Panlingua-KMI MT System for Similar Language Translation Task at WMT 2019

Ojha, Atul Kr.; Kumar, Ritesh; Bansal, Akanksha; Rani, Priya

doi:10.18653/v1/w19-5429

Cited by 3 publications

(2 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [50], the authors conducted a series of experiments to address the challenges of translation between similar languages. Out of which, the authors developed one phrase-based SMT system and one NMT system using byte-pair embedding for the HI↔MR pair.…”

Section: Related Workmentioning

confidence: 99%

“…Reducing Morphological Statistical Neural WX Language Pair Complexity [46] HI↔MR, ES↔PT [47] HI↔MR [48] HI↔MR [49] NE↔HI [50] HI↔MR [51] HI↔MR [52] HI↔MR [53] ES↔PT, CS↔PL, NE↔HI [70] 11 Indian languages [71] 11 Indic languages and English Proposed approach {GU,MR,NE,MAI,PA,UR}↔HI Note-HI: Hindi, MR: Marathi, ES: Spanish, PT: Portuguese, NE: Nepali, CS: Czech, PL:Polish, GU: Gujarati, MAI: Maithili, PA: Punjabi, UR: Urdu using a single standard NMT model for multiple languages [5]. Furthermore, the introduction of 'attention' in NMT has drastically improved the results significantly [7], as for many other problems.…”

Section: Paper Similar Languagementioning

confidence: 99%

See 1 more Smart Citation

Study of Local Site Conditions for Seismic Hazard Assessment at the BHU Campus, Varanasi, North India, using Ambient Noise Measurements

Kumari

Singh

Shankar

et al. 2022

Journal of the Geological Society of India

View full text Add to dashboard Cite

The use of subword embedding has proved to be a major innovation in Neural Machine Translation (NMT). It helps NMT to learn better context vectors for Low Resource Languages (LRLs) so as to predict the target words by better modelling the morphologies of the two languages and also the morphosyntax transfer. Even so, their performance for translation in Indian language to Indian language scenario is still not as good as for resource-rich languages. One reason for this is the relative morphological richness of Indian languages, while another is that most of them fall into the extremely low resource or zero-shot categories. Since most major Indian languages use Indic or Brahmi origin scripts, the text written in them is highly phonetic in nature and phonetically similar in terms of abstract letters and their arrangements. We use these characteristics of Indian languages and their scripts to propose an approach based on common multilingual Latin-based encodings (WX notation) that take advantage of language similarity while addressing the morphological complexity issue in NMT. These multilingual Latin-based encodings in NMT, together with Byte Pair Embedding (BPE) allow us to better exploit their phonetic and orthographic as well as lexical similarities to improve the translation quality by projecting different but similar languages on the same orthographic-phonetic character space. We verify the proposed approach by demonstrating experiments on similar language pairs (Gujarati↔Hindi, Marathi↔Hindi, Nepali↔Hindi, Maithili↔Hindi, Punjabi↔Hindi, and Urdu↔Hindi) under low resource conditions. The proposed approach shows an improvement in a majority of cases, in one case as much as ∼10 BLEU points compared to baseline techniques for similar language pairs. We also get up to ∼1 BLEU points improvement on distant and zero-shot language pairs.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Paper Similar Languagementioning

confidence: 99%

Study of Local Site Conditions for Seismic Hazard Assessment at the BHU Campus, Varanasi, North India, using Ambient Noise Measurements

Kumari

Singh

Shankar

et al. 2022

Journal of the Geological Society of India

View full text Add to dashboard Cite

show abstract

Low Resource Neural Machine Translation: Assamese to/from Other Indo-Aryan (Indic) Languages

BaruahRupjyoti

Mundotiya

Kumar

2021

ACM Trans. Asian Low-Resour. Lang. Inf. Process.

View full text Add to dashboard Cite

Machine translation (MT) systems have been built using numerous different techniques for bridging the language barriers. These techniques are broadly categorized into approaches like Statistical Machine Translation (SMT) and Neural Machine Translation (NMT). End-to-end NMT systems significantly outperform SMT in translation quality on many language pairs, especially those with the adequate parallel corpus. We report comparative experiments on baseline MT systems for Assamese to other Indo-Aryan languages (in both translation directions) using the traditional Phrase-Based SMT as well as some more successful NMT architectures, namely basic sequence-to-sequence model with attention, Transformer, and finetuned Transformer. The results are evaluated using the most prominent and popular standard automatic metric BLEU (BiLingual Evaluation Understudy), as well as other well-known metrics for exploring the performance of different baseline MT systems, since this is the first such work involving Assamese. The evaluation scores are compared for SMT and NMT models for the effectiveness of bi-directional language pairs involving Assamese and other Indo-Aryan languages (Bangla, Gujarati, Hindi, Marathi, Odia, Sinhalese, and Urdu). The highest BLEU scores obtained are for Assamese to Sinhalese for SMT (35.63) and the Assamese to Bangla for NMT systems (seq2seq is 50.92, Transformer is 50.01, and finetuned Transformer is 50.19). We also try to relate the results with the language characteristics, distances, family trees, domains, data sizes, and sentence lengths. We find that the effect of the domain is the most important factor affecting the results for the given data domains and sizes. We compare our results with the only existing MT system for Assamese (Bing Translator) and also with pairs involving Hindi.

show abstract

Findings of the 2019 Conference on Machine Translation (WMT19)

Barrault¹,

Bojar²,

Costa-jussà³

et al. 2019

Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1)

338

261

View full text Add to dashboard Cite

This paper presents the results of the premier shared task organized alongside the Conference on Machine Translation (WMT) 2019. Participants were asked to build machine translation systems for any of 18 language pairs, to be evaluated on a test set of news stories. The main metric for this task is human judgment of translation quality. The task was also opened up to additional test suites to probe specific aspects of translation.

show abstract

Panlingua-KMI MT System for Similar Language Translation Task at WMT 2019

Cited by 3 publications

References 15 publications

Study of Local Site Conditions for Seismic Hazard Assessment at the BHU Campus, Varanasi, North India, using Ambient Noise Measurements

Study of Local Site Conditions for Seismic Hazard Assessment at the BHU Campus, Varanasi, North India, using Ambient Noise Measurements

Low Resource Neural Machine Translation: Assamese to/from Other Indo-Aryan (Indic) Languages

Findings of the 2019 Conference on Machine Translation (WMT19)

Contact Info

Product

Resources

About