1 code implementation • BioNLP (ACL) 2022 • Jennifer Bishop, Qianqian Xie, Sophia Ananiadou
To this end, we propose a hybrid, unsupervised, abstractive-extractive approach, in which we walk through a document, generating salient textual fragments representing its key points.
Ranked #1 on Text Summarization on S2ORC
no code implementations • 30 Mar 2024 • Wentao Xu, Qianqian Xie, Shuo Yang, Jiangxia Cao, Shuchao Pang
However, they still neglect the following two points: (1) The content semantic is a universal world knowledge; how do we extract the multi-aspect semantic information to empower different domains?
no code implementations • 25 Mar 2024 • Kailai Yang, Zhiwei Liu, Qianqian Xie, Tianlin Zhang, Nirui Song, Jimin Huang, Ziyan Kuang, Sophia Ananiadou
Recent advancements in large language models (LLMs) aim to tackle heterogeneous human expectations and values via multi-objective preference alignment.
3 code implementations • 10 Mar 2024 • Gang Hu, Ke Qin, Chenhan Yuan, Min Peng, Alejandro Lopez-Lira, Benyou Wang, Sophia Ananiadou, Wanlong Yu, Jimin Huang, Qianqian Xie
While the progression of Large Language Models (LLMs) has notably propelled financial analysis, their application has largely been confined to singular language realms, leaving untapped the potential of bilingual Chinese-English capacity.
no code implementations • 26 Feb 2024 • Mengxi Xiao, Qianqian Xie, Ziyan Kuang, Zhicheng Liu, Kailai Yang, Min Peng, Weiguang Han, Jimin Huang
Large Language Models (LLMs) can play a vital role in psychotherapy by adeptly handling the crucial task of cognitive reframing and overcoming challenges such as shame, distrust, therapist skill variability, and resource scarcity.
no code implementations • 21 Feb 2024 • Zheheng Luo, Qianqian Xie, Sophia Ananiadou
Moreover, automated methods that can effectively assess the `layness' of generated summaries are lacking.
no code implementations • 21 Feb 2024 • Zheheng Luo, Qianqian Xie, Sophia Ananiadou
Experiments on TreatFact suggest that both previous methods and LLM-based evaluators are unable to capture factual inconsistencies in clinical summaries, posing a new challenge for FC evaluation.
2 code implementations • 20 Feb 2024 • Qianqian Xie, Weiguang Han, Zhengyu Chen, Ruoyu Xiang, Xiao Zhang, Yueru He, Mengxi Xiao, Dong Li, Yongfu Dai, Duanyu Feng, Yijing Xu, Haoqiang Kang, Ziyan Kuang, Chenhan Yuan, Kailai Yang, Zheheng Luo, Tianlin Zhang, Zhiwei Liu, Guojun Xiong, Zhiyang Deng, Yuechen Jiang, Zhiyuan Yao, Haohang Li, Yangyang Yu, Gang Hu, Jiajia Huang, Xiao-Yang Liu, Alejandro Lopez-Lira, Benyou Wang, Yanzhao Lai, Hao Wang, Min Peng, Sophia Ananiadou, Jimin Huang
This along with the rapid development of LLMs, highlights the urgent need for a systematic financial evaluation benchmark for LLMs.
1 code implementation • 20 Feb 2024 • Qianqian Xie, Qingyu Chen, Aokun Chen, Cheng Peng, Yan Hu, Fongci Lin, Xueqing Peng, Jimin Huang, Jeffrey Zhang, Vipina Keloth, Xinyu Zhou, Huan He, Lucila Ohno-Machado, Yonghui Wu, Hua Xu, Jiang Bian
In response to this challenge, this study introduces Me-LLaMA, a novel medical LLM family that includes foundation models - Me-LLaMA 13/70B, along with their chat-enhanced versions - Me-LLaMA 13/70B-chat, developed through continual pre-training and instruction tuning of LLaMA2 using large medical datasets.
2 code implementations • 12 Feb 2024 • Xiao Zhang, Ruoyu Xiang, Chenhan Yuan, Duanyu Feng, Weiguang Han, Alejandro Lopez-Lira, Xiao-Yang Liu, Sophia Ananiadou, Min Peng, Jimin Huang, Qianqian Xie
We evaluate our model and existing LLMs using FLARE-ES, the first comprehensive bilingual evaluation benchmark with 21 datasets covering 9 tasks.
1 code implementation • 16 Jan 2024 • Zhiwei Liu, Kailai Yang, Tianlin Zhang, Qianqian Xie, Zeping Yu, Sophia Ananiadou
In this paper, we propose EmoLLMs, the first series of open-sourced instruction-following LLMs for comprehensive affective analysis based on fine-tuning various LLMs with instruction data, the first multi-task affective analysis instruction dataset (AAID) with 234K data samples based on various classification and regression tasks to support LLM instruction tuning, and a comprehensive affective evaluation benchmark (AEB) with 14 tasks from various sources and domains to test the generalization ability of LLMs.
1 code implementation • 9 Oct 2023 • Yongfu Dai, Duanyu Feng, Jimin Huang, Haochen Jia, Qianqian Xie, Yifang Zhang, Weiguang Han, Wei Tian, Hao Wang
Through automated evaluation of current general and legal domain LLMs on our benchmark, we indicate that these LLMs may not align with the logic of legal practice.
1 code implementation • 2 Oct 2023 • Chenhan Yuan, Qianqian Xie, Jimin Huang, Sophia Ananiadou
In this paper, we introduce the first task of explainable temporal reasoning, to predict an event's occurrence at a future timestamp based on context which requires multiple reasoning over multiple events, and subsequently provide a clear explanation for their prediction.
1 code implementation • 1 Oct 2023 • Duanyu Feng, Yongfu Dai, Jimin Huang, Yifang Zhang, Qianqian Xie, Weiguang Han, Zhengyu Chen, Alejandro Lopez-Lira, Hao Wang
We then propose the first Credit and Risk Assessment Large Language Model (CALM) by instruction tuning, tailored to the nuanced demands of various financial risk assessment tasks.
no code implementations • 29 Sep 2023 • Tomas Goldsack, Zheheng Luo, Qianqian Xie, Carolina Scarton, Matthew Shardlow, Sophia Ananiadou, Chenghua Lin
This paper presents the results of the shared task on Lay Summarisation of Biomedical Research Articles (BioLaySumm), hosted at the BioNLP Workshop at ACL 2023.
2 code implementations • 24 Sep 2023 • Kailai Yang, Tianlin Zhang, Ziyan Kuang, Qianqian Xie, Jimin Huang, Sophia Ananiadou
The raw social media data are collected from 10 existing sources covering 8 mental health analysis tasks.
1 code implementation • 21 Sep 2023 • Jennifer A Bishop, Qianqian Xie, Sophia Ananiadou
This framework outperforms existing state-of-the-art metrics in its ability to correlate with human measures of factuality when used to evaluate long document summarisation data sets.
no code implementations • 14 Jul 2023 • Zhaoyi Sun, Mingquan Lin, Qingqing Zhu, Qianqian Xie, Fei Wang, Zhiyong Lu, Yifan Peng
In this scoping review, we aim to provide a comprehensive overview of the current state of the field and identify key concepts, types of studies, and research gaps with a focus on biomedical images and texts joint learning, mainly because these two were the most commonly available data types in MDL research.
1 code implementation • 5 Jul 2023 • Zheheng Luo, Lei Liu, Qianqian Xie, Sophia Ananiadou
Based on it, we propose the graph contrastive topic model (GCTM), which conducts graph contrastive learning (GCL) using informative positive and negative samples that are generated by the graph-based sampling strategy leveraging in-depth correlation and irrelevance among documents and words.
2 code implementations • 8 Jun 2023 • Qianqian Xie, Weiguang Han, Xiao Zhang, Yanzhao Lai, Min Peng, Alejandro Lopez-Lira, Jimin Huang
This paper introduces PIXIU, a comprehensive framework including the first financial LLM based on fine-tuning LLaMA with instruction data, the first instruction data with 136K data samples to support the fine-tuning, and an evaluation benchmark with 5 tasks and 9 datasets.
1 code implementation • 10 May 2023 • Zhibin Lu, Qianqian Xie, Benyou Wang, Jian-Yun Nie
An inductive Word-grounded Graph Convolutional Network (WGCN) is proposed to learn word and document representations based on WGraph in a supervised manner.
no code implementations • 18 Apr 2023 • Qianqian Xie, Zheheng Luo, Benyou Wang, Sophia Ananiadou
In this paper, we present a systematic review of recent advancements in BTS, leveraging cutting-edge NLP techniques from PLMs to LLMs, to help understand the latest progress, challenges, and future directions.
no code implementations • 11 Apr 2023 • Chenhan Yuan, Qianqian Xie, Sophia Ananiadou
The current shortcomings of ChatGPT on temporal relation extraction are also discussed in this paper.
no code implementations • 10 Apr 2023 • Qianqian Xie, Weiguang Han, Yanzhao Lai, Min Peng, Jimin Huang
Recently, large language models (LLMs) like ChatGPT have demonstrated remarkable performance across a variety of natural language processing tasks.
2 code implementations • 6 Apr 2023 • Kailai Yang, Shaoxiong Ji, Tianlin Zhang, Qianqian Xie, Ziyan Kuang, Sophia Ananiadou
The latest large language models (LLMs) such as ChatGPT, exhibit strong capabilities in automated mental health analysis.
no code implementations • 1 Apr 2023 • Weiguang Han, Jimin Huang, Qianqian Xie, Boyi Zhang, Yanzhao Lai, Min Peng
Although pair trading is the simplest hedging strategy for an investor to eliminate market risk, it is still a great challenge for reinforcement learning (RL) methods to perform pair trading as human expertise.
no code implementations • 27 Mar 2023 • Zheheng Luo, Qianqian Xie, Sophia Ananiadou
In this paper, we particularly explore ChatGPT's ability to evaluate factual inconsistency under a zero-shot setting by examining it on both coarse-grained and fine-grained evaluation tasks including binary entailment inference, summary ranking, and consistency rating.
Abstractive Text Summarization Natural Language Inference +3
no code implementations • 15 Mar 2023 • Qianqian Xie, Jiayu Zhou, Yifan Peng, Fei Wang
We propose to extract medical facts of the input medical report, its gold summary, and candidate summaries based on the RadGraph schema and design the fact-guided reranker to efficiently incorporate the extracted medical facts for selecting the optimal summary.
no code implementations • 26 Jan 2023 • Zheheng Luo, Qianqian Xie, Sophia Ananiadou
To fill that gap, we propose a novel citation-aware scientific paper summarization framework based on citation graphs, able to accurately locate and incorporate the salient contents from references, as well as capture varying relevance between source papers and their references.
1 code implementation • 25 Jan 2023 • Weiguang Han, Boyi Zhang, Qianqian Xie, Min Peng, Yanzhao Lai, Jimin Huang
For pair selection, ignoring the trading performance results in the wrong assets being selected with irrelevant price movements, while the agent trained for trading can overfit to the selected assets without any historical information of other assets.
Ranked #1 on PAIR TRADING on S&P 500 Pair Trading
1 code implementation • 10 Oct 2022 • Miao Peng, Ben Liu, Qianqian Xie, Wenjie Xu, Hua Wang, Min Peng
Specifically, we first exploit network schema as the prior constraint to sample negatives and pre-train our model by employing a multi-level contrastive learning method to yield both prior schema and contextual information.
no code implementations • 10 Oct 2022 • Zheheng Luo, Qianqian Xie, Sophia Ananiadou
Different from general documents, it is recognised that the ease with which people can understand a biomedical text is eminently varied, owing to the highly technical nature of biomedical documents and the variance of readers' domain knowledge.
no code implementations • COLING 2022 • Qianqian Xie, Jimin Huang, Tulika Saha, Sophia Ananiadou
Recently, neural topic models (NTMs) have been incorporated into pre-trained language models (PLMs), to capture the global semantic information for text summarization.
Ranked #9 on Text Summarization on Pubmed
1 code implementation • 2 Jul 2022 • Benyou Wang, Xiangbo Wu, Xiaokang Liu, Jianquan Li, Prayag Tiwari, Qianqian Xie
However, the humor aspect of natural language is relatively under-investigated, especially in the age of pre-trained language models.
1 code implementation • 11 Oct 2021 • Benyou Wang, Qianqian Xie, Jiahuan Pei, Zhihong Chen, Prayag Tiwari, Zhao Li, Jie Fu
In this paper, we summarize the recent progress of pre-trained language models in the biomedical domain and their applications in biomedical downstream tasks.
no code implementations • NAACL 2021 • Qianqian Xie, Jimin Huang, Pan Du, Min Peng, Jian-Yun Nie
T-VGAE inherits the interpretability of the topic model and the efficient information propagation mechanism of VGAE.
Representation Learning Semi-Supervised Text Classification +1
no code implementations • 13 Apr 2020 • Shuangyong Song, Chao Wang, Qianqian Xie, Xinxing Zu, Huan Chen, Haiqing Chen
In this paper, we propose the conversational query rewriting model - MLR, which is a Multi-task model on sequence Labeling and query Rewriting.
no code implementations • ACL 2018 • Min Peng, Qianqian Xie, Yanchun Zhang, Hua Wang, Xiuzhen Zhang, Jimin Huang, Gang Tian
Topic models with sparsity enhancement have been proven to be effective at learning discriminative and coherent latent topics of short texts, which is critical to many scientific and engineering applications.