publications

2024

1. EMNLP

   Dancing in Chains: Reconciling Instruction Following and Faithfulness in Language Models

   Zhengxuan Wu,  Yuhao Zhang*,  Peng Qi*,  Yumo Xu*,  Rujun Han,  Yian Zhang,  Jifan Chen,  Bonan Min, and  Zhiheng Huang

   In Empirical Methods in Natural Language Processing (EMNLP), 2024

   PDF
2. EMNLP

   RAG-QA Arena: Evaluating Domain Robustness for Long-form Retrieval Augmented Question Answering

   Rujun Han,  Yuhao Zhang,  Peng Qi,  Yumo Xu,  Wang Jenyuan,  Lan Liu,  William Yang Wang,  Bonan Min, and  Vittorio Castelli

   In Empirical Methods in Natural Language Processing (EMNLP), 2024

   PDF

2023

1. ACL Findings

   Language Agnostic Multilingual Information Retrieval with Contrastive Learning

   Xiyang Hu,  Xinchi Chen*,  Peng Qi*,  Deguang Kong,  Kunlun Liu,  William Yang Wang, and  Zhiheng Huang

   In Findings of the Association for Computational Linguistics, 2023

   PDF
2. EMNLP Findings

   Tokenization Consistency Matters for Generative Models on Extractive NLP Tasks

   Kaiser Sun,  Peng Qi*,  Yuhao Zhang*,  Lan Liu,  William Yang Wang, and  Zhiheng Huang

   In Findings of the Association for Computational Linguistics: EMNLP , 2023

   PDF
3. ACL Findings

   RobustQA: Benchmarking the Robustness of Domain Adaptation for Open-Domain Question Answering

   Rujun Han,  Peng Qi,  Yuhao Zhang,  Lan Liu,  Juliette Burger,  William Yang Wang,  Zhiheng Huang,  Bing Xiang, and  Dan Roth

   In Findings of the Association for Computational Linguistics: ACL 2023, 2023

   PDF Code
4. ACL Findings

   PragmatiCQA: A Dataset for Pragmatic Question Answering in Conversations

   Peng Qi*,  Nina Du*,  Christopher D. Manning, and  Jing Huang

   In Findings of the Association for Computational Linguistics: ACL 2023, 2023

   PDF Code
5. ACL Findings

   Hybrid Hierarchical Retrieval for Open-Domain Question Answering

   Manoj Ghuhan Arivazhagan,  Lan Liu*,  Peng Qi*,  Xinchi Chen*,  William Yang Wang, and  Zhiheng Huang

   In Findings of the Association for Computational Linguistics: ACL 2023, 2023

   PDF
6. CSUR

   Trustworthy AI: From Principles to Practices

   Bo Li,  Peng Qi,  Bo Liu,  Shuai Di,  Jingen Liu,  Jiquan Pei,  Jinfeng Yi, and  Bowen Zhou

   ACM Computing Surveys, 2023

   PDF

2022

1. arXiv

   How (Not) To Evaluate Explanation Quality

   Hendrik Schuff,  Heike Adel,  Peng Qi, and  Ngoc Thang Vu

   arXiv preprint arXiv:2210.07126, 2022

   PDF
2. arXiv

   SpanDrop: Simple and Effective Counterfactual Learning for Long Sequences

   Peng Qi*,  Guangtao Wang*, and  Jing Huang

   arXiv preprint arXiv:2022.02169, 2022

   PDF
3. SIGDIAL

   Neural Generation Meets Real People: Building a Social, Informative Open-Domain Dialogue Agent

   Ethan A. Chi*,  Ashwin Paranjape*,  Abigail See*,  Caleb Chiam*,  Kathleen Kenealy,  Swee Kiat Lim,  Amelia Hardy,  Chetanya Rastogi,  Haojun Li,  Alexander Iyabor,  Yutong He,  Hari Sowriranjan,  Peng Qi,  Kaushik Ram Sadagopan,  Nguyet Minh Phu,  Dilara Soylu,  Jillian Tang,  Avanika Narayan,  Giovanni Campagna, and  Christopher D. Manning

   In The 23rd Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL 2022), 2022

   PDF
4. ACL

   Improving Time Sensitivity for Question Answering over Temporal Knowledge Graphs

   Chao Shang,  Guangtao Wang,  Peng Qi, and  Jing Huang

   In Association of Computational Linguistics (ACL), 2022

   PDF

2021

1. EMNLP

   Answering Open-Domain Questions of Varying Reasoning Steps from Text

   Peng Qi*,  Haejun Lee*,  Oghenetegiri "TG" Sido*, and  Christopher D. Manning

   In Empirical Methods for Natural Language Processing (EMNLP), 2021

   PDF Code Poster Website
2. AKBC

   Open Temporal Relation Extraction for Question Answering

   Chao Shang,  Peng Qi,  Guangtao Wang,  Jing Huang,  Youzheng Wu, and  Bowen Zhou

   In 3rd Conference on Automated Knowledge Base Construction, 2021

   PDF
3. RepL4NLP

   Entity and Evidence Guided Document-Level Relation Extraction

   Kevin Huang,  Peng Qi,  Guangtao Wang,  Tengyu Ma, and  Jing Huang

   In 6th Workshop on Representation Learning for NLP (RepL4NLP) at ACL 2021, 2021

   PDF
4. TextGraphs

   Selective Attention Based Graph Convolutional Networks for Aspect-Level Sentiment Classification

   Xiaochen Hou,  Jing Huang,  Guangtao Wang,  Peng Qi,  Xiaodong He, and  Bowen Zhou

   In TextGraphs-15 at NAACL 2021, 2021

   PDF
5. arXiv

   Conversational AI Systems for Social Good: Opportunities and Challenges

   Peng Qi,  Jing Huang,  Youzheng Wu,  Xiaodong He, and  Bowen Zhou

   arXiv preprint arXiv:2105.06457, 2021

   PDF
6. JAMIA

   Biomedical and Clinical English Model Packages for the Stanza Python NLP Library

   Yuhao Zhang,  Yuhui Zhang,  Peng Qi,  Christopher D. Manning, and  Curtis P. Langlotz

   Journal of the American Medical Informatics Association, 2021

   PDF
7. NAACL

   Graph Ensemble Learning over Multiple Dependency Trees for Aspect-level Sentiment Classification

   Xiaochen Hou,  Peng Qi,  Guangtao Wang,  Rex Ying,  Jing Huang,  Xiaodong He, and  Bowen Zhou

   In 2021 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL), 2021

   PDF
8. EACL

   Do Syntax Trees Help Pre-trained Transformers Extract Information?

   Devendra Singh Sachan,  Yuhao Zhang,  Peng Qi, and  William Hamilton

   In The 16th Conference of the European Chapter of the Association for Computational Linguistics (EACL), 2021

   PDF Code

2020

1. PhD thesis

   Explainable and Efficient Knowledge Acquisition from Text

   Peng Qi

   Stanford University, 2020

   HTML PDF
2. ACL (Demo)

   Stanza: A Python Natural Language Processing Toolkit for Many Human Languages

   Peng Qi*,  Yuhao Zhang*,  Yuhui Zhang,  Jason Bolton, and  Christopher D. Manning

   In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations, 2020

   HTML PDF Video Code
3. ACL Findings

   Stay Hungry, Stay Focused: Generating Informative and Specific Questions in Information-Seeking Conversations

   Peng Qi,  Yuhao Zhang, and  Christopher D. Manning

   In Findings of the Association for Computational Linguistics: EMNLP 2020, 2020

   PDF Video Code
4. AlexaPrize

   Neural Generation Meets Real People: Towards Emotionally Engaging Mixed-Initiative Conversations

   Ashwin Paranjape*,  Abigail See*,  Kathleen Kenealy,  Haojun Li,  Amelia Hardy,  Peng Qi,  Kaushik Ram Sadagopan,  Nguyet Minh Phu,  Dilara Soylu, and  Christopher D. Manning

   In 3rd Proceedings of Alexa Prize (Alexa Prize 2019), 2020

   Awarded PDF

   Second place in the Alexa Prize Grand Challenge

2019

1. EMNLP-IJCNLP

   Answering Complex Open-domain Questions Through Iterative Query Generation

   Peng Qi,  Xiaowen Lin*,  Leo Mehr*,  Zijian Wang*, and  Christopher D. Manning

   In 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), 2019

   PDF Blog Code Poster

2018

1. ACL

   Sharp Nearby, Fuzzy Far Away: How Neural Language Models Use Context

   Urvashi Khandelwal,  He He,  Peng Qi, and  Dan Jurafsky

   Association for Computational Linguistics (ACL), 2018

   PDF Code
2. CoNLL

   Universal Dependency Parsing from Scratch

   Peng Qi*,  Timothy Dozat*,  Yuhao Zhang*, and  Christopher D. Manning

   In Proceedings of the CoNLL 2018 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies, Oct 2018

   HTML PDF Code Poster
3. EMNLP

   HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering

   Zhilin Yang*,  Peng Qi*,  Saizheng Zhang*,  Yoshua Bengio,  William W. Cohen,  Ruslan Salakhutdinov, and  Christopher D. Manning

   In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), Oct 2018

   PDF Blog
4. EMNLP

   Graph Convolution over Pruned Dependency Trees Improves Relation Extraction

   Yuhao Zhang*,  Peng Qi*, and  Christopher D. Manning

   In Empirical Methods in Natural Language Processing (EMNLP), Oct 2018

   PDF Code Poster

2017

1. CoNLL

   Stanford’s Graph-based Neural Dependency Parser at the CoNLL 2017 Shared Task

   Timothy Dozat,  Peng Qi, and  Christopher D. Manning

   In Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies, Aug 2017

   Awarded Abs PDF Code

   1st place

   This paper describes the neural dependency parser submitted by Stanford to the CoNLL 2017 Shared Task on parsing Universal Dependencies. Our system uses relatively simple LSTM networks to produce part of speech tags and labeled dependency parses from segmented and tokenized sequences of words. In order to address the rare word problem that abounds in languages with complex morphology, we include a character-based word representation that uses an LSTM to produce embeddings from sequences of characters. Our system was ranked first according to all five relevant metrics for the system: UPOS tagging (93.09%), XPOS tagging (82.27%), unlabeled attachment score (81.30%), labeled attachment score (76.30%), and content word labeled attachment score (72.57%).

2. TAC

   Stanford at TAC KBP 2017: Building a Trilingual Relational Knowledge Graph.

   Arun Tejasvi Chaganty,  Ashwin Paranjape,  Jason Bolton,  Matthew Lamm,  Jinhao Lei,  Abigail See,  Kevin Clark,  Yuhao Zhang,  Peng Qi, and  Christopher D Manning

   In Text Analysis Conference (TAC) Proceedings, Aug 2017

   PDF
3. ACL

   Arc-swift: A Novel Transition System for Dependency Parsing

   Peng Qi, and  Christopher D. Manning

   In Association for Computational Linguistics (ACL), Aug 2017

   PDF Code Slides

2016

1. CS&L

   Building DNN Acoustic Models for Large Vocabulary Speech Recognition

   Andrew L Maas,  Peng Qi,  Ziang Xie,  Awni Y Hannun,  Christopher T Lengerich,  Daniel Jurafsky, and  Andrew Y Ng

   Computer Speech & Language, Aug 2016

   PDF
2. TAC

   Stanford at TAC KBP 2016: Sealing Pipeline Leaks and Understanding Chinese

   Yuhao Zhang,  Arun Chaganty,  Ashwin Paranjape,  Danqi Chen,  Jason Bolton,  Peng Qi, and  Christopher D Manning

   In Text Analysis Conference (TAC), Aug 2016

   PDF

2014

1. Neurocomputing

   Modeling response properties of V2 neurons using a hierarchical K-means model

   Xiaolin Hu,  Jianwei Zhang,  Peng Qi, and  Bo Zhang

   Neurocomputing, Aug 2014

   PDF
2. Neural Comp.

   Learning nonlinear statistical regularities in natural images by modeling the outer product of image intensities

   Peng Qi, and  Xiaolin Hu

   Neural computation, Aug 2014

   PDF Code

2013

1. ICACI

   Modeling Outer Products of Features for Image Classification

   Peng Qi,  Shuochen Su, and  Xiaolin Hu

   In Advanced Computational Intelligence (ICACI), 2013 Sixth International Conference on, Aug 2013

   PDF

2012

1. ICONIP

   Hierarchical K-Means Algorithm for Modeling Visual Area V2 Neurons

   Xiaolin Hu,  Peng Qi, and  Bo Zhang

   In Neural Information Processing, Aug 2012

   10.1007/978-3-642-34487-9_46

   Awarded HTML PDF

   Best Paper Award