113 citations · 336 across the 20 of their papers we have counts for
23 papers
Dancing in Chains: Reconciling Instruction Following and Faithfulness in Language Models
Zhengxuan Wu, Yuhao Zhang, Peng Qi +6
Modern language models (LMs) need to follow human instructions while being faithful; yet, they often fail to achieve both. Here, we provide concrete evidence of a trade-off between…
RAG-QA Arena: Evaluating Domain Robustness for Long-form Retrieval Augmented Question Answering
Rujun Han, Yuhao Zhang, Peng Qi +6
Question answering based on retrieval augmented generation (RAG-QA) is an important research topic in NLP and has a wide range of real-world applications. However, most existing da…
Tokenization Consistency Matters for Generative Models on Extractive NLP Tasks
Kaiser Sun, Peng Qi, Yuhao Zhang +3
Generative models have been widely applied to solve extractive tasks, where parts of the input is extracted to form the desired output, and achieved significant success. For exampl…
Language Agnostic Multilingual Information Retrieval with Contrastive Learning
Xiyang Hu, Xinchi Chen, Peng Qi +4
Multilingual information retrieval (IR) is challenging since annotated training data is costly to obtain in many languages. We present an effective method to train multilingual IR…
Neural Generation Meets Real People: Building a Social, Informative Open-Domain Dialogue Agent
Ethan A. Chi, Ashwin Paranjape, Abigail See +18
We present Chirpy Cardinal, an open-domain social chatbot. Aiming to be both informative and conversational, our bot chats with users in an authentic, emotionally intelligent way.…
Trustworthy AI: From Principles to Practices
Bo Li, Peng Qi, Bo Liu +5
The rapid development of Artificial Intelligence (AI) technology has enabled the deployment of various systems based on it. However, many current AI systems are found vulnerable to…
Conversational AI Systems for Social Good: Opportunities and Challenges
Peng Qi, Jing Huang, Youzheng Wu +2
Conversational artificial intelligence (ConvAI) systems have attracted much academic and commercial attention recently, making significant progress on both fronts. However, little…
Graph Ensemble Learning over Multiple Dependency Trees for Aspect-level Sentiment Classification
Xiaochen Hou, Peng Qi, Guangtao Wang +4
Recent work on aspect-level sentiment classification has demonstrated the efficacy of incorporating syntactic structures such as dependency trees with graph neural networks(GNN), b…
Answering Open-Domain Questions of Varying Reasoning Steps from Text
Peng Qi, Haejun Lee, Oghenetegiri "TG" Sido +1
We develop a unified system to answer directly from text open-domain questions that may require a varying number of retrieval steps. We employ a single multi-task transformer model…
Neural Generation Meets Real People: Towards Emotionally Engaging Mixed-Initiative Conversations
Ashwin Paranjape, Abigail See, Kathleen Kenealy +7
We present Chirpy Cardinal, an open-domain dialogue agent, as a research platform for the 2019 Alexa Prize competition. Building an open-domain socialbot that talks to real people…
Entity and Evidence Guided Relation Extraction for DocRED
Kevin Huang, Guangtao Wang, Tengyu Ma +1
Document-level relation extraction is a challenging task which requires reasoning over multiple sentences in order to predict relations in a document. In this paper, we pro-pose a…
Do Syntax Trees Help Pre-trained Transformers Extract Information?
Devendra Singh Sachan, Yuhao Zhang, Peng Qi +1
Much recent work suggests that incorporating syntax information from dependency trees can improve task-specific transformer models. However, the effect of incorporating dependency…
Biomedical and Clinical English Model Packages in the Stanza Python NLP Library
Yuhao Zhang, Yuhui Zhang, Peng Qi +2
We introduce biomedical and clinical English model packages for the Stanza Python NLP library. These packages offer accurate syntactic analysis and named entity recognition capabil…
Stanza: A Python Natural Language Processing Toolkit for Many Human Languages
Peng Qi, Yuhao Zhang, Yuhui Zhang +2
We introduce Stanza, an open-source Python natural language processing toolkit supporting 66 human languages. Compared to existing widely used toolkits, Stanza features a language-…
Stay Hungry, Stay Focused: Generating Informative and Specific Questions in Information-Seeking Conversations
Peng Qi, Yuhao Zhang, Christopher D. Manning
We investigate the problem of generating informative questions in information-asymmetric conversations. Unlike previous work on question generation which largely assumes knowledge…
Answering Complex Open-domain Questions Through Iterative Query Generation
Peng Qi, Xiaowen Lin, Leo Mehr +2
It is challenging for current one-step retrieve-and-read question answering (QA) systems to answer questions like "Which novel by the author of 'Armada' will be adapted as a featur…
Selective Attention Based Graph Convolutional Networks for Aspect-Level Sentiment Classification
Xiaochen Hou, Jing Huang, Guangtao Wang +2
Aspect-level sentiment classification aims to identify the sentiment polarity towards a specific aspect term in a sentence. Most current approaches mainly consider the semantic inf…
Universal Dependency Parsing from Scratch
Peng Qi, Timothy Dozat, Yuhao Zhang +1
This paper describes Stanford's system at the CoNLL 2018 UD Shared Task. We introduce a complete neural pipeline system that takes raw text as input, and performs all tasks require…
Graph Convolution over Pruned Dependency Trees Improves Relation Extraction
Yuhao Zhang, Peng Qi, Christopher D. Manning
Dependency trees help relation extraction models capture long-range relations between words. However, existing dependency-based models either neglect crucial information (e.g., neg…
HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering
Zhilin Yang, Peng Qi, Saizheng Zhang +4
Existing question answering (QA) datasets fail to train QA systems to perform complex reasoning and provide explanations for answers. We introduce HotpotQA, a new dataset with 113k…
Sharp Nearby, Fuzzy Far Away: How Neural Language Models Use Context
Urvashi Khandelwal, He He, Peng Qi +1
We know very little about how neural language models (LM) use prior linguistic context. In this paper, we investigate the role of context in an LSTM LM, through ablation studies. S…
Arc-swift: A Novel Transition System for Dependency Parsing
Peng Qi, Christopher D. Manning
Transition-based dependency parsers often need sequences of local shift and reduce operations to produce certain attachments. Correct individual decisions hence require global info…
Building DNN Acoustic Models for Large Vocabulary Speech Recognition
Andrew L. Maas, Peng Qi, Ziang Xie +4
Deep neural networks (DNNs) are now a central component of nearly all state-of-the-art speech recognition systems. Building neural network acoustic models requires several design d…