Yan Xu

Yan Xu

AI Researcher at Tencent

Sitemap

A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.

Pages

Yan Xu

AI researcher working on reliable and reasoning-capable foundation models.

Posts

portfolio

publications

CAiRE_HKUST at SemEval-2019 Task 3: Hierarchical Attention for Dialogue Emotion Classification

Published in Proceedings of the 13th International Workshop on Semantic Evaluation in conjuction with NAACL, 2019

Recommended citation: Winata, G. I., Madotto, A., Lin, Z., Shin, J., Xu, Y., Xu, P., & Fung, P. (2019, June). CAiRE_HKUST at SemEval-2019 Task 3: Hierarchical Attention for Dialogue Emotion Classification. In Proceedings of the 13th International Workshop on Semantic Evaluation (pp. 142-147). https://arxiv.org/pdf/1810.12264.pdf

Learning to Learn Sales Prediction with Social Media Sentiment

Published in The First Workshop on Financial Technology and Natural Language Processing in conjunction with IJCAI, 2019

Recommended citation: Lin, Z., Madotto, A., Winata, G. I., Liu, Z., Xu, Y., Gao, C., & Fung, P. (2019, July). Learning to Learn Sales Prediction with Social Media Sentiment. In The First Workshop on Financial Technology and Natural Language Processing in conjunction with IJCAI 2019 (p. 47). https://www.aclweb.org/anthology/W19-55#page=57

Zero-shot Cross-lingual Dialogue Systems with Transferable Latent Variables

Published in EMNLP, 2019

Recommended citation: Liu, Z., Shin, J., Xu, Y., Winata, G. I., Xu, P., Madotto, A., & Fung, P. (2019, November). Zero-shot Cross-lingual Dialogue Systems with Transferable Latent Variables. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) (pp. 1297-1303). https://www.aclweb.org/anthology/D19-1129.pdf

CAiRE-COVID: A Question Answering and Query-focused Multi-Document Summarization System for COVID-19 Scholarly Information Management

Published in NLP-COVID Workshop in EMNLP-2020, 2020

Recommended citation: Su, D., Xu, Y., Yu, T., Siddique, F. B., Barezi, E., & Fung, P. (2020, December). CAiRE-COVID: A Question Answering and Query-focused Multi-Document Summarization System for COVID-19 Scholarly Information Management. In Proceedings of the 1st Workshop on NLP for COVID-19 (Part 2) at EMNLP 2020. https://openreview.net/forum?id=k8f2nsLqyTZ

Diverse and Faithful Knowledge-Grounded Dialogue Generation via Sequential Posterior Inference

Published in ICML 2023, 2023

Recommended citation: @InProceedings{pmlr-v202-xu23j, title = {Diverse and Faithful Knowledge-Grounded Dialogue Generation via Sequential Posterior Inference}, author = {Xu, Yan and Kong, Deqian and Xu, Dehong and Ji, Ziwei and Pang, Bo and Fung, Pascale and Wu, Ying Nian}, booktitle = {Proceedings of the 40th International Conference on Machine Learning}, pages = {38518--38534}, year = {2023}, editor = {Krause, Andreas and Brunskill, Emma and Cho, Kyunghyun and Engelhardt, Barbara and Sabato, Sivan and Scarlett, Jonathan}, volume = {202}, series = {Proceedings of Machine Learning Research}, month = {23--29 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v202/xu23j/xu23j.pdf}, url = {https://proceedings.mlr.press/v202/xu23j.html}, abstract = {The capability to generate responses with diversity and faithfulness using factual knowledge is paramount for creating a human-like, trustworthy dialogue system. Common strategies either adopt a two-step paradigm, which optimizes knowledge selection and response generation separately, and may overlook the inherent correlation between these two tasks, or leverage conditional variational method to jointly optimize knowledge selection and response generation by employing an inference network. In this paper, we present an end-to-end learning framework, termed Sequential Posterior Inference (SPI), capable of selecting knowledge and generating dialogues by approximately sampling from the posterior distribution. Unlike other methods, SPI does not require the inference network or assume a simple geometry of the posterior distribution. This straightforward and intuitive inference procedure of SPI directly queries the response generation model, allowing for accurate knowledge selection and generation of faithful responses. In addition to modeling contributions, our experimental results on two common dialogue datasets (Wizard of Wikipedia and Holl-E) demonstrate that SPI outperforms previous strong baselines according to both automatic and human evaluation metrics.} } https://proceedings.mlr.press/v202/xu23j/xu23j.pdf

talks

teaching

Teaching experience 1

Undergraduate course, University 1, Department, 2014

This is a description of a teaching experience. You can use markdown like any other post.

Teaching experience 2

Workshop, University 1, Department, 2015

This is a description of a teaching experience. You can use markdown like any other post.