• Publications
  • Influence
Multilingual Unsupervised NMT using Shared Encoder and Language-Specific Decoders
TLDR
A multilingual unsupervised NMT scheme which jointly trains multiple languages with a shared encoder and multiple decoders based on denoising autoencoding of each language and back-translating between English and multiple non-English languages, which results in a universal encoder which can encode any language participating in training into an inter-lingual representation, and language-specific decoder. Expand
IITP-MT at WAT2018: Transformer-based Multilingual Indic-English Neural Machine Translation System
TLDR
This paper describes the systems submitted by the IITP-MT team to WAT 2018 multilingual Indic languages shared task and evaluates the models using BLEU score and finds that a single multilingual NMT model performs better than separate bilingual models when the target is English. Expand
Solving Data Sparsity for Aspect Based Sentiment Analysis Using Cross-Linguality and Multi-Linguality
TLDR
This work trains and evaluates Long Short Term Memory (LSTM) based architecture for aspect level sentiment classification and shows the efficacy of the proposed model against state-of-the-art methods in two experimental setups i.e. multi-lingual and cross-lingUAL. Expand
Improving Word Embedding Coverage in Less-Resourced Languages Through Multi-Linguality and Cross-Linguality
TLDR
This work proposes an effective method to improve the word embedding coverage in less-resourced languages by leveraging bilingual word embeddings learned from different corpora and shows the effectiveness of the proposed approach for two aspect-level sentiment analysis tasks. Expand
Parallel Corpus Filtering Based on Fuzzy String Matching
TLDR
The IIT Patna’s submission to WMT 2019 shared task on parallel corpus filtering is described and the scoring method obtains 2nd position in the team ranking for 1-million NepaliEnglish NMT and 5-million Sinhala- English NMT categories. Expand
IITP-MT System for Gujarati-English News Translation Task at WMT 2019
TLDR
It is observed that incorporating monolingual data through back-translation improves the BLEU score significantly over baseline NMT and SMT systems for this language pair. Expand
IITP English-Hindi Machine Translation System at WAT 2016
TLDR
A system based on hierarchical phrase-based SMT for English to Hindi language pair is developed and re-ordering and augment bilingual dictionary is performed to improve the performance. Expand
Neural machine translation of low-resource languages using SMT phrase pair injection
TLDR
This paper proposes an effective approach to improve an NMT system in low-resource scenario without using any additional data, based on the gated recurrent unit (GRU) and transformer networks, and finds that the proposed method outperforms SMT—which is known to work better than the neural models in high-resource scenarios—for some translation directions. Expand
Can SMT and RBMT Improve each other’s Performance?- An Experiment with English-Hindi Translation
TLDR
This paper proposes an effective method of serial coupling where it attempts to build a hybrid model that exploits the benefits of both the architectures of RBMT and SMT, and shows the effectiveness with improvement in BLEU score. Expand
Temporality as seen through translation:a case study on Hindi texts
TLDR
It is found that the task of manual temporal annotation becomes difficult in the translated texts while the automatic temporal processing system manages to correctly capture temporal information from the translations. Expand
...
1
2
...