1 code implementation • CoNLL (EMNLP) 2021 • Shisong Chen, Binbin Gu, Jianfeng Qu, Zhixu Li, An Liu, Lei Zhao, Zhigang Chen
Zero pronoun resolution aims at recognizing dropped pronouns and pointing out their anaphoric mentions, while non-zero coreference resolution targets at clustering mentions referring to the same entity.
no code implementations • 24 Feb 2025 • Chenghua Huang, Lu Wang, Fangkai Yang, Pu Zhao, Zhixu Li, QIngwei Lin, Dongmei Zhang, Saravan Rajmohan, Qi Zhang
Proximal Policy Optimization (PPO)-based Reinforcement Learning from Human Feedback (RLHF) is essential for aligning large language models (LLMs) with human preferences.
1 code implementation • 14 Oct 2024 • Xiangru Zhu, Penglei Sun, Yaoxian Song, Yanghua Xiao, Zhixu Li, Chengyu Wang, Jun Huang, Bei Yang, Xiaoxiao Xu
To address these deficiencies, we propose a novel metric called SemVarEffect and a benchmark named SemVarBench, designed to evaluate the causality between semantic variations in inputs and outputs in T2I synthesis.
no code implementations • 23 Sep 2024 • Yuyan Chen, Yiwen Qian, Songzhou Yan, Jiyuan Jia, Zhixu Li, Yanghua Xiao, Xiaobo Li, Ming Yang, Qingpei Guo
In the era of social media video platforms, popular ``hot-comments'' play a crucial role in attracting user impressions of short-form videos, making them vital for marketing and branding purpose.
no code implementations • 4 Sep 2024 • Chunyan An, Yunhan Li, Qiang Yang, Winston K. G. Seah, Zhixu Li, Conghao Yang
This approach not only alleviates the problem of friend data sparsity but also effectively incorporates users with similar preferences to the target user.
no code implementations • 24 Jul 2024 • Yuyan Chen, Songzhou Yan, Zhihong Zhu, Zhixu Li, Yanghua Xiao
Humor, deeply rooted in societal meanings and cultural details, poses a unique challenge for machines.
no code implementations • 4 Jul 2024 • Yuyan Chen, Qiang Fu, Yichen Yuan, Zhihao Wen, Ge Fan, Dayiheng Liu, Dongmei Zhang, Zhixu Li, Yanghua Xiao
Large Language Models (LLMs) have gained widespread adoption in various natural language processing tasks, including question answering and dialogue systems.
no code implementations • 4 Jul 2024 • Yuyan Chen, Zhixu Li, Jiaqing Liang, Yanghua Xiao, Bang Liu, Yunwen Chen
Humor understanding is an important and challenging research in natural language processing.
no code implementations • 4 Jul 2024 • Yuyan Chen, Zhihao Wen, Ge Fan, Zhengyu Chen, Wei Wu, Dayiheng Liu, Zhixu Li, Bang Liu, Yanghua Xiao
Prompt engineering, as an efficient and effective way to leverage Large Language Models (LLM), has drawn a lot of attention from the research community.
no code implementations • 3 Jul 2024 • Penglei Sun, Yaoxian Song, Xinglin Pan, Peijie Dong, Xiaofei Yang, Qiang Wang, Zhixu Li, Tiefeng Li, Xiaowen Chu
However, they have failed to consider exploring the cross-modal representation of language-vision alignment in the cross-domain field.
3 code implementations • 21 Jun 2024 • Haiquan Zhao, Lingyu Li, Shisong Chen, Shuqi Kong, Jiaan Wang, Kexin Huang, Tianle Gu, Yixu Wang, Wang Jian, Dandan Liang, Zhixu Li, Yan Teng, Yanghua Xiao, Yingchun Wang
Inspired by the awesome development of role-playing agents, we propose an ESC Evaluation framework (ESC-Eval), which uses a role-playing agent to interact with ESC models, followed by a manual evaluation of the interactive dialogues.
1 code implementation • 19 Jun 2024 • Jipeng Cen, Jiaxin Liu, Zhixu Li, Jingjing Wang
Subsequently, leveraging similar repair retrieval and failure memory reflection, the SQLRefiner agent selects the most fitting SQL statement from the candidates as the final repair.
no code implementations • 15 Jun 2024 • Xiaoxuan Zhu, Zhouhong Gu, Sihang Jiang, Zhixu Li, Hongwei Feng, Yanghua Xiao
Online courses have significantly lowered the barrier to accessing education, yet the varying content quality of these videos poses challenges.
2 code implementations • 19 Apr 2024 • Wenhao Huang, Zhouhong Gu, Chenghao Peng, Zhixu Li, Jiaqing Liang, Yanghua Xiao, Liqian Wen, Zulong Chen
In this work, we introduce the paradigm of generating web scrapers with LLMs and propose AutoScraper, a two-stage framework that can handle diverse and changing web environments more efficiently.
1 code implementation • 25 Mar 2024 • Wenhao Huang, Qianyu He, Zhixu Li, Jiaqing Liang, Yanghua Xiao
Definition bias is a negative phenomenon that can mislead models.
no code implementations • 20 Mar 2024 • Haoyu Liu, Yaoxian Song, Xuwu Wang, Zhu Xiangru, Zhixu Li, Wei Song, Tiefeng Li
Text-image retrieval research is needed to realize high-quality and efficient retrieval between different modalities.
no code implementations • 3 Mar 2024 • Haiquan Zhao, Xuwu Wang, Shisong Chen, Zhixu Li, Xin Zheng, Yanghua Xiao
In this paper, we propose a task called Online Video Entity Linking OVEL, aiming to establish connections between mentions in online videos and a knowledge base with high accuracy and timeliness.
1 code implementation • 9 Jan 2024 • Jiaan Wang, Jianfeng Qu, Kexin Wang, Zhixu Li, Wen Hua, Ximing Li, An Liu
Knowledge-grounded dialogue (KGD) learns to generate an informative response based on a given dialogue context and external knowledge (\emph{e. g.}, knowledge graphs; KGs).
1 code implementation • 16 Dec 2023 • Zhiwei Zha, Jiaan Wang, Zhixu Li, Xiangru Zhu, Wei Song, Yanghua Xiao
Comprising 951K images and 152K concepts, M^2ConceptBase links each concept to an average of 6. 27 images and a single description, ensuring comprehensive visual and textual semantics.
1 code implementation • 4 Dec 2023 • Xiangru Zhu, Penglei Sun, Chengyu Wang, Jingping Liu, Zhixu Li, Yanghua Xiao, Jun Huang
We use Winoground-T2I with a dual objective: to evaluate the performance of T2I models and the metrics used for their evaluation.
1 code implementation • 9 Aug 2023 • Jingdan Zhang, Jiaan Wang, Xiaodan Wang, Zhixu Li, Yanghua Xiao
Multi-modal knowledge graphs (MMKGs) combine different modal data (e. g., text and image) for a comprehensive understanding of entities.
1 code implementation • 19 Jun 2023 • Wenhao Huang, Jiaqing Liang, Zhixu Li, Yanghua Xiao, Chuanjun Ji
Information extraction (IE) has been studied extensively.
no code implementations • 17 Jun 2023 • Jiaan Wang, Jianfeng Qu, Yunlong Liang, Zhixu Li, An Liu, Guanfeng Liu, Xin Zheng
Constructing commonsense knowledge graphs (CKGs) has attracted wide research attention due to its significant importance in cognitive intelligence.
no code implementations • 16 May 2023 • Jiaan Wang, Fandong Meng, Duo Zheng, Yunlong Liang, Zhixu Li, Jianfeng Qu, Jie zhou
In this paper, we aim to unify MLS and CLS into a more general setting, i. e., many-to-many summarization (M2MS), where a single model could process documents in any language and generate their summaries also in any language.
no code implementations • 25 Mar 2023 • Zhouhong Gu, Sihang Jiang, Jingping Liu, Yanghua Xiao, Hongwei Feng, Zhixu Li, Jiaqing Liang, Jian Zhong
The previous methods suffer from low-efficiency since they waste much time when most of the new coming concepts are indeed noisy concepts.
1 code implementation • 7 Mar 2023 • Jiaan Wang, Yunlong Liang, Fandong Meng, Zengkui Sun, Haoxiang Shi, Zhixu Li, Jinan Xu, Jianfeng Qu, Jie zhou
In detail, we regard ChatGPT as a human evaluator and give task-specific (e. g., summarization) and aspect-specific (e. g., relevance) instruction to prompt ChatGPT to evaluate the generated results of NLG models.
no code implementations • 28 Feb 2023 • Jiaan Wang, Yunlong Liang, Fandong Meng, Beiqi Zou, Zhixu Li, Jianfeng Qu, Jie zhou
Given a document in a source language, cross-lingual summarization (CLS) aims to generate a summary in a different target language.
no code implementations • 27 Jan 2023 • Yaoxian Song, Penglei Sun, Piaopiao Jin, Yi Ren, Yu Zheng, Zhixu Li, Xiaowen Chu, Yue Zhang, Tiefeng Li, Jason Gu
From the perspective of robotic cognition, we design a two-stage fine-grained robotic grasping framework (named LangPartGPD), including a novel 3D part language grounding model and a part-aware grasp pose detection model, in which explicit language input from human or large language models (LLMs) could guide a robot to generate part-level 6-DoF grasping pose with textual explanation.
no code implementations • 14 Dec 2022 • Jiaan Wang, Fandong Meng, Yunlong Liang, Tingyi Zhang, Jiarong Xu, Zhixu Li, Jie zhou
In detail, we find that (1) the translationese in documents or summaries of test sets might lead to the discrepancy between human judgment and automatic evaluation; (2) the translationese in training sets would harm model performance in real-world applications; (3) though machine-translated documents involve translationese, they are very useful for building CLS systems on low-resource languages under specific training strategies.
1 code implementation • 1 Dec 2022 • Shaohui Zheng, Zhixu Li, Jiaan Wang, Jianfeng Qu, An Liu, Lei Zhao, Zhigang Chen
Cross-Lingual Summarization (CLS) aims at generating summaries in one language for the given documents in another language.
1 code implementation • 6 Oct 2022 • Siyu Yuan, Deqing Yang, Jiaqing Liang, Zhixu Li, Jinxi Liu, Jingyue Huang, Yanghua Xiao
To overcome these drawbacks, we propose a novel generative entity typing (GET) paradigm: given a text with an entity mention, the multiple types for the role that the entity plays in the text are generated with a pre-trained language model (PLM).
1 code implementation • 17 Jul 2022 • Kexin Wang, Zhixu Li, Jiaan Wang, Jianfeng Qu, Ying He, An Liu, Lei Zhao
Nevertheless, the correlations between knowledge implied in the multi-turn context and the transition regularities between relations in KGs are under-explored.
3 code implementations • ACL 2022 • Xuwu Wang, Junfeng Tian, Min Gui, Zhixu Li, Rui Wang, Ming Yan, Lihan Chen, Yanghua Xiao
In this paper, we present WikiDiverse, a high-quality human-annotated MEL dataset with diversified contextual topics and entity types from Wikinews, which uses Wikipedia as the corresponding knowledge base.
no code implementations • 23 Mar 2022 • Jiaan Wang, Fandong Meng, Duo Zheng, Yunlong Liang, Zhixu Li, Jianfeng Qu, Jie zhou
Cross-lingual summarization is the task of generating a summary in one language (e. g., English) for the given document(s) in a different language (e. g., Chinese).
1 code implementation • ACL 2022 • Qianyu He, Sijie Cheng, Zhixu Li, Rui Xie, Yanghua Xiao
In this paper, we investigate the ability of PLMs in simile interpretation by designing a novel task named Simile Property Probing, i. e., to let the PLMs infer the shared properties of similes.
2 code implementations • 11 Feb 2022 • Jiaan Wang, Fandong Meng, Ziyao Lu, Duo Zheng, Zhixu Li, Jianfeng Qu, Jie zhou
We present ClidSum, a benchmark dataset for building cross-lingual summarization systems on dialogue documents.
no code implementations • 11 Feb 2022 • Xiangru Zhu, Zhixu Li, Xiaodan Wang, Xueyao Jiang, Penglei Sun, Xuwu Wang, Yanghua Xiao, Nicholas Jing Yuan
In this survey on MMKGs constructed by texts and images, we first give definitions of MMKGs, followed with the preliminaries on multi-modal tasks and techniques.
1 code implementation • 29 Jan 2022 • Jiaan Wang, Beiqi Zou, Zhixu Li, Jianfeng Qu, Pengpeng Zhao, An Liu, Lei Zhao
Story ending generation is an interesting and challenging task, which aims to generate a coherent and reasonable ending given a story context.
1 code implementation • 24 Nov 2021 • Jiaan Wang, Zhixu Li, Tingyi Zhang, Duo Zheng, Jianfeng Qu, An Liu, Lei Zhao, Zhigang Chen
Additionally, we also introduce a knowledge-enhanced summarizer that utilizes both live commentaries and the knowledge to generate sports news.
2 code implementations • 12 Oct 2021 • Jiaan Wang, Zhixu Li, Qiang Yang, Jianfeng Qu, Zhigang Chen, Qingsheng Liu, Guoping Hu
Sports game summarization aims to generate news articles from live text commentaries.
1 code implementation • 27 Jun 2021 • Jiaan Wang, Zhixu Li, Binbin Gu, Tingyi Zhang, Qingsheng Liu, Zhigang Chen
In addition, our approach also helps to improve the accuracy of its downstream task - song search by more than 10. 6%.
no code implementations • 2 Oct 2020 • Hongzhi Yin, Qinyong Wang, Kai Zheng, Zhixu Li, Xiaofang Zhou
Specifically, we first extend BGEM to model group-item interactions, and then in order to overcome the limitation and sparsity of the interaction data generated by occasional groups, we propose a self-attentive mechanism to represent groups based on the group members.
no code implementations • 18 Jun 2018 • Pengpeng Zhao, Haifeng Zhu, Yanchi Liu, Zhixu Li, Jiajie Xu, Victor S. Sheng
Furthermore, to reduce the number of parameters and improve efficiency, we further integrate coupled input and forget gates with our proposed model.