no code implementations • 17 Apr 2024 • Xiangci Li, Jessica Ouyang
To convince readers of the novelty of their research paper, authors must perform a literature review and compose a coherent story that connects and relates prior works to the current work.
no code implementations • 6 Mar 2024 • Xiangci Li, Linfeng Song, Lifeng Jin, Haitao Mi, Jessica Ouyang, Dong Yu
In this paper, we present a high-quality benchmark named multi-source Wizard of Wikipedia (Ms. WoW) for evaluating multi-source dialogue knowledge selection and response generation.
no code implementations • 28 Feb 2024 • Biswadip Mandal, Xiangci Li, Jessica Ouyang
Abstractive citation text generation is usually framed as an infilling task, where a sequence-to-sequence model is trained to generate a citation given a reference paper and the context window around the target; the generated citation should be a brief discussion of the reference paper as it relates to the citing context.
no code implementations • 20 Feb 2024 • Xiangci Li, Jessica Ouyang
Due to the rapid pace of research publications, keeping up to date with all the latest related papers is very time-consuming, even with daily feed tools.
1 code implementation • 12 Sep 2023 • Xiangci Li, Yi-Hui Lee, Jessica Ouyang
Because manual CTS annotation is extremely time- and labor-intensive, we experiment with distant labeling of candidate CTS sentences, achieving sufficiently strong performance to substitute for expensive human annotations in model training, and we propose a human-in-the-loop, keyword-based CTS retrieval approach that makes generating citation texts grounded in the full text of cited papers both promising and practical.
1 code implementation • NAACL 2022 • Xiangci Li, Biswadip Mandal, Jessica Ouyang
As a first step toward a linguistically-motivated related work generation framework, we present a Citation Oriented Related Work Annotation (CORWA) dataset that labels different types of citation text fragments from different information sources.
no code implementations • 6 Jan 2022 • Xiangci Li, Jessica Ouyang
In this survey, we conduct a meta-study to compare the existing literature on related work generation from the perspectives of problem formulation, dataset collection, methodological approach, performance evaluation, and future prospects to provide the reader insight into the progress of the state-of-the-art studies, as well as and how future studies can be conducted.
no code implementations • 11 Oct 2021 • Kinjal Basu, Huaduo Wang, Nancy Dominguez, Xiangci Li, Fang Li, Sarat Chandra Varanasi, Gopal Gupta
We present the philosophy behind CASPR's design as well as details of its implementation.
1 code implementation • 28 Dec 2020 • Xiangci Li, Gully Burns, Nanyun Peng
Even for domain experts, it is a non-trivial task to verify a scientific claim by providing supporting or refuting evidence rationales.
1 code implementation • Findings of the Association for Computational Linguistics 2020 • Xiangci Li, Hairong Liu, Liang Huang
Existing natural language processing systems are vulnerable to noisy inputs resulting from misspellings.
1 code implementation • EACL 2021 • Xiangci Li, Gully Burns, Nanyun Peng
We apply richly contextualized deep representation learning pre-trained on biomedical domain corpus to the analysis of scientific discourse structures and the extraction of "evidence fragments" (i. e., the text in the results section describing data presented in a specified subfigure) from a set of biomedical experimental research articles.