Dataset and Neural Recurrent Sequence Labeling Model for Open-Domain Factoid Question Answering (2016-07-21T00:00:00.000000Z)

TL;DR

This work casts neural QA as a sequence labeling problem and proposes an end-to-end sequence labeling model, which overcomes all the above challenges and outperforms the baselines significantly on WebQA.

Abstract

While question answering (QA) with neural network, i.e. neural QA, has achieved promising results in recent years, lacking of large scale real-word QA dataset is still a challenge for developing and evaluating neural QA system. To alleviate this problem, we propose a large scale human annotated real-world QA dataset WebQA with more than 42k questions and 556k evidences. As existing neural QA methods resolve QA either as sequence generation or classification/ranking problem, they face challenges of expensive softmax computation, unseen answers handling or separate candidate answer generation component. In this work, we cast neural QA as a sequence labeling problem and propose an end-to-end sequence labeling model, which overcomes all the above challenges. Experimental results on WebQA show that our model outperforms the baselines significantly with an F1 score of 74.69% with word-based input, and the performance drops only 3.72 F1 points with more challenging character-based input.

Authors

Peng Li

9 papers

Wei Li

1 papers

Zhen He

1 papers

TL;DR

Abstract

Authors

References35 items

Attention-over-Attention Neural Networks for Reading Comprehension

Separating Answers from Queries for Neural Reading Comprehension

A Thorough Examination of the CNN/Daily Mail Reading Comprehension Task

Iterative Alternating Neural Attention for Machine Reading

Gated-Attention Readers for Text Comprehension

Machine Comprehension Based on Learning to Rank

Generating Factoid Questions With Recurrent Neural Networks: The 30M Factoid Question-Answer Corpus

Text Understanding with the Attention Sum Reader Network

Attentive Pooling Networks

Attention-Based Convolutional Neural Network for Machine Comprehension

Deep Residual Learning for Image Recognition

The Goldilocks Principle: Reading Children's Books with Explicit Memory Representations

Bidirectional LSTM-CRF Models for Sequence Tagging

Question Answering over Freebase with Multi-Column Convolutional Neural Networks

End-to-end learning of semantic role labeling using recurrent neural networks

Ask Me Anything: Dynamic Memory Networks for Natural Language Processing

Teaching Machines to Read and Comprehend

Large-scale Simple Question Answering with Memory Networks

End-To-End Memory Networks

Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks

Neural Turing Machines

Memory Networks

A Neural Network for Factoid Question Answering over Paragraphs

Neural Machine Translation by Jointly Learning to Align and Translate

Semantic Parsing for Single-Relation Question Answering

Reasoning With Neural Tensor Networks for Knowledge Base Completion

Semantic Parsing on Freebase from Question-Answer Pairs

Generating Sequences With Recurrent Neural Networks

Large-scale Semantic Parsing via Schema Matching and Lexicon Extension

Answer Extraction as Sequence Tagging with Tree Edit Distance

Improving neural networks by preventing co-adaptation of feature detectors

TREC: An overview

A Neural Probabilistic Language Model

Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data

Gradient-based learning applied to document recognition

Field of Study

Journal Information

Name

Volume

Venue Information

Name

Type

URL

Alternate Names