Ruchit Agrawal


pdf bib
No more beating about the bush : A Step towards Idiom Handling for Indian Language NLP
Ruchit Agrawal | Vighnesh Chenthil Kumar | Vigneshwaran Muralidharan | Dipti Sharma
Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)

pdf bib
Contextual Handling in Neural Machine Translation: Look behind, ahead and on both sides
Ruchit Agrawal | Marco Turchi | Matteo Negri
Proceedings of the 21st Annual Conference of the European Association for Machine Translation

A salient feature of Neural Machine Translation (NMT) is the end-to-end nature of training employed, eschewing the need of separate components to model different linguistic phenomena. Rather, an NMT model learns to translate individual sentences from the labeled data itself. However, traditional NMT methods trained on large parallel corpora with a one-to-one sentence mapping make an implicit assumption of sentence independence. This makes it challenging for current NMT systems to model inter-sentential discourse phenomena. While recent research in this direction mainly leverages a single previous source sentence to model discourse, this paper proposes the incorporation of a context window spanning previous as well as next sentences as source-side context and previously generated output as target-side context, using an effective non-recurrent architecture based on self-attention. Experiments show improvement over non-contextual models as well as contextual methods using only previous context.

pdf bib
Multi-source transformer with combined losses for automatic post editing
Amirhossein Tebbifakhr | Ruchit Agrawal | Matteo Negri | Marco Turchi
Proceedings of the Third Conference on Machine Translation: Shared Task Papers

Recent approaches to the Automatic Post-editing (APE) of Machine Translation (MT) have shown that best results are obtained by neural multi-source models that correct the raw MT output by also considering information from the corresponding source sentence. To this aim, we present for the first time a neural multi-source APE model based on the Transformer architecture. Moreover, we employ sequence-level loss functions in order to avoid exposure bias during training and to be consistent with the automatic evaluation metrics used for the task. These are the main features of our submissions to the WMT 2018 APE shared task, where we participated both in the PBSMT subtask (i.e. the correction of MT outputs from a phrase-based system) and in the NMT subtask (i.e. the correction of neural outputs). In the first subtask, our system improves over the baseline up to -5.3 TER and +8.23 BLEU points ranking second out of 11 submitted runs. In the second one, characterized by the higher quality of the initial translations, we report lower but statistically significant gains (up to -0.38 TER and +0.8 BLEU), ranking first out of 10 submissions.


pdf bib
Three-phase training to address data sparsity in Neural Machine Translation
Ruchit Agrawal | Mihir Shekhar | Dipti Sharma
Proceedings of the 14th International Conference on Natural Language Processing (ICON-2017)

pdf bib
A vis-à-vis evaluation of MT paradigms for linguistically distant languages
Ruchit Agrawal | Jahfar Ali | Dipti Misra Sharma
Proceedings of the 14th International Conference on Natural Language Processing (ICON-2017)