1 code implementation • 22 May 2023 • Jianfeng He, Julian Salazar, Kaisheng Yao, Haoqi Li, Jinglun Cai
End-to-end (E2E) spoken language understanding (SLU) is constrained by the cost of collecting speech-semantics pairs, especially when label domains change.
Natural Language Understanding Spoken Language Understanding
no code implementations • 11 May 2023 • Jinglun Cai, Monica Sunkara, Xilai Li, Anshu Bhatia, Xiao Pan, Sravan Bodapati
Masked Language Models (MLMs) have proven to be effective for second-pass rescoring in Automatic Speech Recognition (ASR) systems.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +4
no code implementations • 5 May 2023 • Nilaksh Das, Monica Sunkara, Sravan Bodapati, Jinglun Cai, Devang Kulshreshtha, Jeff Farris, Katrin Kirchhoff
Internal language model estimation (ILME) has been proposed to mitigate this bias for autoregressive models such as attention-based encoder-decoder and RNN-T.
no code implementations • 21 Feb 2023 • Jinglun Cai, Mingda Li, Ziyan Jiang, Eunah Cho, Zheng Chen, Yang Liu, Xing Fan, Chenlei Guo
Query Rewriting (QR) plays a critical role in large-scale dialogue systems for reducing frictions.
no code implementations • Findings (NAACL) 2022 • Yujie Xing, Jinglun Cai, Nils Barlaug, Peng Liu, Jon Atle Gulla
Furthermore, we propose Domain-specific Frequency (DF), a novel word-level importance weight that measures the relative importance of a word for a specific corpus compared to other corpora.