1 code implementation • NAACL (ACL) 2022 • Xinya Du, Zixuan Zhang, Sha Li, Pengfei Yu, Hongwei Wang, Tuan Lai, Xudong Lin, Ziqi Wang, Iris Liu, Ben Zhou, Haoyang Wen, Manling Li, Darryl Hannan, Jie Lei, Hyounghun Kim, Rotem Dror, Haoyu Wang, Michael Regan, Qi Zeng, Qing Lyu, Charles Yu, Carl Edwards, Xiaomeng Jin, Yizhu Jiao, Ghazaleh Kazeminejad, Zhenhailong Wang, Chris Callison-Burch, Mohit Bansal, Carl Vondrick, Jiawei Han, Dan Roth, Shih-Fu Chang, Martha Palmer, Heng Ji
We introduce RESIN-11, a new schema-guided event extraction&prediction framework that can be applied to a large variety of newsworthy scenarios.
1 code implementation • 7 Apr 2024 • Liqiang Jing, Xinya Du
To handle these limitations, we propose an innovative method to align modalities in LVLMs through Fine-Grained Artificial Intelligence Feedback (FGAIF), which mainly consists of three steps: AI-based Feedback Collection, Fine-grained Reward Model Training, and Reinforcement Learning with Fine-grained Reward.
1 code implementation • 7 Nov 2023 • Ruosen Li, Xinya Du
Neural models, including large language models (LLMs), achieve superior performance on multi-hop question-answering.
1 code implementation • 2 Nov 2023 • Liqiang Jing, Ruosen Li, Yunmo Chen, Mengzhao Jia, Xinya Du
We introduce FAITHSCORE (Faithfulness to Atomic Image Facts Score), a reference-free and fine-grained evaluation metric that measures the faithfulness of the generated free-form answers from large vision-language models (LVLMs).
1 code implementation • 24 Oct 2023 • Chenkai Ma, Xinya Du
Language models (LMs) are capable of conducting in-context learning for multiple choice reasoning tasks, but the options in these tasks are treated equally.
1 code implementation • 23 Oct 2023 • Barry Wang, Xinya Du, Claire Cardie
This work is the first to apply the probing paradigm to representations learned for document-level information extraction (IE).
1 code implementation • 10 Sep 2023 • Son Quoc Tran, Gia-Huy Do, Phong Nguyen-Thuan Do, Matt Kretchmar, Xinya Du
In this paper, we demonstrate the usefulness of this AGent pipeline by creating two sets of unanswerable questions from answerable questions in SQuAD and HotpotQA.
1 code implementation • 6 Sep 2023 • Zonglin Yang, Xinya Du, Junxian Li, Jie Zheng, Soujanya Poria, Erik Cambria
Hypothetical induction is recognized as the main reasoning type when scientists make observations about the world and try to propose hypotheses to explain those observations.
1 code implementation • 6 Jul 2023 • Jishnu Jaykumar P, Kamalesh Palanisamy, Yu-Wei Chao, Xinya Du, Yu Xiang
The two encoders are used to compute prototypes of image classes for classification.
no code implementations • 6 Jul 2023 • Ruosen Li, Teerth Patel, Xinya Du
Specifically, we propose the (1) peer rank (PR) algorithm that takes into account each peer LLM's pairwise preferences of all answer pairs, and outputs a final ranking of models; and (2) peer discussion (PD), where we prompt two LLMs to discuss and try to reach a mutual agreement on preferences of two answers.
1 code implementation • 22 May 2023 • Chi Han, Qizheng He, Charles Yu, Xinya Du, Hanghang Tong, Heng Ji
A LERP is designed as a vector of probabilistic logical functions on the entity's neighboring sub-graph.
Ranked #9 on Link Prediction on WN18RR
1 code implementation • 21 Mar 2023 • Zonglin Yang, Xinya Du, Rui Mao, Jinjie Ni, Erik Cambria
This paper provides a comprehensive overview on a new paradigm of logical reasoning, which uses natural language as knowledge representation and pretrained language models as reasoners, including philosophical definition and categorization of logical reasoning, advantages of the new paradigm, benchmarks and methods, challenges of the new paradigm, possible future directions, and relation to related NLP fields.
1 code implementation • 21 Dec 2022 • Zonglin Yang, Li Dong, Xinya Du, Hao Cheng, Erik Cambria, Xiaodong Liu, Jianfeng Gao, Furu Wei
To this end, we propose a new paradigm (task) for inductive reasoning, which is to induce natural language rules from natural language facts, and create a dataset termed DEER containing 1. 2k rule-fact pairs for the task, where rules and facts are written in natural language.
1 code implementation • 14 Nov 2022 • Xinya Du, Heng Ji
We propose a retrieval-augmented generative QA model (R-GQA) for event argument extraction.
1 code implementation • 7 Nov 2022 • Chi Han, Hengzhi Pei, Xinya Du, Heng Ji
To this end, we propose the framework CLORE (Classification by LOgical Reasoning on Explanations).
1 code implementation • ACL 2022 • Xinya Du, Sha Li, Heng Ji
Extracting informative arguments of events from news articles is a challenging problem in information extraction, which requires a global contextual understanding of each document.
1 code implementation • ACL 2022 • Aliva Das, Xinya Du, Barry Wang, Kejian Shi, Jiayuan Gu, Thomas Porter, Claire Cardie
Document-level information extraction (IE) tasks have recently begun to be revisited in earnest using the end-to-end neural network techniques that have been successful on their sentence-level IE counterparts.
no code implementations • ACL 2021 • Xinya Du, Luheng He, Qi Li, Dian Yu, Panupong Pasupat, Yuan Zhang
To address this problem, we introduce QA-driven slot filling (QASF), which extracts slot-filler spans from utterances with a span-based QA model.
1 code implementation • NAACL 2021 • Xinya Du, Alexander Rush, Claire Cardie
Template filling is generally tackled by a pipeline of two separate supervised systems {--} one for role-filler extraction and another for template/event recognition.
no code implementations • NAACL 2021 • Dian Yu, Luheng He, Yuan Zhang, Xinya Du, Panupong Pasupat, Qi Li
Few-shot learning arises in important practical scenarios, such as when a natural language understanding system needs to learn new semantic labels for an emerging, resource-scarce domain.
no code implementations • Asian Chapter of the Association for Computational Linguistics 2020 • Xinya Du, Ahmed Hassan Awadallah, Adam Fourney, Robert Sim, Paul Bennett, Claire Cardie
We show that leveraging metadata information from web pages can improve the performance of models for answer passage selection/reranking.
no code implementations • Findings of the Association for Computational Linguistics 2020 • Zonglin Yang, Xinya Du, Alexander Rush, Claire Cardie
End-to-end models in NLP rarely encode external world knowledge about length of time.
2 code implementations • EACL 2021 • Xinya Du, Alexander M. Rush, Claire Cardie
We revisit the classic problem of document-level role-filler entity extraction (REE) for template filling.
1 code implementation • ACL 2020 • Xinya Du, Claire Cardie
Few works in the literature of event extraction have gone beyond individual sentences to make extraction decisions.
3 code implementations • EMNLP 2020 • Xinya Du, Claire Cardie
The problem of event extraction requires detecting the event trigger and extracting its corresponding arguments.
1 code implementation • NAACL 2019 • Xinya Du, Bhavana Dalvi Mishra, Niket Tandon, Antoine Bosselut, Wen-tau Yih, Peter Clark, Claire Cardie
Our goal is procedural text comprehension, namely tracking how the properties of entities (e. g., their location) change with time given a procedural text (e. g., a paragraph about photosynthesis, a recipe).
1 code implementation • ACL 2018 • Xinya Du, Claire Cardie
We study the task of generating from Wikipedia articles question-answer pairs that cover content beyond a single sentence.
no code implementations • EMNLP 2017 • Xinya Du, Claire Cardie
A first step in the task of automatically generating questions for testing reading comprehension is to identify \textit{question-worthy} sentences, i. e. sentences in a text passage that humans find it worthwhile to ask questions about.
9 code implementations • ACL 2017 • Xinya Du, Junru Shao, Claire Cardie
We study automatic question generation for sentences from text passages in reading comprehension.