Rui Xing

Hi, I am Rui Xing(邢瑞 in Chinese, a close pronunciation /reɪ, ʃɪŋ/ ).

Currently, I am a Ph.D. Candidate in The University of Melbourne NLP Group, happily working with Dr.Jey Han Lau and Prof. Tim Baldwin. Currently I am visiting MBZUAI NLP department, hosted by Prof. Preslav Nakov.

I have broad research interests in Natural Language Processing. Currently working on explainable fact checking, justification/explanation generation and affective information in the diffusion of misinformation.

Email:imDOT[LASTNAME][FIRSTNAME]GMAIL  /  LinkedIn  /  Twitter  /  Github

profile photo

What's new fun:)

2023-12-01     Thanks everyone for attending ALTA 2023!

2023-11-16     Please consider subscribing to our ALTA Youtube channel & Twitter!

2023-10-24     Poster talk at 2023 CIS Doctoral Colloquium, Melbourne University.

2023-04-21     The official ALTA 2023 website is launched!

2023-02-21     I passed my confirmation, officially a PhD Candidate!

2022-11-07     Got one paper accepted to ALTA 2022!

2022-07-07     Our team participated Qiskit Hackathon Melbourne 2022!

2022-05-04     Our team completed all challenges in the 2022 Unimelb Amazing Race!

2022-02-23     Officially start my PhD journey!

2020-11-18     Got one paper accepted to BMC Bioinformatics!

2019-09-16     Got one paper accepted to EMNLP-IJCNLP 2019 (WNUT Workshop)!

Selected Publications

Evaluating Evidence Attribution in Generated Fact Checking Explanations
Rui Xing, Timothy Baldwin and Jey Han Lau
In arxiv

Automated fact-checking systems often struggle with trustworthiness, as their generated explanations can include hallucinations. In this work, we explore evidence attribution for fact-checking explanation generation. We introduce a novel evaluation protocol, citation masking and recovery, to assess attribution quality in generated explanations. We implement our protocol using both human annotators and automatic annotators, and find that LLM annotation correlates with human annotation, suggesting that attribution assessment can be automated. Finally, our experiments reveal that: (1) the best-performing LLMs still generate explanations with inaccurate attributions; and (2) human-curated evidence is essential for generating better explanations. [paper / code]

Automatic Explanation Generation For Climate Science Claims
Rui Xing, Shraey Bhatia, Timothy Baldwin and Jey Han Lau
In Proceedings of The 20th Annual Workshop of the Australasian Language Technology Association (ALTA 2022)

Climate change is an existential threat to humanity, the proliferation of unsubstantiated claims relating to climate science is manipulating public perception, motivating the need for fact-checking in climate science. In this work, we draw on recent work that uses retrieval-augmented generation for veracity prediction and explanation generation, in framing explanation generation as a query-focused multi-document summarization task. [paper / code]

BioRel: towards large-scale biomedical relation extraction
Rui Xing and Jie Luo
BMC Bioinformatics. 2020 Dec 16;21(Suppl 16):543.

We construct BioRel, a large-scale dataset for biomedical relation extraction problem, by using Unified Medical Language System as knowledge base and Medline as corpus. [paper / data]

Distant Supervised Relation Extraction with Separate Head-Tail CNN
Rui Xing and Jie Luo
Proceedings of the EMNLP Workshop W-NUT: The 5th Workshop on Noisy User-generated Text (EMNLP 2019 W-NUT)

Distant supervised relation extraction is an efficient and effective strategy to find relations between entities in texts. However, it inevitably suffers from mislabeling problem and the noisy data will hinder the performance. In this paper, we propose the Separate Head-Tail Convolution Neural Network (SHTCNN), a novel neural relation extraction framework to alleviate this issue. [paper / code]

Selected Honors

2022: Melbourne Plus digital credential for community engagement, University of Melbourne
2022: ALTA Student Travelling Scholarship, Australasian Language Technology Association
2016: Honorable Mention in Mathematical Contest in Modeling, the Consortium for Mathematics and Its Application
2015, 2016: National Scholarship, Ministry of Education in China

Teaching

Tutor

2024: Undergraduate Research Internship Program (MBZUAI)
2023 Semester 1: Natural Language Processing COMP90042 (University of Melbourne)
2023 Semester 1: Statistical Machine Learning COMP90051 (University of Melbourne)
2022 Semester 2: Statistical Machine Learning COMP90051 (University of Melbourne)
2022 Semester 1: Natural Language Processing COMP90042 (University of Melbourne)

Service

2023-present: ALTA student representative
2024: reviewer, ACL 2024 Student Research Workshop
2022-2024: student organizer, University of Melbourne NLP Reading Group
2023: technology chair, ALTA 2023 Workshop
2023: reviewer, ACL 2023 Student Research Workshop, IJCNLP-AACL 2023 Student Research Workshop
2022, 2023: coordinator, Master of Computer Science Research Project Presentation (University of Melbourne)

Miscellaneous

Volunteer
Voluntary work provides me with a lot of valuable fun experiences. Here are some selected fun events I enjoyed.
Hobbies
I like swimming and table tennis. I also go hiking and cycling from time to time.
I am fond of playing, designing games and Pokemon is my favourite.

Copyright © 2024 Rui Xing


Template from here.