Nan Duan

Improving Question Answering by Commonsense-Based Pre-Training

2018 · arXiv (Cornell University)

Although neural network approaches achieve remarkable success on a variety of NLP tasks, many of them struggle to answer questions that require commonsense knowledge. We believe the main reason is the lack of commonsense \mbox{connections} …

Unicoder: A Universal Language Encoder by Pre-training with Multiple Cross-lingual Tasks

2019 · arXiv (Cornell University)

Haoyang Huang, Yaobo Liang, Nan Duan, Ming Gong, Linjun Shou, Daxin Jiang, Ming Zhou. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language …

Multi-Task Learning for Conversational Question Answering over a Large-Scale Knowledge Base

2019 · arXiv (Cornell University)

We consider the problem of conversational question answering over a large-scale knowledge base. To handle huge entity vocabulary of a large-scale knowledge base, recent neural semantic parsing based approaches usually decompose the task into several …

No Answer is Better Than Wrong Answer: A Reflection Model for Document Level Machine Reading Comprehension

2020

The Natural Questions (NQ) benchmark set brings new challenges to Machine Reading Comprehension: the answers are not only at different levels of granularity (long and short), but also of richer types (including no-answer, yes/no, single-span …

ReACC: A Retrieval-Augmented Code Completion Framework

2022 · arXiv (Cornell University)

Code completion, which aims to predict the following code token(s) according to the code context, can improve the productivity of software development. Recent work has proved that statistical language modeling with transformers can greatly improve …

ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving

2023 · arXiv (Cornell University)

Large language models have made significant progress in various language tasks, yet they still struggle with complex mathematics. In this paper, we propose ToRA a series of Tool-integrated Reasoning Agents designed to solve challenging mathematical …

Intervention-Based Alignment of Code Search with Execution Feedback

2023

One of the fundamental goals in code search is to retrieve a functionally correct code for a given natural language query. As annotating for correctness requires executing test cases (i.e. obtaining execution feedback), existing code …

Constraint-Based Question Answering with Knowledge Graph

2016 · International Conference on Computational Linguistics

WebQuestions and SimpleQuestions are two benchmark data-sets commonly used in recent knowledge-based question answering (KBQA) work. Most questions in them are ‘simple’ questions which can be answered based on a single relation in the knowledge …

Question Answering and Question Generation as Dual Tasks

2017 · arXiv (Cornell University)

We study the problem of joint question answering (QA) and question generation (QG) in this paper. Our intuition is that QA and QG have intrinsic connections and these two tasks could improve each other. On …

Question Generation for Question Answering

2017

This paper presents how to generate questions from given passages using neural networks, where large scale QA pairs are automatically crawled and processed from Community-QA website, and used as training data. The contribution of the …

Dialog-to-action: conversational question answering over a large-scale knowledge base

2018 · Neural Information Processing Systems

We present an approach to map utterances in conversation to logical forms, which will be executed on a large-scale knowledge base. To handle enormous ellipsis phenomena in conversation, we introduce dialog memory management to manipulate …

Asking Clarification Questions in Knowledge-Based Question Answering

2019

Jingjing Xu, Yuechen Wang, Duyu Tang, Nan Duan, Pengcheng Yang, Qi Zeng, Ming Zhou, Xu Sun. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on …

Graph-Based Reasoning over Heterogeneous External Knowledge for Commonsense Question Answering

2020 · Proceedings of the AAAI Conference on Artificial Intelligence

Commonsense question answering aims to answer questions which require background knowledge that is not explicitly expressed in the question. The key challenge is how to obtain evidence from external knowledge and make predictions based on …

Graph Neural News Recommendation with Unsupervised Preference Disentanglement

2020

With the explosion of news information, personalized news recommendation has become very important for users to quickly find their interested contents. Most existing methods usually learn the representations of users and news from news contents …

CodeBERT: A Pre-Trained Model for Programming and Natural Languages

2020

Zhangyin Feng, Daya Guo, Duyu Tang, Nan Duan, Xiaocheng Feng, Ming Gong, Linjun Shou, Bing Qin, Ting Liu, Daxin Jiang, Ming Zhou. Findings of the Association for Computational Linguistics: EMNLP 2020. 2020.

XGLUE: A New Benchmark Dataset for Cross-lingual Pre-training, Understanding and Generation

2020

Yaobo Liang, Nan Duan, Yeyun Gong, Ning Wu, Fenfei Guo, Weizhen Qi, Ming Gong, Linjun Shou, Daxin Jiang, Guihong Cao, Xiaodong Fan, Ruofei Zhang, Rahul Agrawal, Edward Cui, Sining Wei, Taroon Bharti, Ying Qiao, Jiun-Hung …

K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapters

2021

We study the problem of injecting knowledge into large pre-trained models like BERT and RoBERTa. Existing methods typically update the original parameters of pre-trained models when injecting knowledge. However, when multiple kinds of knowledge are …