1

Language Relatedness and Lexical Closeness can help Improve Multilingual NMT: IITBombay@MultiIndicNMT WAT2021

Multilingual Neural Machine Translation hasachieved remarkable performance by traininga single translation model for multiple languages. This paper describes our submission(Team ID- CFILT-IITB) for the MultiIndicMT:An Indic Language Multilingual …

Disfluency Correction using Unsupervised and Semi-supervised Learning

Spoken language is different from the written language in its style and structure. Disfluencies that appear in transcriptions from speech recognition systems generally hamper the performance of downstream NLP tasks. Thus, a disfluency correction …

Load Balancing in Heterogeneous Distributed Systems Using Singleton Model

In this paper, we present an implementation to do load balancing in heterogeneous distributed systems using a singleton model by making use of simple technologies provided by Java Programming language. The ObjectOriented concepts in Java enable us to invoke any POJO containing the Business logic of an Application from the RMI Server program without editing the code.

Generating Fluent Translations from Disfluent Text Without Access to Fluent References: IIT Bombay@IWSLT2020

Using denoising auto-encoder and backtranslation, this work beats a baseline model by a margin of 4.21 and 3.11 BLEU points where the baseline uses disfluent and fluent references, respectively, without an access to disfluent-to-fluent parallel corpus.