439 citations · 1.1k across the 29 of their papers we have counts for
29 papers
Augmenting Policy Learning with Routines Discovered from a Single Demonstration
Zelin Zhao, Chuang Gan, Jiajun Wu +2
Humans can abstract prior knowledge from very little data and use it to boost skill learning. In this paper, we propose routine-augmented policy learning (RAPL), which discovers ro…
Interactive Fiction Game Playing as Multi-Paragraph Reading Comprehension with Reinforcement Learning
Xiaoxiao Guo, Mo Yu, Yupeng Gao +3
Interactive Fiction (IF) games with real human-written natural language texts provide a new natural evaluation for language understanding techniques. In contrast to previous text g…
Frustratingly Hard Evidence Retrieval for QA Over Books
Xiangyang Mou, Mo Yu, Bingsheng Yao +4
A lot of progress has been made to improve question answering (QA) in recent years, but the special problem of QA over narrative book stories has not been explored in-depth. We for…
Simple yet Effective Bridge Reasoning for Open-Domain Multi-Hop Question Answering
Wenhan Xiong, Mo Yu, Xiaoxiao Guo +4
A key challenge of multi-hop question answering (QA) in the open-domain setting is to accurately retrieve the supporting passages from a large corpus. Existing work on open-domain…
Do Multi-hop Readers Dream of Reasoning Chains?
Haoyu Wang, Mo Yu, Xiaoxiao Guo +3
General Question Answering (QA) systems over texts require the multi-hop reasoning capability, i.e. the ability to reason with information collected from multiple passages to deriv…
Multi-step Entity-centric Information Retrieval for Multi-Hop Question Answering
Ameya Godbole, Dilip Kavarthapu, Rajarshi Das +8
Multi-hop question answering (QA) requires an information retrieval (IR) system that can find \emph{multiple} supporting evidence needed to answer the question, making the retrieva…
Meta Reasoning over Knowledge Graphs
Hong Wang, Wenhan Xiong, Mo Yu +3
The ability to reason over learned knowledge is an innate ability for humans and humans can easily master new reasoning rules with only a few demonstrations. While most existing st…
TWEETQA: A Social Media Focused Question Answering Dataset
Wenhan Xiong, Jiawei Wu, Hong Wang +5
With social media becoming increasingly pop-ular on which lots of news and real-time eventsare reported, developing automated questionanswering systems is critical to the effective…
Self-Supervised Learning for Contextualized Extractive Summarization
Hong Wang, Xin Wang, Wenhan Xiong +4
Existing models for extractive summarization are usually trained from scratch with a cross-entropy loss, which does not explicitly capture the global context at the document level.…
Improving Question Answering over Incomplete KBs with Knowledge-Aware Reader
Wenhan Xiong, Mo Yu, Shiyu Chang +2
We propose a new end-to-end question answering model, which learns to aggregate answer evidence from an incomplete knowledge base (KB) and a set of retrieved text snippets. Under t…
Fashion IQ: A New Dataset Towards Retrieving Images by Natural Language Feedback
Hui Wu, Yupeng Gao, Xiaoxiao Guo +4
Conversational interfaces for the detail-oriented retail fashion domain are more natural, expressive, and user friendly than classical keyword-based search interfaces. In this pape…
A Hybrid Approach with Optimization and Metric-based Meta-Learner for Few-Shot Learning
Duo Wang, Yu Cheng, Mo Yu +2
Few-shot learning aims to learn classifiers for new classes with only a few training examples per class. Most existing few-shot learning approaches belong to either metric-based me…
Sentence Embedding Alignment for Lifelong Relation Extraction
Hong Wang, Wenhan Xiong, Mo Yu +3
Conventional approaches to relation extraction usually require a fixed set of pre-defined relations. Such requirement is hard to meet in many real applications, especially when new…
Hybrid Reinforcement Learning with Expert State Sequences
Xiaoxiao Guo, Shiyu Chang, Mo Yu +2
Existing imitation learning approaches often require that the complete demonstration data, including sequences of actions and states, are available. In this paper, we consider a mo…
Imposing Label-Relational Inductive Bias for Extremely Fine-Grained Entity Typing
Wenhan Xiong, Jiawei Wu, Deren Lei +4
Existing entity typing systems usually exploit the type hierarchy provided by knowledge base (KB) schema to model label correlations and thus improve the overall performance. Such…
Extracting Multiple-Relations in One-Pass with Pre-Trained Transformers
Haoyu Wang, Ming Tan, Mo Yu +5
Most approaches to extraction multiple relations from a paragraph require multiple passes over the paragraph. In practice, multiple passes are computationally expensive and this ma…
Few-shot Learning with Meta Metric Learners
Yu Cheng, Mo Yu, Xiaoxiao Guo +1
Few-shot Learning aims to learn classifiers for new classes with only a few training examples per class. Existing meta-learning or metric-learning based few-shot learning approache…
One-Shot Relational Learning for Knowledge Graphs
Wenhan Xiong, Mo Yu, Shiyu Chang +2
Knowledge graphs (KGs) are the key components of various natural language processing applications. To further expand KGs' coverage, previous studies on knowledge graph completion u…
Scheduled Policy Optimization for Natural Language Communication with Intelligent Agents
Wenhan Xiong, Xiaoxiao Guo, Mo Yu +3
We investigate the task of learning to follow natural language instructions by jointly reasoning with visual observations and language inputs. In contrast to existing methods which…
Diverse Few-Shot Text Classification with Multiple Metrics
Mo Yu, Xiaoxiao Guo, Jinfeng Yi +6
We study few-shot learning in natural language domains. Compared to many existing works that apply either metric-based or optimization-based meta-learning to image domain with low…
Evidence Aggregation for Answer Re-Ranking in Open-Domain Question Answering
Shuohang Wang, Mo Yu, Jing Jiang +7
A popular recent approach to answering open-domain questions is to first search for question-related passages and then apply reading comprehension models to extract answers. Existi…
Eigenoption Discovery through the Deep Successor Representation
Marlos C. Machado, Clemens Rosenbaum, Xiaoxiao Guo +3
Options in reinforcement learning allow agents to hierarchically decompose a task into subtasks, having the potential to speed up learning and planning. However, autonomously learn…
R: Reinforced Reader-Ranker for Open-Domain Question Answering
Shuohang Wang, Mo Yu, Xiaoxiao Guo +7
In recent years researchers have achieved considerable success applying neural network methods to question answering (QA). These approaches have achieved state of the art results i…
Robust Task Clustering for Deep Many-Task Learning
Mo Yu, Xiaoxiao Guo, Jinfeng Yi +5
We investigate task clustering for deep-learning based multi-task and few-shot learning in a many-task setting. We propose a new method to measure task similarities with cross-task…