Yulong Pei


2023

pdf bib
Are ChatGPT and GPT-4 General-Purpose Solvers for Financial Text Analytics? A Study on Several Typical Tasks
Xianzhi Li | Samuel Chan | Xiaodan Zhu | Yulong Pei | Zhiqiang Ma | Xiaomo Liu | Sameena Shah
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track

The most recent large language models (LLMs) such as ChatGPT and GPT-4 have shown exceptional capabilities of generalist models, achieving state-of-the-art performance on a wide range of NLP tasks with little or no adaptation. How effective are such models in the finance domain? Understanding this basic question would have a significant impact on many downstream financial analytical tasks. In this paper, we conduct empirical studies and provide experimental evidences of their performance on a wide variety of financial text analytical problems, using eight benchmark datasets from five categories of tasks. We report both the strengths and limitations of the current models by comparing them to the state-of-the-art fine-tuned approaches and the recently released domain-specific pretrained models. We hope our study can help to understand the capability of the existing models in the financial domain and facilitate further improvements.

2022

pdf bib
TweetFinSent: A Dataset of Stock Sentiments on Twitter
Yulong Pei | Amarachi Mbakwe | Akshat Gupta | Salwa Alamir | Hanxuan Lin | Xiaomo Liu | Sameena Shah
Proceedings of the Fourth Workshop on Financial Technology and Natural Language Processing (FinNLP)

Stock sentiment has strong correlations with the stock market but traditional sentiment analysis task classifies sentiment according to having feelings and emotions of good or bad. This definition of sentiment is not an accurate indicator of public opinion about specific stocks. To bridge this gap, we introduce a new task of stock sentiment analysis and present a new dataset for this task named TweetFinSent. In TweetFinSent, tweets are annotated based on if one gained or expected to gain positive or negative return from a stock. Experiments on TweetFinSent with several sentiment analysis models from lexicon-based to transformer-based have been conducted. Experimental results show that TweetFinSent dataset constitutes a challenging problem and there is ample room for improvement on the stock sentiment analysis task. TweetFinSent is available at https://github.com/jpmcair/tweetfinsent.

2012

pdf bib
A Supervised Aggregation Framework for Multi-Document Summarization
Yulong Pei | Wenpeng Yin | Qifeng Fan | Lian’en Huang
Proceedings of COLING 2012

pdf bib
RelationListwise for Query-Focused Multi-Document Summarization
Wenpeng Yin | Lifu Huang | Yulong Pei | Lian’en Huang
Proceedings of COLING 2012

pdf bib
SentTopic-MultiRank: a Novel Ranking Model for Multi-Document Summarization
Wenpeng Yin | Yulong Pei | Fan Zhang | Lian’en Huang
Proceedings of COLING 2012