Yan Xu

I am Yan (Yana) Xu (徐妍). I received Bachelor Degree from Xi’an Jiaotong University. Currently, I am a Ph.D. candidate at Department of Electronic and Computer Engineering, The Hong Kong University of Science and Technology and Center of AI Research, supervised by Prof. Pascale Fung. My current research interests are Conversational AI and knowledge grounding. I also serve as the Program Committee and Reviewer in top conferences and workshops. Please feel free to contact me via email!

News

Two papers got accepted in EMNLP 2023: Contrastive Learning for Inductive Reasoning in Dialogue and Towards Mitigating LLM Hallucination via Self Reflection. The camera-ready versions are coming soon!
I finished my thesis defense in Sep. 2023. My thesis entitled Unstructured Knowledge Grounding for Open-domain Dialogues and the corresponding slides are available online!
Two papers got accepted in AACL 2023: PICK and ChatGPT Evaluation.
Paper Diverse and Faithful Knowledge-Grounded Dialogue Generation via Sequential Posterior Inference collaborating with Deqian Kong and Prof. Ying Nian Wu got accepted in ICML 2023!
Two papers got accepted in ACL 2023, including my paper during my internship in Amazon Alexa AI – KILM: Knowledge Injection into Encoder-Decoder Language Models.
Paper Retrieval-Free Knowledge-Grounded Dialogue Response Generation with Adapters got accepted and the Best Student Paper Award in in DialDoc Workshop in ACL 2022!
Paper Can Question Rewriting Help Conversational Question Answering? got accepted in Insights Workshop in ACL 2022.
One paper got accepted in Student Research Workshop in ACL 2022.
Got third place in subtask 2 of DialDoc 21 shared task in ACL 2021.
One paper got accepted in AAAI 2021.
Two papers got accepted in Findings of EMNLP 2020.
Paper “CAiRE-COVID: A Question Answering and Query-focused Multi-Document Summarization System for COVID-19 Scholarly Information Management” got accapted in NLP-COVID Workshop in EMNLP 2020.
Winner of the task “What has been published about information sharing and inter-sectoral collaboration?” of Kaggle COVID-19 Open Research Dataset Challenge (CORD-19).

Publications

2022

Retrieval-Free Knowledge-Grounded Dialogue Response Generation with Adapters

Yan Xu *, Etsuko Ishii*, , Zihan Liu, Genta Indra Winata, Dan Su, Andrea Madotto, Pascale Fung

DialDoc Workshop in ACL 2022 2022

[PAPER] [CODE]

Best Student Paper

Can Question Rewriting Help Conversational Question Answering?

Etsuko Ishii*, Yan Xu *, Samuel Cahyawijaya*, Bryan Wilie

Insights Workshop in ACL 2022 2022

[PAPER] [CODE]

CAiRE in DialDoc21: Data Augmentation for Information-SeekingDialogue System

Yan Xu *, Etsuko Ishii*, Genta Indra Winata, Zhaojiang Lin, Andrea Madotto, Zihan Liu, Peng Xu and Pascale Fung

Proceedings of the 1st International Workshop on Document-grounded Dialogue and Conversational QA in conjuction with ACL 2021

[PAPER] [CODE]

Third Place in the Shared Task

2020

CrossNER: Evaluating Cross-Domain Named Entity Recognition

Zihan Liu, Yan Xu , Tiezheng Yu, Wenliang Dai, Ziwei Ji, Samuel Cahyawijaya, Andrea Madotto, Pascale Fung

AAAI-2021 2020

[PAPER] [CODE]

Multi-hop Question Generation with Graph Convolutional Network

Dan Su, Yan Xu , Wenliang Dai, Ziwei Ji, Tiezheng Yu, Pascale Fung

Findings of EMNLP-2020 2020

[PAPER] [CODE]

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

Dan Su, Yan Xu ,Tiezheng Yu,Farhad Bin Siddique,Elham J. Barezi,Pascale Fung

NLP-COVID Workshop in EMNLP-2020 2020

[PAPER] [CODE]

Learning Knowledge Bases with Parameters for Task-Oriented Dialogue Systems

Andrea Madotto, Samuel Cahyawijaya, Genta Indra Winata, Yan Xu , Zihan Liu, Zhaojiang Lin, Pascale Fung

Findings of EMNLP-2020 2020

[PAPER] [CODE]

2019

Generalizing Question Answering System with Pre-trained Language Model Fine-tuning

Dan Su*, Yan Xu *, Genta Indra Winata, Peng Xu, Hyeondey Kim, Zihan Liu and Pascale Fung

EMNLP 2019

[PAPER] [CODE]

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

Zihan Liu, Jamin Shin, Yan Xu , Genta Indra Winata, Peng Xu, Andrea Madotto and Pascale Fung

EMNLP 2019

[PAPER] [CODE]

Incorporating Word and Subword Units in Unsupervised Machine Translation Using Language Model Rescoring

Zihan Liu*, Yan Xu *, Genta Indra Winata, Pascale Fung

Proceedings of the Fourth Conference on Machine Translation (WMT-2019) in conjunction with ACL 2019

[PAPER]

Learning to Learn Sales Prediction with Social Media Sentiment

Zhaojiang Lin, Andrea Madotto, Genta Indra Winata, Zihan Liu, Yan Xu , Cong Gao, Pascale Fung

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

[PAPER] [SLIDES]

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

Genta Indra Winata, Andrea Madotto, Zhaojiang Lin, Jamin Shin, Yan Xu , Peng Xu, Pascale Fung

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

[PAPER] [CODE]

Top 4 out of 160 teams

Awards

Third Place in DialDoc21 Shared Task, ACL 2021
Winner of Task 10 in Kaggle CORD-19 Challenge, Kaggle Competition
Fourth Place in MRQA-2019 Shared Task, EMNLP 2019
First Place in Chatbot Millionare Challenge, HKSTP 2019
Top Four out of 160 teams in SemEval-2019 Task 3, NAACL 2019
National Scholarship (Top 2%), 2014 - 2016

Service and leadership

Reviewer: ACL 2023, NLPCC 2023, EMNLP 2022, ACL 2022, ACL 2021, NLPCC 2021