improved the unsupervised neural machine translation by tackling the ambiguity problem and the quality of pseudo-parallel sentence pairs generated through back-translation for morphologically rich languages. The ambiguity problem is solved by taking the cross-lingual sense embedding at the source side instead of cross-lingual word embedding. By giving more weight to better pseudo-parallel sentence pairs in the back-translation step, the quality of pseudo-parallel sentences is increased. Different evaluation metrics have been used to check the robustness of the model and compared with different baseline models. The experiment is performed on different morphologically rich languages English-Hindi, English-Tamil, English-Telegu, and one low-resource endangered kangri language.
- 4 September 2022
- Published by Taylor & Francis in Journal of Experimental & Theoretical Artificial Intelligence
- Vol. 36 (6) , 1-20
Unsupervised SMT: an analysis of Indic languages and a low resource language
The rapid globalisation in language technology and the Internet’s fast expansion have brought nations and their cultures close together, and the demand for inter-language interactions has risen enormously. However, in many low-resource languages (LRL) pairings and areas, Machine Translation (MT) is still not viable because of a lack of parallel data. The challenge of MT is still unsolved. Recent studies employing monolingual datasets have shown excellent outcomes in Phrase-based Statistical MT (PBSMT) and Neural MT (NMT) systems. However, earlier researchers have demonstrated that unsupervised Statistical MT surpasses unsupervised NMT, especially for different language pairings. The study unveils the compendium of ten unsupervised SMT systems translation tasks utilizing a monolingual dataset from the Dravidian and Indo-Aryan language families; and a low-resource endangered language. The machine-translated experimental outcomes examined the system using different tokenizers and investigated them for various language pairs using different evaluation metrics for various iterations. The statistical significance of test results has been computed for each evaluation metric to check the true system quality of the translation tasks.
- 4 September 2022
- Published by Taylor & Francis in Journal of Experimental & Theoretical Artificial Intelligence
- Vol. 36 (6) , 1-20
Unsupervised SMT: an analysis of Indic languages and a low resource language
The rapid globalisation in language technology and the Internet’s fast expansion have brought nations and their cultures close together, and the demand for inter-language interactions has risen enormously. However, in many low-resource languages (LRL) pairings and areas, Machine Translation (MT) is still not viable because of a lack of parallel data. The challenge of MT is still unsolved. Recent studies employing monolingual datasets have shown excellent outcomes in Phrase-based Statistical MT (PBSMT) and Neural MT (NMT) systems. However, earlier researchers have demonstrated that unsupervised Statistical MT surpasses unsupervised NMT, especially for different language pairings. The study unveils the compendium of ten unsupervised SMT systems translation tasks utilizing a monolingual dataset from the Dravidian and Indo-Aryan language families; and a low-resource endangered language. The machine-translated experimental outcomes examined the system using different tokenizers and investigated them for various language pairs using different evaluation metrics for various iterations. The statistical significance of test results has been computed for each evaluation metric to check the true system quality of the translation tasks.
- 22 July 2022
- Published by Taylor & Francis in IETE Journal of Research
- Vol. 69 (12) , 8848-8858
Improved Unsupervised Statistical Machine TranslationviaUnsupervised Word Sense Disambiguation for a Low-Resource and Indic Languages
Besides word order, word choice is a key stumbling block for machine translation (MT) in morphologically rich languages due to homonyms and polysemous difficulties. On the other hand, un-translated/improperly translated words are a severe issue for Statistical Machine Translation (SMT) models. The quantity of parallel training corpus has limited unsupervised SMT (USMT) systems. Still, current research lines have successfully trained SMT systems in an unsupervised manner using monolingual data alone. However, there is still a need to enhance the translation quality of the MT output due to unaligned and improperly sensed words. This problem is addressed by incorporating unsupervised Word Sense Disambiguation (WSD) into the decoding phase of USMT. The work provided a compendium of SMT systems for five translation tasks, i.e. En→Indic languages for the WMT test dataset and evaluated on BLEU and METEOR evaluation metrics. The studies were performed on En→Hi, En→Kn, En→Ta, En→Te, and En→Be tasks and showed an improvement in BLEU points by 2.3, 2.68, 0.78, 2.32, and 1.79, respectively, and METEOR points by 1.07, 1.34, 0.72, 0.693, and 1.191, respectively, over the baseline model.
- 22 July 2022
- Published by Taylor & Francis in IETE Journal of Research
- Vol. 69 (12) , 8848-8858
Improved Unsupervised Statistical Machine TranslationviaUnsupervised Word Sense Disambiguation for a Low-Resource and Indic Languages
Besides word order, word choice is a key stumbling block for machine translation (MT) in morphologically rich languages due to homonyms and polysemous difficulties. On the other hand, un-translated/improperly translated words are a severe issue for Statistical Machine Translation (SMT) models. The quantity of parallel training corpus has limited unsupervised SMT (USMT) systems. Still, current research lines have successfully trained SMT systems in an unsupervised manner using monolingual data alone. However, there is still a need to enhance the translation quality of the MT output due to unaligned and improperly sensed words. This problem is addressed by incorporating unsupervised Word Sense Disambiguation (WSD) into the decoding phase of USMT. The work provided a compendium of SMT systems for five translation tasks, i.e. En→Indic languages for the WMT test dataset and evaluated on BLEU and METEOR evaluation metrics. The studies were performed on En→Hi, En→Kn, En→Ta, En→Te, and En→Be tasks and showed an improvement in BLEU points by 2.3, 2.68, 0.78, 2.32, and 1.79, respectively, and METEOR points by 1.07, 1.34, 0.72, 0.693, and 1.191, respectively, over the baseline model.
- 27 June 2022
- Published by Springer Nature in Sādhanā
- Vol. 47 (3) , 1-5
Kinnauri-Pahari (version_0.1): parallel, monolingual dataset and word-embeddings
- 27 June 2022
- Published by Springer Nature in Sādhanā
- Vol. 47 (3) , 1-5
Kinnauri-Pahari (version_0.1): parallel, monolingual dataset and word-embeddings
- 2 June 2022
- Published by Springer Nature in Sādhanā
- Vol. 47 (2) , 1-5
Explicitly unsupervised statistical machine translation analysis on five Indian languages using automatic evaluation metrics
- 2 June 2022
- Published by Springer Nature in Sādhanā
- Vol. 47 (2) , 1-5
Explicitly unsupervised statistical machine translation analysis on five Indian languages using automatic evaluation metrics
- 24 April 2022
- Published by Springer Nature
- p. 61-68
Analysis of Unsupervised Statistical Machine Translation Using Cross-Lingual Word Embedding for English–Hindi
- 24 April 2022
- Published by Springer Nature
- p. 61-68
Analysis of Unsupervised Statistical Machine Translation Using Cross-Lingual Word Embedding for English–Hindi
- 24 April 2022
- Published by Springer Nature
- p. 53-60
A Universal Dependency Treebank for Definitely Endangered Low-Resource Kangri Language
- 24 April 2022
- Published by Springer Nature
- p. 53-60
A Universal Dependency Treebank for Definitely Endangered Low-Resource Kangri Language