no code implementations • 7 Sep 2023 • Xiaocheng Yang, Yik-Cheung Tam
Consequently, we employ chain-of-thought to fine-tune LLaMA7B as a baseline model and develop other fine-tuned LLaMA7B models for the generation of Prolog code, Prolog code + chain-of-thought, and chain-of-thought + Prolog code, respectively.
1 code implementation • 8 Nov 2022 • Yik-Cheung Tam, Jiacheng Xu, Jiakai Zou, Zecheng Wang, Tinglong Liao, Shuhan Yuan
Knowledge cluster classification is boosted from 0. 7924 to 0. 9333 in Recall@1.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +4
1 code implementation • 6 Nov 2022 • Zecheng Wang, Yik-Cheung Tam
SUREALM employs an embedding retriever to search for training sentences in a data store that share similar word history during sequence generation.
1 code implementation • 7 Dec 2021 • Yichen Huang, Yuchen Wang, Yik-Cheung Tam
Our model ranks second in the official evaluation on the object coreference resolution task with an F1 score of 73. 3% after model ensembling.
no code implementations • 25 Aug 2021 • Yuhao Ding, Yik-Cheung Tam
In multi-domain task-oriented dialog system, user utterances and system responses may mention multiple named entities and attributes values.
1 code implementation • 11 Mar 2020 • Changyu Miao, Zhen Cao, Yik-Cheung Tam
Deep Semantic Matching is a crucial component in various natural language processing applications such as question and answering (QA), where an input query is compared to each candidate question in a QA corpus in terms of relevance.
1 code implementation • ACL 2019 • Zhi-Qiang Liu, Zuohui Fu, Jie Cao, Gerard de Melo, Yik-Cheung Tam, Cheng Niu, Jie zhou
Rhetoric is a vital element in modern poetry, and plays an essential role in improving its aesthetics.
no code implementations • NAACL 2018 • Haohui Deng, Yik-Cheung Tam
GA Reader makes two assumptions: (1) a uni-directional attention that uses an input query to gate token encodings of a document; (2) encoding at the cloze position of an input query is considered for answer prediction.
no code implementations • NeurIPS 2008 • Yik-Cheung Tam, Tanja Schultz
We propose using correlated bigram LSA for unsupervised LM adaptation for automatic speech recognition.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2