38 citations · 206 across the 28 of their papers we have counts for
12 papers · 1 filter
EFIM: Efficient Serving of LLMs for Infilling Tasks with Improved KV Cache Reuse
Tianyu Guo, Hande Dong, Yichong Leng +4
Large language models (LLMs) are often used for infilling tasks, which involve predicting or generating missing information in a given text. These tasks typically require multiple…
Sentence-Level or Token-Level? A Comprehensive Study on Knowledge Distillation
Jingxuan Wei, Linzhuang Sun, Yichong Leng +3
Knowledge distillation, transferring knowledge from a teacher model to a student model, has emerged as a powerful technique in neural machine translation for compressing models or…
Extract and Attend: Improving Entity Translation in Neural Machine Translation
Zixin Zeng, Rui Wang, Yichong Leng +4
While Neural Machine Translation(NMT) has achieved great progress in recent years, it still suffers from inaccurate translation of entities (e.g., person/organization name, locatio…
SoftCorrect: Error Correction with Soft Detection for Automatic Speech Recognition
Yichong Leng, Xu Tan, Wenjie Liu +6
Error correction in automatic speech recognition (ASR) aims to correct those incorrect words in sentences generated by ASR models. Since recent ASR models usually have low word err…
Mask the Correct Tokens: An Embarrassingly Simple Approach for Error Correction
Kai Shen, Yichong Leng, Xu Tan +4
Text error correction aims to correct the errors in text sequences such as those typed by humans or generated by speech recognition models. Previous error correction methods usuall…
Transcormer: Transformer for Sentence Scoring with Sliding Language Modeling
Kaitao Song, Yichong Leng, Xu Tan +3
Sentence scoring aims at measuring the likelihood score of a sentence and is widely used in many natural language processing scenarios, like reranking, which is to select the best…
FastCorrect 2: Fast Error Correction on Multiple Candidates for Automatic Speech Recognition
Yichong Leng, Xu Tan, Rui Wang +8
Error correction is widely used in automatic speech recognition (ASR) to post-process the generated sentence, and can further reduce the word error rate (WER). Although multiple ca…
Analyzing and Mitigating Interference in Neural Architecture Search
Jin Xu, Xu Tan, Kaitao Song +5
Weight sharing is a popular approach to reduce the cost of neural architecture search (NAS) by reusing the weights of shared operators from previously trained child models. However…
FastCorrect: Fast Error Correction with Edit Alignment for Automatic Speech Recognition
Yichong Leng, Xu Tan, Linchen Zhu +7
Error correction techniques have been used to refine the output sentences from automatic speech recognition (ASR) models and achieve a lower word error rate (WER) than original ASR…
A Study of Multilingual Neural Machine Translation
Xu Tan, Yichong Leng, Jiale Chen +3
Multilingual neural machine translation (NMT) has recently been investigated from different aspects (e.g., pivot translation, zero-shot translation, fine-tuning, or training from s…
Microsoft Research Asia's Systems for WMT19
Yingce Xia, Xu Tan, Fei Tian +11
We Microsoft Research Asia made submissions to 11 language directions in the WMT19 news translation tasks. We won the first place for 8 of the 11 directions and the second place fo…
Unsupervised Pivot Translation for Distant Languages
Yichong Leng, Xu Tan, Tao Qin +2
Unsupervised neural machine translation (NMT) has attracted a lot of attention recently. While state-of-the-art methods for unsupervised translation usually perform well between si…