Wei Luo


2021

pdf bib
Mutual-Learning Improves End-to-End Speech Translation
Jiawei Zhao | Wei Luo | Boxing Chen | Andrew Gilman
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

A currently popular research area in end-to-end speech translation is the use of knowledge distillation from a machine translation (MT) task to improve the speech translation (ST) task. However, such scenario obviously only allows one way transfer, which is limited by the performance of the teacher model. Therefore, We hypothesis that the knowledge distillation-based approaches are sub-optimal. In this paper, we propose an alternative–a trainable mutual-learning scenario, where the MT and the ST models are collaboratively trained and are considered as peers, rather than teacher/student. This allows us to improve the performance of end-to-end ST more effectively than with a teacher-student paradigm. As a side benefit, performance of the MT model also improves. Experimental results show that in our mutual-learning scenario, models can effectively utilise the auxiliary information from peer models and achieve compelling results on Must-C dataset.

2018

pdf bib
IRCMS at SemEval-2018 Task 7 : Evaluating a basic CNN Method and Traditional Pipeline Method for Relation Classification
Zhongbo Yin | Zhunchen Luo | Wei Luo | Mao Bin | Changhai Tian | Yuming Ye | Shuai Wu
Proceedings of the 12th International Workshop on Semantic Evaluation

This paper presents our participation for sub-task1 (1.1 and 1.2) in SemEval 2018 task 7: Semantic Relation Extraction and Classification in Scientific Papers (Gábor et al., 2018). We experimented on this task with two methods: CNN method and traditional pipeline method. We use the context between two entities (included) as input information for both methods, which extremely reduce the noise effect. For the CNN method, we construct a simple convolution neural network to automatically learn features from raw texts without any manual processing. Moreover, we use the softmax function to classify the entity pair into a specific relation category. For the traditional pipeline method, we use the Hackabout method as a representation which is described in section3.5. The CNN method’s result is much better than traditional pipeline method (49.1% vs. 42.3% and 71.1% vs. 54.6% ).

2016

pdf bib
Speculation and Negation Scope Detection via Convolutional Neural Networks
Zhong Qian | Peifeng Li | Qiaoming Zhu | Guodong Zhou | Zhunchen Luo | Wei Luo
Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing

2010

pdf bib
The ICT statistical machine translation system for IWSLT 2010
Hao Xiong | Jun Xie | Hui Yu | Kai Liu | Wei Luo | Haitao Mi | Yang Liu | Yajuan Lü | Qun Liu
Proceedings of the 7th International Workshop on Spoken Language Translation: Evaluation Campaign

2002

pdf bib
Medstract: creating large-scale information servers from biomedical texts
James Pustejovsky | José Castaño | Roser Saurí | Jason Zhang | Wei Luo
Proceedings of the ACL-02 Workshop on Natural Language Processing in the Biomedical Domain