Sukanta Sen


Constrained Regeneration for Cross-Lingual Query-Focused Extractive Summarization
Elsbeth Turcan | David Wan | Faisal Ladhak | Petra Galuscakova | Sukanta Sen | Svetlana Tchistiakova | Weijia Xu | Marine Carpuat | Kenneth Heafield | Douglas Oard | Kathleen McKeown
Proceedings of the 29th International Conference on Computational Linguistics

Query-focused summaries of foreign-language, retrieved documents can help a user understand whether a document is actually relevant to the query term. A standard approach to this problem is to first translate the source documents and then perform extractive summarization to find relevant snippets. However, in a cross-lingual setting, the query term does not necessarily appear in the translations of relevant documents. In this work, we show that constrained machine translation and constrained post-editing can improve human relevance judgments by including a query term in a summary when its translation appears in the source document. We also present several strategies for selecting only certain documents for regeneration which yield further improvements


The University of Edinburgh’s Submission to the IWSLT21 Simultaneous Translation Task
Sukanta Sen | Ulrich Germann | Barry Haddow
Proceedings of the 18th International Conference on Spoken Language Translation (IWSLT 2021)

We describe our submission to the IWSLT 2021 shared task on simultaneous text-to-text English-German translation. Our system is based on the re-translation approach where the agent re-translates the whole source prefix each time it receives a new source token. This approach has the advantage of being able to use a standard neural machine translation (NMT) inference engine with beam search, however, there is a risk that incompatibility between successive re-translations will degrade the output. To improve the quality of the translations, we experiment with various approaches: we use a fixed size wait at the beginning of the sentence, we use a language model score to detect translatable units, and we apply dynamic masking to determine when the translation is unstable. We find that a combination of dynamic masking and language model score obtains the best latency-quality trade-off.

The University of Edinburgh’s Bengali-Hindi Submissions to the WMT21 News Translation Task
Proyag Pal | Alham Fikri Aji | Pinzhen Chen | Sukanta Sen
Proceedings of the Sixth Conference on Machine Translation

We describe the University of Edinburgh’s BengaliHindi constrained systems submitted to the WMT21 News Translation task. We submitted ensembles of Transformer models built with large-scale back-translation and fine-tuned on subsets of training data retrieved based on similarity to the target domain.


IITP-MT System for Gujarati-English News Translation Task at WMT 2019
Sukanta Sen | Kamal Kumar Gupta | Asif Ekbal | Pushpak Bhattacharyya
Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1)

We describe our submission to WMT 2019 News translation shared task for Gujarati-English language pair. We submit constrained systems, i.e, we rely on the data provided for this language pair and do not use any external data. We train Transformer based subword-level neural machine translation (NMT) system using original parallel corpus along with synthetic parallel corpus obtained through back-translation of monolingual data. Our primary systems achieve BLEU scores of 10.4 and 8.1 for Gujarati→English and English→Gujarati, respectively. We observe that incorporating monolingual data through back-translation improves the BLEU score significantly over baseline NMT and SMT systems for this language pair.

Parallel Corpus Filtering Based on Fuzzy String Matching
Sukanta Sen | Asif Ekbal | Pushpak Bhattacharyya
Proceedings of the Fourth Conference on Machine Translation (Volume 3: Shared Task Papers, Day 2)

In this paper, we describe the IIT Patna’s submission to WMT 2019 shared task on parallel corpus filtering. This shared task asks the participants to develop methods for scoring each parallel sentence from a given noisy parallel corpus. Quality of the scoring method is judged based on the quality of SMT and NMT systems trained on smaller set of high-quality parallel sentences sub-sampled from the original noisy corpus. This task has two language pairs. We submit for both the Nepali-English and Sinhala-English language pairs. We define fuzzy string matching score between English and the translated (into English) source based on Levenshtein distance. Based on the scores, we sub-sample two sets (having 1 million and 5 millions English tokens) of parallel sentences from each parallel corpus, and train SMT systems for development purpose only. The organizers publish the official evaluation using both SMT and NMT on the final official test set. Total 10 teams participated in the shared task and according the official evaluation, our scoring method obtains 2nd position in the team ranking for 1-million NepaliEnglish NMT and 5-million Sinhala-English NMT categories.

Multilingual Unsupervised NMT using Shared Encoder and Language-Specific Decoders
Sukanta Sen | Kamal Kumar Gupta | Asif Ekbal | Pushpak Bhattacharyya
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

In this paper, we propose a multilingual unsupervised NMT scheme which jointly trains multiple languages with a shared encoder and multiple decoders. Our approach is based on denoising autoencoding of each language and back-translating between English and multiple non-English languages. This results in a universal encoder which can encode any language participating in training into an inter-lingual representation, and language-specific decoders. Our experiments using only monolingual corpora show that multilingual unsupervised model performs better than the separately trained bilingual models achieving improvement of up to 1.48 BLEU points on WMT test sets. We also observe that even if we do not train the network for all possible translation directions, the network is still able to translate in a many-to-many fashion leveraging encoder’s ability to generate interlingual representation.


IITP-MT at WAT2018: Transformer-based Multilingual Indic-English Neural Machine Translation System
Sukanta Sen | Kamal Kumar Gupta | Asif Ekbal | Pushpak Bhattacharyya
Proceedings of the 32nd Pacific Asia Conference on Language, Information and Computation: 5th Workshop on Asian Translation: 5th Workshop on Asian Translation

Solving Data Sparsity for Aspect Based Sentiment Analysis Using Cross-Linguality and Multi-Linguality
Md Shad Akhtar | Palaash Sawant | Sukanta Sen | Asif Ekbal | Pushpak Bhattacharyya
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)

Efficient word representations play an important role in solving various problems related to Natural Language Processing (NLP), data mining, text mining etc. The issue of data sparsity poses a great challenge in creating efficient word representation model for solving the underlying problem. The problem is more intensified in resource-poor scenario due to the absence of sufficient amount of corpus. In this work we propose to minimize the effect of data sparsity by leveraging bilingual word embeddings learned through a parallel corpus. We train and evaluate Long Short Term Memory (LSTM) based architecture for aspect level sentiment classification. The neural network architecture is further assisted by the hand-crafted features for the prediction. We show the efficacy of the proposed model against state-of-the-art methods in two experimental setups i.e. multi-lingual and cross-lingual.


Temporality as Seen through Translation: A Case Study on Hindi Texts
Sabyasachi Kamila | Sukanta Sen | Mohammad Hasanuzzaman | Asif Ekbal | Andy Way | Pushpak Bhattacharyya
Proceedings of Machine Translation Summit XVI: Research Track


IITP English-Hindi Machine Translation System at WAT 2016
Sukanta Sen | Debajyoty Banik | Asif Ekbal | Pushpak Bhattacharyya
Proceedings of the 3rd Workshop on Asian Translation (WAT2016)

In this paper we describe the system that we develop as part of our participation in WAT 2016. We develop a system based on hierarchical phrase-based SMT for English to Hindi language pair. We perform re-ordering and augment bilingual dictionary to improve the performance. As a baseline we use a phrase-based SMT model. The MT models are fine-tuned on the development set, and the best configurations are used to report the evaluation on the test set. Experiments show the BLEU of 13.71 on the benchmark test data. This is better compared to the official baseline BLEU score of 10.79.

Can SMT and RBMT Improve each other’s Performance?- An Experiment with English-Hindi Translation
Debajyoty Banik | Sukanta Sen | Asif Ekbal | Pushpak Bhattacharyya
Proceedings of the 13th International Conference on Natural Language Processing