Zheng Chen


2024

pdf bib
RecMind: Large Language Model Powered Agent For Recommendation
Yancheng Wang | Ziyan Jiang | Zheng Chen | Fan Yang | Yingxue Zhou | Eunah Cho | Xing Fan | Yanbin Lu | Xiaojiang Huang | Yingzhen Yang
Findings of the Association for Computational Linguistics: NAACL 2024

While the recommendation system (RS) has advanced significantly through deep learning, current RS approaches usually train and fine-tune models on task-specific datasets, limiting their generalizability to new recommendation tasks and their ability to leverage external knowledge due to model scale and data size constraints. Thus, we designed an LLM-powered autonomous recommender agent, RecMind, which is capable of leveraging external knowledge, utilizing tools with careful planning to provide zero-shot personalized recommendations. We propose a Self-Inspiring algorithm to improve the planning ability. At each intermediate step, the LLM “self-inspires” to consider all previously explored states to plan for the next step. This mechanism greatly improves the model’s ability to comprehend and utilize historical information in planning for recommendation. We evaluate RecMind’s performance in various recommendation scenarios. Our experiment shows that RecMind outperforms existing zero/few-shot LLM-based recommendation baseline methods in various tasks and achieves comparable performance to a fully trained recommendation model P5.

2023

pdf bib
Harnessing LLMs for Temporal Data - A Study on Explainable Financial Time Series Forecasting
Xinli Yu | Zheng Chen | Yanbin Lu
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track

Applying machine learning to financial time series has been an active area of industrial research enabling innovation in market insights, risk management, strategic decision-making, and policy formation. This paper explores the novel use of Large Language Models (LLMs) for explainable financial time series forecasting, addressing challenges in cross-sequence reasoning, multi-modal data integration, and result interpretation that are inherent in traditional approaches. Focusing on NASDAQ-100 stocks, we utilize public historical stock data, company metadata, and economic/financial news. Our experiments employ GPT-4 for zero-shot/few-shot inference and Open LLaMA for instruction-based fine-tuning. The study demonstrates LLMs’ ability to generate well-reasoned decisions by leveraging cross-sequence information and extracting insights from text and price time series. We show that our LLM-based approach outperforms classic ARMA-GARCH and gradient-boosting tree models. Furthermore, fine-tuned public LLMs, such as Open-LLaMA, can generate reasonable and explainable forecasts, although they underperform compared to GPT-4.

pdf bib
Graph Meets LLM: A Novel Approach to Collaborative Filtering for Robust Conversational Understanding
Zheng Chen | Ziyan Jiang | Fan Yang | Eunah Cho | Xing Fan | Xiaojiang Huang | Yanbin Lu | Aram Galstyan
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track

A Personalized Query Rewriting system strives to minimize defective queries to ensure robust conversational functionality by considering individual user behavior and preferences. It’s designed as a search-based system, maintaining a user index of past successful interactions with the conversational AI. However, this method faces challenges with unseen interactions, which refers to novel user interactions not covered by the user’s historical index. This paper introduces our Collaborative Query Rewriting approach, which utilizes underlying topological information to assist in rewriting defective queries arising from unseen user interactions. This approach begins by constructing a “User Feedback Interaction Graph” (FIG) using historical user-entity interactions. Subsequently, we traverse through the graph edges to establish an enhanced user index, referred to as the “collaborative user index”. This paper then further explores the use of Large Language Models (LLMs) in conjunction with graph traversal, leading to a significant increase in index coverage for unseen interactions. The effectiveness of our proposed approach has been proven through experiments on a large-scale real-world dataset and online A/B experiments.

2022

pdf bib
CATAMARAN: A Cross-lingual Long Text Abstractive Summarization Dataset
Zheng Chen | Hongyu Lin
Proceedings of the Thirteenth Language Resources and Evaluation Conference

Cross-lingual summarization, which produces the summary in one language from a given source document in another language, could be extremely helpful for humans to obtain information across the world. However, it is still a little-explored task due to the lack of datasets. Recent studies are primarily based on pseudo-cross-lingual datasets obtained by translation. Such an approach would inevitably lead to the loss of information in the original document and introduce noise into the summary, thus hurting the overall performance. In this paper, we present CATAMARAN, the first high-quality cross-lingual long text abstractive summarization dataset. It contains about 20,000 parallel news articles and corresponding summaries, all written by humans. The average lengths of articles are 1133.65 for English articles and 2035.33 for Chinese articles, and the average lengths of the summaries are 26.59 and 70.05, respectively. We train and evaluate an mBART-based cross-lingual abstractive summarization model using our dataset. The result shows that, compared with mono-lingual systems, the cross-lingual abstractive summarization system could also achieve solid performance.

pdf bib
Overcoming Catastrophic Forgetting During Domain Adaptation of Seq2seq Language Generation
Dingcheng Li | Zheng Chen | Eunah Cho | Jie Hao | Xiaohu Liu | Fan Xing | Chenlei Guo | Yang Liu
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Seq2seq language generation models that are trained offline with multiple domains in a sequential fashion often suffer from catastrophic forgetting. Lifelong learning has been proposed to handle this problem. However, existing work such as experience replay or elastic weighted consolidation requires incremental memory space. In this work, we propose an innovative framework, RMR_DSEthat leverages a recall optimization mechanism to selectively memorize important parameters of previous tasks via regularization, and uses a domain drift estimation algorithm to compensate the drift between different do-mains in the embedding space. These designs enable the model to be trained on the current task while keep-ing the memory of previous tasks, and avoid much additional data storage. Furthermore, RMR_DSE can be combined with existing lifelong learning approaches. Our experiments on two seq2seq language generation tasks, paraphrase and dialog response generation, show thatRMR_DSE outperforms SOTA models by a considerable margin and reduces forgetting greatly.

2021

pdf bib
Personalized Search-based Query Rewrite System for Conversational AI
Eunah Cho | Ziyan Jiang | Jie Hao | Zheng Chen | Saurabh Gupta | Xing Fan | Chenlei Guo
Proceedings of the 3rd Workshop on Natural Language Processing for Conversational AI

Query rewrite (QR) is an emerging component in conversational AI systems, reducing user defect. User defect is caused by various reasons, such as errors in the spoken dialogue system, users’ slips of the tongue or their abridged language. Many of the user defects stem from personalized factors, such as user’s speech pattern, dialect, or preferences. In this work, we propose a personalized search-based QR framework, which focuses on automatic reduction of user defect. We build a personalized index for each user, which encompasses diverse affinity layers to reflect personal preferences for each user in the conversational AI. Our personalized QR system contains retrieval and ranking layers. Supported by user feedback based learning, training our models does not require hand-annotated data. Experiments on personalized test set showed that our personalized QR system is able to correct systematic and user errors by utilizing phonetic and semantic inputs.

2020

pdf bib
ForceReader: a BERT-based Interactive Machine Reading Comprehension Model with Attention Separation
Zheng Chen | Kangjian Wu
Proceedings of the 28th International Conference on Computational Linguistics

The release of BERT revolutionized the development of NLP. Various BERT-based reading comprehension models have been proposed, thus updating the performance ranking of reading comprehension tasks. However, the above BERT-based models inherently employ BERT’s combined input method, representing the input question and paragraph as a single packed sequence, without further modification for reading comprehension. This paper makes an in-depth analysis of this input method, proposes a problem of this approach. We call it attention deconcentration. Accordingly, this paper proposes ForceReader, a BERT-based interactive machine reading comprehension model. First, ForceReader proposes a novel solution called the Attention Separation Representation to respond to attention deconcentration. Moreover, starting from the logical nature of reading comprehension tasks, ForceReader adopts Multi-mode Reading and Interactive Reasoning strategy. For the calculation of attention, ForceReader employs Conditional Background Attention to solve the lack of the overall context semantic after the separation of attention. As an integral model, ForceReader shows a significant improvement in reading comprehension tasks compared to BERT. Moreover, this paper makes detailed visual analyses of the attention and propose strategies accordingly. This may be another argument to the explanations of the attention.

2017

pdf bib
Detecting and Explaining Causes From Text For a Time Series Event
Dongyeop Kang | Varun Gangal | Ang Lu | Zheng Chen | Eduard Hovy
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

Explaining underlying causes or effects about events is a challenging but valuable task. We define a novel problem of generating explanations of a time series event by (1) searching cause and effect relationships of the time series with textual data and (2) constructing a connecting chain between them to generate an explanation. To detect causal features from text, we propose a novel method based on the Granger causality of time series between features extracted from text such as N-grams, topics, sentiments, and their composition. The generation of the sequence of causal entities requires a commonsense causative knowledge base with efficient reasoning. To ensure good interpretability and appropriate lexical usage we combine symbolic and neural representations, using a neural reasoning algorithm trained on commonsense causal tuples to predict the next cause step. Our quantitative and human analysis show empirical evidence that our method successfully extracts meaningful causality relationships between time series with textual features and generates appropriate explanation between them.

2016

pdf bib
Entity Disambiguation by Knowledge and Text Jointly Embedding
Wei Fang | Jianwen Zhang | Dilin Wang | Zheng Chen | Ming Li
Proceedings of the 20th SIGNLL Conference on Computational Natural Language Learning

2015

pdf bib
Aligning Knowledge and Text Embeddings by Entity Descriptions
Huaping Zhong | Jianwen Zhang | Zhen Wang | Hai Wan | Zheng Chen
Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing

2014

pdf bib
Knowledge Graph and Text Jointly Embedding
Zhen Wang | Jianwen Zhang | Jianlin Feng | Zheng Chen
Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)

2013

pdf bib
Towards Accurate Distant Supervision for Relational Facts Extraction
Xingxing Zhang | Jianwen Zhang | Junyu Zeng | Jun Yan | Zheng Chen | Zhifang Sui
Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

2011

pdf bib
Collaborative Ranking: A Case Study on Entity Linking
Zheng Chen | Heng Ji
Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing

pdf bib
Cross-lingual Slot Filling from Comparable Corpora
Matthew Snover | Xiang Li | Wen-Pin Lin | Zheng Chen | Suzanne Tamang | Mingmin Ge | Adam Lee | Qi Li | Hao Li | Sam Anzaroot | Heng Ji
Proceedings of the 4th Workshop on Building and Using Comparable Corpora: Comparable Corpora and the Web

2010

pdf bib
Graph-Based Clustering for Computational Linguistics: A Survey
Zheng Chen | Heng Ji
Proceedings of TextGraphs-5 - 2010 Workshop on Graph-based Methods for Natural Language Processing

pdf bib
Utility Evaluation of Cross-document Information Extraction
Heng Ji | Zheng Chen | Jonathan Feldman | Antonio Gonzalez | Ralph Grishman | Vivek Upadhyay
Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics

2009

pdf bib
Can One Language Bootstrap the Other: A Case Study on Event Extraction
Zheng Chen | Heng Ji
Proceedings of the NAACL HLT 2009 Workshop on Semi-supervised Learning for Natural Language Processing

pdf bib
Graph-based Event Coreference Resolution
Zheng Chen | Heng Ji
Proceedings of the 2009 Workshop on Graph-based Methods for Natural Language Processing (TextGraphs-4)

pdf bib
A Pairwise Event Coreference Model, Feature Impact and Evaluation for Event Coreference Resolution
Zheng Chen | Heng Ji | Robert Haralick
Proceedings of the Workshop on Events in Emerging Text Types

pdf bib
Cross-document Event Extraction and Tracking: Task, Evaluation, Techniques and Challenges
Heng Ji | Ralph Grishman | Zheng Chen | Prashant Gupta
Proceedings of the International Conference RANLP-2009

pdf bib
Language Specific Issue and Feature Exploration in Chinese Event Extraction
Zheng Chen | Heng Ji
Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics, Companion Volume: Short Papers

pdf bib
Cross-document Temporal and Spatial Person Tracking System Demonstration
Heng Ji | Zheng Chen
Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics, Companion Volume: Demonstration Session

2003

pdf bib
A Study for Document Summarization Based on Personal Annotation
Haiqin Zhang | Zheng Chen | Wei-ying Ma | Qingsheng Cai
Proceedings of the HLT-NAACL 03 Text Summarization Workshop

2000

pdf bib
A New Statistical Approach To Chinese Pinyin Input
Zheng Chen | Kai-Fu Lee
Proceedings of the 38th Annual Meeting of the Association for Computational Linguistics