Yan Wang

Yan Wang

Auto-generated profile, based on publicly available information

Yan Wang

Bi are with Tencent AI Lab Tsinghua-Berkeley Shenzhen Institute Tsinghua University Shenzhen Shenzhen China China

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
7 February 2022 in IEEE Transactions on Games
Verified
Journal Article
Closed access
ZYZelong Yang
Zelong Yang
ZPZhufeng Pan
Zhufeng Pan
YWYan Wang
Yan Wang
DCDeng Cai
Deng Cai
SSShuming Shi
Shuming Shi
XLXiaojiang Liu
Xiaojiang Liu
With the rapid prevalence and explosive development of MOBA esports (Multiplayer Online Battle Arena electronic sports), much research effort has been devoted to automatically predicting game results (win predictions). While this task has great potential in various applications, such as esports live streaming and game commentator AI systems, previous studies fail to investigate the methods to interpret these win predictions. To mitigate this issue, we collected a large-scale dataset that contains real-time game records with rich input features of the popular MOBA game Honor of Kings. For interpretable predictions, we proposed a Two-Stage Spatial-Temporal Network (TSSTN) that can not only provide accurate real-time win predictions but also attribute the ultimate prediction results to the contributions of different features for interpretability. Experiment results and applications in real-world live streaming scenarios showed that the proposed TSSTN model is effective both in prediction accuracy and interpretability.

22 January 2024 in ACM Transactions on Information Systems
Verified
Journal Article
Open access
TLTian Lan
Tian Lan
DCDeng Cai
Deng Cai
YWYan Wang
Yan Wang
YSYixuan Su
Yixuan Su
HHHeyan Huang
Heyan Huang
XMXian-Ling Mao
Xian-Ling Mao
Recent progress in deep learning has continuously improved the accuracy of dialogue response selection. However, in real-world scenarios, the high computation cost forces existing dialogue response selection models to rank only a small number of candidates, recalled by a coarse-grained model, precluding many high-quality candidates. To overcome this problem, we present a novel and efficient response selection model and a set of tailor-designed learning strategies to train it effectively. The proposed model consists of a dense retrieval module and an interaction layer, which could directly select the proper response from a large corpus. We conduct re-rank and full-rank evaluations on widely used benchmarks to evaluate our proposed model. Extensive experimental results demonstrate that our proposed model notably outperforms the state-of-the-art baselines on both re-rank and full-rank evaluations. Moreover, human evaluation results show that the response quality could be improved further by enlarging the candidate pool with nonparallel corpora. In addition, we also release high-quality benchmarks that are carefully annotated for more accurate dialogue response selection evaluation. All source codes, datasets, model parameters, and other related resources have been publicly available. 1

13 February 2022 in arXiv
Verified
Preprint
Open access
PDF file
HLHuayang Li
Huayang Li
YSYixuan Su
Yixuan Su
DCDeng Cai
Deng Cai
YWYan Wang
Yan Wang
LLLemao Liu
Lemao Liu
Recently, retrieval-augmented text generation attracted increasing attention of the computational linguistics community. Compared with conventional generation models, retrieval-augmented text generation has remarkable advantages and particularly has achieved state-of-the-art performance in many NLP tasks. This paper aims to conduct a survey about retrieval-augmented text generation. It firstly highlights the generic paradigm of retrieval-augmented generation, and then it reviews notable approaches according to different tasks including dialogue response generation, machine translation, and other generation tasks. Finally, it points out some important directions on top of recent methods to facilitate future research.

16 March 2022 in IEEE Transactions on Games
Verified
Journal Article
Closed access
ZYZelong Yang
Zelong Yang
YWYan Wang
Yan Wang
PLPiji Li
Piji Li
SLShaobin Lin
Shaobin Lin
SSShuming Shi
Shuming Shi
WBWei Bi
Wei Bi
The multiplayer online battle arena (MOBA) games have become increasingly popular in recent years. Consequently, many efforts have been devoted to providing pre-game or in-game predictions for them. These predictions can be used in many MOBA esports related applications, such as AI commentator systems, in-game data analysis, and game-assistant bots. However, these works are limited in the following two aspects: 1) the lack of sufficient in-game features; 2) the absence of interpretability in the prediction results. These two limitations greatly restrict the practical performance and industrial application of the current works. In this work, we collect a large-scale dataset containing rich in-game features for the popular MOBA game Honor of Kings. We then propose to predict four types of prediction tasks in an interpretable way by attributing the predictions to the input features using two gradient-based attribution methods: Integrated Gradients and SmoothGrad. To evaluate the explanatory power of different models and attribution methods, a fidelity-based evaluation metric is further proposed. Finally, we evaluate the accuracy and Fidelity of several competitive methods to assess how well machines predict events in MOBA games.

28 February 2020 in arXiv
Verified
Preprint
Open access
PDF file
DCDeng Cai
Deng Cai
YWYan Wang
Yan Wang
VBVictoria Bi
Victoria Bi
Zhaopeng TuZhaopeng Tu
Zhaopeng Tu
XLXiaojiang Liu
Xiaojiang Liu
SSShuming Shi
Shuming Shi
For dialogue response generation, traditional generative models generate responses solely from input queries. Such models rely on insufficient information for generating a specific response since a certain query could be answered in multiple ways. Consequentially, those models tend to output generic and dull responses, impeding the generation of informative utterances. Recently, researchers have attempted to fill the information gap by exploiting information retrieval techniques. When generating a response for a current query, similar dialogues retrieved from the entire training data are considered as an additional knowledge source. While this may harvest massive information, the generative models could be overwhelmed, leading to undesirable performance. In this paper, we propose a new framework which exploits retrieval results via a skeleton-then-response paradigm. At first, a skeleton is generated by revising the retrieved responses. Then, a novel generative model uses both the generated skeleton and the original query for response generation. Experimental results show that our approaches significantly improve the diversity and informativeness of the generated responses.

16 April 2021 in arXiv
Verified
Preprint
Open access
PDF file
ZYZelong Yang
Zelong Yang
ZPZhufeng Pan
Zhufeng Pan
YWYan Wang
Yan Wang
DCDeng Cai
Deng Cai
XLXiaojiang Liu
Xiaojiang Liu
SHShao-Lun Huang
Shao-Lun Huang
With the rapid prevalence and explosive development of MOBA esports (Multiplayer Online Battle Arena electronic sports), much research effort has been devoted to automatically predicting game results (win predictions). While this task has great potential in various applications, such as esports live streaming and game commentator AI systems, previous studies fail to investigate the methods to interpret these win predictions. To mitigate this issue, we collected a large-scale dataset that contains real-time game records with rich input features of the popular MOBA game Honor of Kings. For interpretable predictions, we proposed a Two-Stage Spatial-Temporal Network (TSSTN) that can not only provide accurate real-time win predictions but also attribute the ultimate prediction results to the contributions of different features for interpretability. Experiment results and applications in real-world live streaming scenarios showed that the proposed TSSTN model is effective both in prediction accuracy and interpretability.