Interactive Post-Editing for Verbosity Controlled Translation

no code implementations • COLING 2022 • Prabhakar Gupta, Anil Nelakanti, Grant M. Berry, Abhishek Sharma

We explore Interactive Post-Editing (IPE) models for human-in-loop translation to help correct translation errors and rephrase it with a desired style variation.

Machine Translation Translation

Adapting Neural Machine Translation for Automatic Post-Editing

no code implementations • WMT (EMNLP) 2021 • Abhishek Sharma, Prabhakar Gupta, Anil Nelakanti

Automatic post-editing (APE) models are usedto correct machine translation (MT) system outputs by learning from human post-editing patterns.

Automatic Post-Editing Translation

Detecting over/under-translation errors for determining adequacy in human translations

no code implementations • 1 Apr 2021 • Prabhakar Gupta, Ridha Juneja, Anil Nelakanti, Tamojit Chatterjee

We present a novel approach to detecting over and under translations (OT/UT) as part of adequacy error checks in translation evaluation.

Language Modelling Machine Translation +1

DeepSubQE: Quality estimation for subtitle translations

no code implementations • 22 Apr 2020 • Prabhakar Gupta, Anil Nelakanti

Quality estimation (QE) for tasks involving language data is hard owing to numerous aspects of natural language like variations in paraphrasing, style, grammar, etc.

Data Augmentation Translation

A context sensitive real-time Spell Checker with language adaptability

2 code implementations • 23 Oct 2019 • Prabhakar Gupta

We show that our system can be extended to new languages with minimal language-specific processing.

Problems with automating translation of movie/TV show subtitles

no code implementations • 4 Sep 2019 • Prabhakar Gupta, Mayank Sharma, Kartik Pitale, Keshav Kumar

We present 27 problems encountered in automating the translation of movie/TV show subtitles.

Machine Translation Translation