Search Results for author: Neha Verma

Found 6 papers, 3 papers with code

Strategies for Adapting Multilingual Pre-training for Domain-Specific Machine Translation

no code implementations AMTA 2022 Neha Verma, Kenton Murray, Kevin Duh

Therefore, in this work, we propose two major fine-tuning strategies: our language-first approach first learns the translation language pair via general bitext, followed by the domain via in-domain bitext, and our domain-first approach first learns the domain via multilingual in-domain bitext, followed by the language pair via language pair-specific in-domain bitext.

Domain Adaptation Machine Translation +1

IsoVec: Controlling the Relative Isomorphism of Word Embedding Spaces

1 code implementation11 Oct 2022 Kelly Marchisio, Neha Verma, Kevin Duh, Philipp Koehn

The ability to extract high-quality translation dictionaries from monolingual word embedding spaces depends critically on the geometric similarity of the spaces -- their degree of "isomorphism."

Bilingual Lexicon Induction Translation

FeTaQA: Free-form Table Question Answering

1 code implementation1 Apr 2021 Linyong Nan, Chiachun Hsieh, Ziming Mao, Xi Victoria Lin, Neha Verma, Rui Zhang, Wojciech Kryściński, Nick Schoelkopf, Riley Kong, Xiangru Tang, Murori Mutuma, Ben Rosand, Isabel Trindade, Renusree Bandaru, Jacob Cunningham, Caiming Xiong, Dragomir Radev

Existing table question answering datasets contain abundant factual questions that primarily evaluate the query and schema comprehension capability of a system, but they fail to include questions that require complex reasoning and integration of information due to the constraint of the associated short-form answers.

Question Answering Retrieval +2

Cannot find the paper you are looking for? You can Submit a new open access paper.