Attention-Based Convolutional Neural Network for Machine Comprehension

2016-02-13 · WS 2016 6 · Wenpeng Yin, Sebastian Ebert, Hinrich Schütze

Understanding open-domain text is one of the primary challenges in natural language processing (NLP). Machine comprehension benchmarks evaluate the system's ability to understand text based on the text content only. In this work, we investigate machine comprehension on MCTest, a question answering (QA) benchmark. Prior work is mainly based on feature engineering approaches. We come up with a neural network framework, named hierarchical attention-based convolutional neural network (HABCNN), to address this task without any manually designed features. Specifically, we explore HABCNN for this task by two routes, one is through traditional joint modeling of passage, question and answer, one is through textual entailment. HABCNN employs an attention mechanism to detect key phrases, key sentences and key snippets that are relevant to answering the question. Experiments show that HABCNN outperforms prior deep learning approaches by a big margin.

📄 PDF Abstract BibTeX arXiv:1602.04341

Code (0)

등록된 구현이 없습니다.

Tasks

Feature Engineering Natural Language Inference Question Answering Reading Comprehension

Comparing Attention-based Convolutional and Recurrent Neural Networks: Success and Limitations in Machine Reading Comprehension

2018-08-27 · CONLL 2018 10 · Matthias Blohm, Glorianna Jagfeld, Ekta Sood, Xiang Yu 외

We propose a machine reading comprehension model based on the compare-aggregate framework with two-staged attention that achieves state-of-the-art results on the MovieQA question answering dataset. To investigate the lim…

Machine Reading Comprehension Question Answering Reading Comprehension

Convolutional Spatial Attention Model for Reading Comprehension with Multiple-Choice Questions

2018-11-21 · Zhipeng Chen, Yiming Cui, Wentao Ma, Shijin Wang 외

Machine Reading Comprehension (MRC) with multiple-choice questions requires the machine to read given passage and select the correct answer among several candidates. In this paper, we propose a novel approach called Conv…

Machine Reading Comprehension Multiple-choice Reading Comprehension

Interpreting Attention Models with Human Visual Attention in Machine Reading Comprehension

2020-10-13 · CONLL 2020 · Ekta Sood, Simon Tannert, Diego Frassinelli, Andreas Bulling 외

While neural networks with attention mechanisms have achieved superior performance on many natural language processing tasks, it remains unclear to which extent learned attention resembles human visual attention. In this…

Machine Reading Comprehension Reading Comprehension

YNU-HPCC at Semeval-2018 Task 11: Using an Attention-based CNN-LSTM for Machine Comprehension using Commonsense Knowledge

2018-06-01 · SEMEVAL 2018 6 · Hang Yuan, Jin Wang, Xue-jie Zhang

This shared task is a typical question answering task. Compared with the normal question and answer system, it needs to give the answer to the question based on the text provided. The essence of the problem is actually r…

Question Answering Reading Comprehension

ForceReader: a BERT-based Interactive Machine Reading Comprehension Model with Attention Separation

2020-12-01 · COLING 2020 8 · Zheng Chen, Kangjian Wu

The release of BERT revolutionized the development of NLP. Various BERT-based reading comprehension models have been proposed, thus updating the performance ranking of reading comprehension tasks. However, the above BERT…