Search Results for author: Mo Yu

Found 107 papers, 61 papers with code

Timeline Summarization based on Event Graph Compression via Time-Aware Optimal Transport

1 code implementation EMNLP 2021 Manling Li, Tengfei Ma, Mo Yu, Lingfei Wu, Tian Gao, Heng Ji, Kathleen McKeown

Timeline Summarization identifies major events from a news collection and describes them following temporal order, with key dates tagged.

Timeline Summarization

Personality Understanding of Fictional Characters during Book Reading

no code implementations17 May 2023 Mo Yu, Jiangnan Li, Shunyu Yao, Wenjie Pang, Xiaochen Zhou, Zhou Xiao, Fandong Meng, Jie zhou

As readers engage with a story, their understanding of a character evolves based on new events and information; and multiple fine-grained aspects of personalities can be perceived.

Towards Coherent Image Inpainting Using Denoising Diffusion Implicit Models

1 code implementation6 Apr 2023 Guanhua Zhang, Jiabao Ji, Yang Zhang, Mo Yu, Tommi Jaakkola, Shiyu Chang

COPAINT also uses the Bayesian framework to jointly modify both revealed and unrevealed regions, but approximates the posterior distribution in a way that allows the errors to gradually drop to zero throughout the denoising steps, thus strongly penalizing any mismatches with the reference image.

Denoising Image Inpainting

Can Large Language Models Play Text Games Well? Current State-of-the-Art and Open Questions

no code implementations6 Apr 2023 Chen Feng Tsai, Xiaochen Zhou, Sierra S. Liu, Jing Li, Mo Yu, Hongyuan Mei

Large language models (LLMs) such as ChatGPT and GPT-4 have recently demonstrated their remarkable abilities of communicating with human users.

Explicit Planning Helps Language Models in Logical Reasoning

1 code implementation28 Mar 2023 Hongyu Zhao, Kangrui Wang, Mo Yu, Hongyuan Mei

In this paper, we propose a novel system that uses language models to perform multi-step logical reasoning.

Logical Reasoning Multiple-choice +1

MetaNO: How to Transfer Your Knowledge on Learning Hidden Physics

no code implementations28 Jan 2023 Lu Zhang, Huaiqian You, Tian Gao, Mo Yu, Chung-Hao Lee, Yue Yu

Gradient-based meta-learning methods have primarily been applied to classical machine learning tasks such as image classification.

Image Classification Meta-Learning

Few-Shot Character Understanding in Movies as an Assessment to Meta-Learning of Theory-of-Mind

1 code implementation9 Nov 2022 Mo Yu, Yisi Sang, Kangsheng Pu, Zekai Wei, Han Wang, Jing Li, Yue Yu, Jie zhou

When reading a story, humans can rapidly understand new fictional characters with a few observations, mainly by drawing analogy to fictional and real people they met before in their lives.

Meta-Learning Metric Learning

Question-Interlocutor Scope Realized Graph Modeling over Key Utterances for Dialogue Reading Comprehension

no code implementations26 Oct 2022 Jiangnan Li, Mo Yu, Fandong Meng, Zheng Lin, Peng Fu, Weiping Wang, Jie zhou

Although these tasks are effective, there are still urging problems: (1) randomly masking speakers regardless of the question cannot map the speaker mentioned in the question to the corresponding speaker in the dialogue, and ignores the speaker-centric nature of utterances.

Reading Comprehension

JECC: Commonsense Reasoning Tasks Derived from Interactive Fictions

1 code implementation18 Oct 2022 Mo Yu, Yi Gu, Xiaoxiao Guo, Yufei Feng, Xiaodan Zhu, Michael Greenspan, Murray Campbell, Chuang Gan

Hence, in order to achieve higher performance on our tasks, models need to effectively utilize such functional knowledge to infer the outcomes of actions, rather than relying solely on memorizing facts.

Reading Comprehension

Revisiting the Roles of "Text" in Text Games

no code implementations15 Oct 2022 Yi Gu, Shunyu Yao, Chuang Gan, Joshua B. Tenenbaum, Mo Yu

Text games present opportunities for natural language understanding (NLU) methods to tackle reinforcement learning (RL) challenges.

Natural Language Understanding Passage Retrieval +2

Learning as Conversation: Dialogue Systems Reinforced for Information Acquisition

1 code implementation NAACL 2022 Pengshan Cai, Hui Wan, Fei Liu, Mo Yu, Hong Yu, Sachindra Joshi

We propose novel AI-empowered chat bots for learning as conversation where a user does not read a passage but gains information and knowledge through conversation with a teacher bot.

A Survey of Machine Narrative Reading Comprehension Assessments

no code implementations30 Apr 2022 Yisi Sang, Xiangyang Mou, Jing Li, Jeffrey Stanton, Mo Yu

As the body of research on machine narrative comprehension grows, there is a critical need for consideration of performance assessment strategies as well as the depth and scope of different benchmark tasks.

Reading Comprehension

FaithDial: A Faithful Benchmark for Information-Seeking Dialogue

1 code implementation22 Apr 2022 Nouha Dziri, Ehsan Kamalloo, Sivan Milton, Osmar Zaiane, Mo Yu, Edoardo M. Ponti, Siva Reddy

The goal of information-seeking dialogue is to respond to seeker queries with natural language utterances that are grounded on knowledge sources.

Dialogue Generation

On the Origin of Hallucinations in Conversational Models: Is it the Datasets or the Models?

1 code implementation NAACL 2022 Nouha Dziri, Sivan Milton, Mo Yu, Osmar Zaiane, Siva Reddy

Knowledge-grounded conversational models are known to suffer from producing factually invalid statements, a phenomenon commonly called hallucination.

TVShowGuess: Character Comprehension in Stories as Speaker Guessing

1 code implementation NAACL 2022 Yisi Sang, Xiangyang Mou, Mo Yu, Shunyu Yao, Jing Li, Jeffrey Stanton

We propose a new task for assessing machines' skills of understanding fictional characters in narrative stories.

Probing Script Knowledge from Pre-Trained Models

no code implementations16 Apr 2022 Zijian Jin, Xingyu Zhang, Mo Yu, Lifu Huang

Script knowledge is critical for humans to understand the broad daily tasks and routine activities in the world.

Story Generation

The Art of Prompting: Event Detection based on Type Specific Prompts

no code implementations14 Apr 2022 Sijia Wang, Mo Yu, Lifu Huang

We compare various forms of prompts to represent event types and develop a unified framework to incorporate the event type specific prompts for supervised, few-shot, and zero-shot event detection.

Event Detection Vocal Bursts Type Prediction

Linking Emergent and Natural Languages via Corpus Transfer

1 code implementation ICLR 2022 Shunyu Yao, Mo Yu, Yang Zhang, Karthik R Narasimhan, Joshua B. Tenenbaum, Chuang Gan

In this work, we propose a novel way to establish such a link by corpus transfer, i. e. pretraining on a corpus of emergent language for downstream natural language tasks, which is in contrast to prior work that directly transfers speaker and listener parameters.

Disentanglement Image Captioning +1

Efficient Long Sequence Encoding via Synchronization

no code implementations15 Mar 2022 Xiangyang Mou, Mo Yu, Bingsheng Yao, Lifu Huang

Pre-trained Transformer models have achieved successes in a wide range of NLP tasks, but are inefficient when dealing with long input sequences.

StoryBuddy: A Human-AI Collaborative Chatbot for Parent-Child Interactive Storytelling with Flexible Parental Involvement

1 code implementation13 Feb 2022 Zheng Zhang, Ying Xu, Yanhao Wang, Bingsheng Yao, Daniel Ritchie, Tongshuang Wu, Mo Yu, Dakuo Wang, Toby Jia-Jun Li

Despite its benefits for children's skill development and parent-child bonding, many parents do not often engage in interactive storytelling by having story-related dialogues with their child due to limited availability or challenges in coming up with appropriate questions.


Understanding Interlocking Dynamics of Cooperative Rationalization

1 code implementation NeurIPS 2021 Mo Yu, Yang Zhang, Shiyu Chang, Tommi S. Jaakkola

The selection mechanism is commonly integrated into the model itself by specifying a two-component cascaded system consisting of a rationale generator, which makes a binary selection of the input features (which is the rationale), and a predictor, which predicts the output based only on the selected features.

Hard Attention

Query and Extract: Refining Event Extraction as Type-oriented Binary Decoding

no code implementations Findings (ACL) 2022 Sijia Wang, Mo Yu, Shiyu Chang, Lichao Sun, Lifu Huang

Event extraction is typically modeled as a multi-class classification problem where event types and argument roles are treated as atomic symbols.

Event Extraction Multi-class Classification +2

Feudal Reinforcement Learning by Reading Manuals

no code implementations13 Oct 2021 Kai Wang, Zhonghao Wang, Mo Yu, Humphrey Shi

The manager agent is a multi-hop plan generator dealing with high-level abstract information and generating a series of sub-goals in a backward manner.

reinforcement-learning Reinforcement Learning (RL)

Narrative Question Answering with Cutting-Edge Open-Domain QA Techniques: A Comprehensive Study

3 code implementations7 Jun 2021 Xiangyang Mou, Chenghao Yang, Mo Yu, Bingsheng Yao, Xiaoxiao Guo, Saloni Potdar, Hui Su

Recent advancements in open-domain question answering (ODQA), i. e., finding answers from large open-domain corpus like Wikipedia, have led to human-level performance on many datasets.

Open-Domain Question Answering

CASS: Towards Building a Social-Support Chatbot for Online Health Community

2 code implementations4 Jan 2021 Liuping Wang, Dakuo Wang, Feng Tian, Zhenhui Peng, Xiangmin Fan, Zhan Zhang, Shuai Ma, Mo Yu, Xiaojuan Ma, Hongan Wang

Chatbots systems, despite their popularity in today's HCI and CSCW research, fall short for one of the two reasons: 1) many of the systems use a rule-based dialog flow, thus they can only respond to a limited number of pre-defined inputs with pre-scripted responses; or 2) they are designed with a focus on single-user scenarios, thus it is unclear how these systems may affect other users or the community.


Benchmarking Commercial Intent Detection Services with Practice-Driven Evaluations

1 code implementation NAACL 2021 Haode Qi, Lin Pan, Atin Sood, Abhishek Shah, Ladislav Kunc, Mo Yu, Saloni Potdar

Secondly, even with large training data, the intent detection models can see a different distribution of test data when being deployed in the real world, leading to poor accuracy.

Benchmarking Goal-Oriented Dialog +1

Multilingual BERT Post-Pretraining Alignment

no code implementations NAACL 2021 Lin Pan, Chung-Wei Hang, Haode Qi, Abhishek Shah, Saloni Potdar, Mo Yu

We propose a simple method to align multilingual contextual embeddings as a post-pretraining step for improved zero-shot cross-lingual transferability of the pretrained models.

Contrastive Learning Language Modelling +1

Deriving Commonsense Inference Tasks from Interactive Fictions

no code implementations19 Oct 2020 Mo Yu, Xiaoxiao Guo, Yufei Feng, Xiaodan Zhu, Michael Greenspan, Murray Campbell

Commonsense reasoning simulates the human ability to make presumptions about our physical world, and it is an indispensable cornerstone in building general AI systems.

Reading Comprehension

MCMH: Learning Multi-Chain Multi-Hop Rules for Knowledge Graph Reasoning

no code implementations Findings of the Association for Computational Linguistics 2020 Lu Zhang, Mo Yu, Tian Gao, Yue Yu

Multi-hop reasoning approaches over knowledge graphs infer a missing relationship between entities with a multi-hop rule, which corresponds to a chain of relationships.

Knowledge Graphs

Frustratingly Hard Evidence Retrieval for QA Over Books

no code implementations WS 2020 Xiangyang Mou, Mo Yu, Bingsheng Yao, Chenghao Yang, Xiaoxiao Guo, Saloni Potdar, Hui Su

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.

Question Answering Retrieval

Invariant Rationalization

1 code implementation ICML 2020 Shiyu Chang, Yang Zhang, Mo Yu, Tommi S. Jaakkola

Selective rationalization improves neural network interpretability by identifying a small subset of input features -- the rationale -- that best explains or supports the prediction.

Differential Treatment for Stuff and Things: A Simple Unsupervised Domain Adaptation Method for Semantic Segmentation

1 code implementation CVPR 2020 Zhonghao Wang, Mo Yu, Yunchao Wei, Rogerio Feris, JinJun Xiong, Wen-mei Hwu, Thomas S. Huang, Humphrey Shi

We consider the problem of unsupervised domain adaptation for semantic segmentation by easing the domain shift between the source domain (synthetic data) and the target domain (real data) in this work.

Semantic Segmentation Unsupervised Domain Adaptation

Generalizable Resource Allocation in Stream Processing via Deep Reinforcement Learning

1 code implementation19 Nov 2019 Xiang Ni, Jing Li, Mo Yu, Wang Zhou, Kun-Lung Wu

In this paper, we present a graph-aware encoder-decoder framework to learn a generalizable resource allocation strategy that can properly distribute computation tasks of stream processing graphs unobserved from training data.

Graph Embedding graph partitioning +2

Context-Aware Conversation Thread Detection in Multi-Party Chat

no code implementations IJCNLP 2019 Ming Tan, Dakuo Wang, Yupeng Gao, Haoyu Wang, Saloni Potdar, Xiaoxiao Guo, Shiyu Chang, Mo Yu

In multi-party chat, it is common for multiple conversations to occur concurrently, leading to intermingled conversation threads in chat logs.

Do Multi-hop Readers Dream of Reasoning Chains?

1 code implementation WS 2019 Haoyu Wang, Mo Yu, Xiaoxiao Guo, Rajarshi Das, Wenhan Xiong, Tian Gao

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 derive the answer.

Question Answering

Rethinking Cooperative Rationalization: Introspective Extraction and Complement Control

2 code implementations IJCNLP 2019 Mo Yu, Shiyu Chang, Yang Zhang, Tommi S. Jaakkola

Moreover, we explicitly control the rationale complement via an adversary so as not to leave any useful information out of the selection.

A Game Theoretic Approach to Class-wise Selective Rationalization

1 code implementation NeurIPS 2019 Shiyu Chang, Yang Zhang, Mo Yu, Tommi S. Jaakkola

Selection of input features such as relevant pieces of text has become a common technique of highlighting how complex neural predictors operate.

Sentiment Analysis Sentiment Classification

An Efficient and Margin-Approaching Zero-Confidence Adversarial Attack

no code implementations ICLR 2019 Yang Zhang, Shiyu Chang, Mo Yu, Kaizhi Qian

The second paradigm, called the zero-confidence attack, finds the smallest perturbation needed to cause mis-classification, also known as the margin of an input feature.

Adversarial Attack

Simple yet Effective Bridge Reasoning for Open-Domain Multi-Hop Question Answering

no code implementations WS 2019 Wenhan Xiong, Mo Yu, Xiaoxiao Guo, Hong Wang, Shiyu Chang, Murray Campbell, William Yang Wang

To resolve this issue, we introduce a new sub-problem of open-domain multi-hop QA, which aims to recognize the bridge (\emph{i. e.}, the anchor that links to the answer passage) from the context of a set of start passages with a reading comprehension model.

Information Retrieval Multi-hop Question Answering +3

Multi-step Entity-centric Information Retrieval for Multi-Hop Question Answering

no code implementations WS 2019 Ameya Godbole, Dilip Kavarthapu, Rajarshi Das, Zhiyu Gong, Abhishek Singhal, Hamed Zamani, Mo Yu, Tian Gao, Xiaoxiao Guo, Manzil Zaheer, Andrew McCallum

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 retrieval process very challenging.

Information Retrieval Multi-hop Question Answering +2

Neural Correction Model for Open-Domain Named Entity Recognition

1 code implementation13 Sep 2019 Mengdi Zhu, Zheye Deng, Wenhan Xiong, Mo Yu, Ming Zhang, William Yang Wang

In this work, to address the low precision and recall problems, we first utilize DBpedia as the source of distant supervision to annotate abstracts from Wikipedia and design a neural correction model trained with a human-annotated NER dataset, DocRED, to correct the false entity labels.

Multi-Task Learning named-entity-recognition +4

Meta Reasoning over Knowledge Graphs

no code implementations13 Aug 2019 Hong Wang, Wenhan Xiong, Mo Yu, Xiaoxiao Guo, Shiyu Chang, William Yang Wang

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.

Few-Shot Learning Knowledge Base Completion +1

TWEETQA: A Social Media Focused Question Answering Dataset

no code implementations ACL 2019 Wenhan Xiong, Jiawei Wu, Hong Wang, Vivek Kulkarni, Mo Yu, Shiyu Chang, Xiaoxiao Guo, William Yang Wang

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-ness of many applications that rely on real-time knowledge.

Question Answering

Self-Supervised Learning for Contextualized Extractive Summarization

2 code implementations ACL 2019 Hong Wang, Xin Wang, Wenhan Xiong, Mo Yu, Xiaoxiao Guo, Shiyu Chang, William Yang Wang

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.

Extractive Summarization Self-Supervised Learning

Group Chat Ecology in Enterprise Instant Messaging: How Employees Collaborate Through Multi-User Chat Channels on Slack

no code implementations4 Jun 2019 Dakuo Wang, Haoyu Wang, Mo Yu, Zahra Ashktorab, Ming Tan

We cross-referenced 117 project teams and their team-based Slack channels and identified 57 teams that appeared in both datasets, then we built a regression model to reveal the relationship between these group communication styles and the project team performance.


Cross-lingual Knowledge Graph Alignment via Graph Matching Neural Network

1 code implementation ACL 2019 Kun Xu, Li-Wei Wang, Mo Yu, Yansong Feng, Yan Song, Zhiguo Wang, Dong Yu

Previous cross-lingual knowledge graph (KG) alignment studies rely on entity embeddings derived only from monolingual KG structural information, which may fail at matching entities that have different facts in two KGs.

Entity Embeddings Graph Attention +1

Improving Question Answering over Incomplete KBs with Knowledge-Aware Reader

2 code implementations ACL 2019 Wenhan Xiong, Mo Yu, Shiyu Chang, Xiaoxiao Guo, William Yang Wang

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.

Question Answering

Selection Bias Explorations and Debias Methods for Natural Language Sentence Matching Datasets

2 code implementations ACL 2019 Guanhua Zhang, Bing Bai, Jian Liang, Kun Bai, Shiyu Chang, Mo Yu, Conghui Zhu, Tiejun Zhao

Natural Language Sentence Matching (NLSM) has gained substantial attention from both academics and the industry, and rich public datasets contribute a lot to this process.

Selection bias

DAG-GNN: DAG Structure Learning with Graph Neural Networks

3 code implementations22 Apr 2019 Yue Yu, Jie Chen, Tian Gao, Mo Yu

Learning a faithful directed acyclic graph (DAG) from samples of a joint distribution is a challenging combinatorial problem, owing to the intractable search space superexponential in the number of graph nodes.

A Hybrid Approach with Optimization and Metric-based Meta-Learner for Few-Shot Learning

no code implementations4 Apr 2019 Duo Wang, Yu Cheng, Mo Yu, Xiaoxiao Guo, Tao Zhang

The task-specific classifiers are required to be homogeneous-structured to ease the parameter prediction, so the meta-learning approaches could only handle few-shot learning problems where the tasks share a uniform number of classes.

Few-Shot Learning General Classification +3

Hybrid Reinforcement Learning with Expert State Sequences

1 code implementation11 Mar 2019 Xiaoxiao Guo, Shiyu Chang, Mo Yu, Gerald Tesauro, Murray Campbell

The empirical results show that (1) the agents are able to leverage state expert sequences to learn faster than pure reinforcement learning baselines, (2) our tensor-based action inference model is advantageous compared to standard deep neural networks in inferring expert actions, and (3) the hybrid policy optimization objective is robust against noise in expert state sequences.

Atari Games Imitation Learning +2

Sentence Embedding Alignment for Lifelong Relation Extraction

2 code implementations NAACL 2019 Hong Wang, Wenhan Xiong, Mo Yu, Xiaoxiao Guo, Shiyu Chang, William Yang Wang

We formulate such a challenging problem as lifelong relation extraction and investigate memory-efficient incremental learning methods without catastrophically forgetting knowledge learned from previous tasks.

Incremental Learning Relation Extraction +2

Imposing Label-Relational Inductive Bias for Extremely Fine-Grained Entity Typing

1 code implementation NAACL 2019 Wenhan Xiong, Jiawei Wu, Deren Lei, Mo Yu, Shiyu Chang, Xiaoxiao Guo, William Yang Wang

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.

Entity Typing Inductive Bias

Few-shot Learning with Meta Metric Learners

no code implementations26 Jan 2019 Yu Cheng, Mo Yu, Xiaoxiao Guo, Bo-Wen Zhou

Our meta metric learning approach consists of task-specific learners, that exploit metric learning to handle flexible labels, and a meta learner, that discovers good parameters and gradient decent to specify the metrics in task-specific learners.

Few-Shot Learning Metric Learning

Learning Corresponded Rationales for Text Matching

no code implementations27 Sep 2018 Mo Yu, Shiyu Chang, Tommi S Jaakkola

The ability to predict matches between two sources of text has a number of applications including natural language inference (NLI) and question answering (QA).

Natural Language Inference Question Answering +1

Improving Reinforcement Learning Based Image Captioning with Natural Language Prior

1 code implementation EMNLP 2018 Tszhang Guo, Shiyu Chang, Mo Yu, Kun Bai

Recently, Reinforcement Learning (RL) approaches have demonstrated advanced performance in image captioning by directly optimizing the metric used for testing.

Image Captioning reinforcement-learning +1

Exploring Graph-structured Passage Representation for Multi-hop Reading Comprehension with Graph Neural Networks

no code implementations6 Sep 2018 Linfeng Song, Zhiguo Wang, Mo Yu, Yue Zhang, Radu Florian, Daniel Gildea

Multi-hop reading comprehension focuses on one type of factoid question, where a system needs to properly integrate multiple pieces of evidence to correctly answer a question.

Multi-Hop Reading Comprehension Question Answering

Deriving Machine Attention from Human Rationales

3 code implementations EMNLP 2018 Yujia Bao, Shiyu Chang, Mo Yu, Regina Barzilay

Attention-based models are successful when trained on large amounts of data.

One-Shot Relational Learning for Knowledge Graphs

1 code implementation EMNLP 2018 Wenhan Xiong, Mo Yu, Shiyu Chang, Xiaoxiao Guo, William Yang Wang

Knowledge graphs (KGs) are the key components of various natural language processing applications.

Relational Reasoning

Exploiting Rich Syntactic Information for Semantic Parsing with Graph-to-Sequence Model

1 code implementation EMNLP 2018 Kun Xu, Lingfei Wu, Zhiguo Wang, Mo Yu, Li-Wei Chen, Vadim Sheinin

Existing neural semantic parsers mainly utilize a sequence encoder, i. e., a sequential LSTM, to extract word order features while neglecting other valuable syntactic information such as dependency graph or constituent trees.

Graph-to-Sequence Semantic Parsing

Scheduled Policy Optimization for Natural Language Communication with Intelligent Agents

3 code implementations16 Jun 2018 Wenhan Xiong, Xiaoxiao Guo, Mo Yu, Shiyu Chang, Bo-Wen Zhou, William Yang Wang

We investigate the task of learning to follow natural language instructions by jointly reasoning with visual observations and language inputs.

Efficient Exploration reinforcement-learning +1

A Co-Matching Model for Multi-choice Reading Comprehension

1 code implementation ACL 2018 Shuohang Wang, Mo Yu, Shiyu Chang, Jing Jiang

Multi-choice reading comprehension is a challenging task, which involves the matching between a passage and a question-answer pair.

Reading Comprehension

NE-Table: A Neural key-value table for Named Entities

1 code implementation RANLP 2019 Janarthanan Rajendran, Jatin Ganhotra, Xiaoxiao Guo, Mo Yu, Satinder Singh, Lazaros Polymenakos

Many Natural Language Processing (NLP) tasks depend on using Named Entities (NEs) that are contained in texts and in external knowledge sources.

Goal-Oriented Dialog Question Answering +2

Faster Reinforcement Learning with Expert State Sequences

no code implementations ICLR 2018 Xiaoxiao Guo, Shiyu Chang, Mo Yu, Miao Liu, Gerald Tesauro

In this paper, we consider a realistic and more difficult sce- nario where a reinforcement learning agent only has access to the state sequences of an expert, while the expert actions are not available.

Imitation Learning reinforcement-learning +1

A Neural Method for Goal-Oriented Dialog Systems to interact with Named Entities

no code implementations ICLR 2018 Janarthanan Rajendran, Jatin Ganhotra, Xiaoxiao Guo, Mo Yu, Satinder Singh

Many goal-oriented dialog tasks, especially ones in which the dialog system has to interact with external knowledge sources such as databases, have to handle a large number of Named Entities (NEs).

Goal-Oriented Dialog Question Answering

Dilated Recurrent Neural Networks

2 code implementations NeurIPS 2017 Shiyu Chang, Yang Zhang, Wei Han, Mo Yu, Xiaoxiao Guo, Wei Tan, Xiaodong Cui, Michael Witbrock, Mark Hasegawa-Johnson, Thomas S. Huang

To provide a theory-based quantification of the architecture's advantages, we introduce a memory capacity measure, the mean recurrent length, which is more suitable for RNNs with long skip connections than existing measures.

Sequential Image Classification

Robust Task Clustering for Deep Many-Task Learning

no code implementations26 Aug 2017 Mo Yu, Xiaoxiao Guo, Jin-Feng Yi, Shiyu Chang, Saloni Potdar, Gerald Tesauro, Haoyu Wang, Bo-Wen Zhou

We propose a new method to measure task similarities with cross-task transfer performance matrix for the deep learning scenario.

Clustering Few-Shot Learning +7

Comparative Study of CNN and RNN for Natural Language Processing

4 code implementations7 Feb 2017 Wenpeng Yin, Katharina Kann, Mo Yu, Hinrich Schütze

Deep neural networks (DNN) have revolutionized the field of natural language processing (NLP).

End-to-End Answer Chunk Extraction and Ranking for Reading Comprehension

no code implementations31 Oct 2016 Yang Yu, Wei zhang, Kazi Hasan, Mo Yu, Bing Xiang, Bo-Wen Zhou

This paper proposes dynamic chunk reader (DCR), an end-to-end neural reading comprehension (RC) model that is able to extract and rank a set of answer candidates from a given document to answer questions.

Question Answering Reading Comprehension

Simple Question Answering by Attentive Convolutional Neural Network

no code implementations COLING 2016 Wenpeng Yin, Mo Yu, Bing Xiang, Bo-Wen Zhou, Hinrich Schütze

In fact selection, we match the subject entity in a fact candidate with the entity mention in the question by a character-level convolutional neural network (char-CNN), and match the predicate in that fact with the question by a word-level CNN (word-CNN).

Entity Linking Fact Selection +1

Embedding Lexical Features via Low-Rank Tensors

1 code implementation NAACL 2016 Mo Yu, Mark Dredze, Raman Arora, Matthew Gormley

Modern NLP models rely heavily on engineered features, which often combine word and contextual information into complex lexical features.

Relation Extraction

Leveraging Sentence-level Information with Encoder LSTM for Semantic Slot Filling

no code implementations EMNLP 2016 Gakuto Kurata, Bing Xiang, Bo-Wen Zhou, Mo Yu

Recurrent Neural Network (RNN) and one of its specific architectures, Long Short-Term Memory (LSTM), have been widely used for sequence labeling.

Natural Language Understanding slot-filling +1

Improved Relation Extraction with Feature-Rich Compositional Embedding Models

1 code implementation EMNLP 2015 Matthew R. Gormley, Mo Yu, Mark Dredze

We propose a Feature-rich Compositional Embedding Model (FCM) for relation extraction that is expressive, generalizes to new domains, and is easy-to-implement.

 Ranked #1 on Relation Extraction on ACE 2005 (Cross Sentence metric)

Relation Classification Word Embeddings

Learning Composition Models for Phrase Embeddings

1 code implementation TACL 2015 Mo Yu, Mark Dredze

We propose efficient unsupervised and task-specific learning objectives that scale our model to large datasets.

Language Modelling Semantic Similarity +2

Accelerated Mini-batch Randomized Block Coordinate Descent Method

no code implementations NeurIPS 2014 Tuo Zhao, Mo Yu, Yiming Wang, Raman Arora, Han Liu

When the regularization function is block separable, we can solve the minimization problems in a randomized block coordinate descent (RBCD) manner.

Sparse Learning Stochastic Optimization

Cannot find the paper you are looking for? You can Submit a new open access paper.