no code implementations • 11 Oct 2021 • Suyoun Kim, Duc Le, Weiyi Zheng, Tarun Singh, Abhinav Arora, Xiaoyu Zhai, Christian Fuegen, Ozlem Kalinli, Michael L. Seltzer
Measuring automatic speech recognition (ASR) system quality is critical for creating user-satisfying voice-driven applications.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +3
no code implementations • Findings (EMNLP) 2021 • Akshat Shrivastava, Pierce Chuang, Arun Babu, Shrey Desai, Abhinav Arora, Alexander Zotov, Ahmed Aly
An effective recipe for building seq2seq, non-autoregressive, task-oriented parsers to map utterances to semantic frames proceeds in three steps: encoding an utterance $x$, predicting a frame's length |y|, and decoding a |y|-sized frame with utterance and ontology tokens.
no code implementations • 5 Apr 2021 • Suyoun Kim, Abhinav Arora, Duc Le, Ching-Feng Yeh, Christian Fuegen, Ozlem Kalinli, Michael L. Seltzer
We define SemDist as the distance between a reference and hypothesis pair in a sentence-level embedding space.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +14
no code implementations • EACL 2021 • Arash Einolghozati, Abhinav Arora, Lorena Sainz-Maza Lecanda, Anuj Kumar, Sonal Gupta
Being able to parse code-switched (CS) utterances, such as Spanish+English or Hindi+English, is essential to democratize task-oriented semantic parsing systems for certain locales.
no code implementations • EACL 2021 • Haoran Li, Abhinav Arora, Shuohui Chen, Anchit Gupta, Sonal Gupta, Yashar Mehdad
Scaling semantic parsing models for task-oriented dialog systems to new languages is often expensive and time-consuming due to the lack of available datasets.
1 code implementation • 30 Dec 2019 • Varun Gangal, Abhinav Arora, Arash Einolghozati, Sonal Gupta
We are hitherto the first to investigate the use of generative classifiers for OOD detection at test-time.
2 code implementations • 12 Dec 2018 • Ahmed Aly, Kushal Lakhotia, Shicong Zhao, Mrinal Mohit, Barlas Oguz, Abhinav Arora, Sonal Gupta, Christopher Dewan, Stef Nelson-Lindall, Rushin Shah
We introduce PyText - a deep learning based NLP modeling framework built on PyTorch.