Attention-over-Attention Neural Networks for Reading Comprehension

Cui, Yiming; Chen, Zhipeng; Wei, Si; Wang, Shijin; Liu, Ting; Hu, Guoping

doi:10.18653/v1/p17-1055

Cited by 334 publications

(360 citation statements)

References 18 publications

Supporting

Mentioning

357

Contrasting

Unclassified

Order By: Relevance

“…One basic deep learning architecture for cQA is shown as Figure 1, which is used in a great many papers (Tan et al, 2015;Feng et al, 2015;Cui et al, 2016;Hu et al, 2014). The question and the comment are mapped into fixed-length word vectors.…”

Section: Methodsmentioning

confidence: 99%

FuRongWang at SemEval-2017 Task 3: Deep Neural Networks for Selecting Relevant Answers in Community Question Answering

Zhang

Cheng

Wang³

et al. 2017

Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017)

View full text Add to dashboard Cite

We describe deep neural networks frameworks in this paper to address the community question answering (cQA) ranking task (SemEval-2017 task 3). Convolutional neural networks and bi-directional long-short term memory networks are applied in our methods to extract semantic information from questions and answers (comments). In addition, in order to take the full advantage of question-comment semantic relevance, we deploy interaction layer and augmented features before calculating the similarity. The results show that our methods have the excellent effectiveness for both subtask A and subtask C.

show abstract

Section: Methodsmentioning

confidence: 99%

FuRongWang at SemEval-2017 Task 3: Deep Neural Networks for Selecting Relevant Answers in Community Question Answering

Zhang

Cheng

Wang³

et al. 2017

Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017)

View full text Add to dashboard Cite

show abstract

“…Our Chengyu cloze test task is similar to reading comprehension (Hermann et al, 2015;Cui et al, 2016;Kadlec et al, 2016;Seo et al, 2016 (Xu et al, 2010) and improve Chinese word segmentation (Chan and Chong, 2008;Sun and Xu, 2011;Wang and Xu, 2017). Chengyus differ from metaphors in other languages (Tsvetkov et al, 2014;Shutova, 2010) because they do not follow the grammatical structure and syntax of the modern Chinese.…”

Section: Related Workmentioning

confidence: 99%

Chengyu Cloze Test

Jiang¹,

Zhang²,

Huang³

et al. 2018

Proceedings of the Thirteenth Workshop on Innovative Use of NLP For Building Educational Applications

View full text Add to dashboard Cite

We present a neural recommendation model for Chengyu, which is a special type of Chinese idiom. Given a query, which is a sentence with an empty slot where the Chengyu is taken out, our model will recommend the Chengyu candidate that best fits the slot context. The main challenge lies in that the literal meaning of a Chengyu is usually very different from its figurative meaning. We propose a neural approach to incorporate the definition of each Chengyu as background knowledge. Experiments on both Chengyu cloze test and coherence checking in college entrance exams show that our system achieves 89.5% accuracy on cloze test and outperforms human experts who attended competitive universities in China. We will make all of our data sets and resources publicly available as a new benchmark for research purposes 1 .

show abstract

“…The embeddings matrix is regarded as a parameter and will be updated while training the neural network. This method is used by [35,37,42]. Another initialization method is to use publicly available pre-trained embeddings.…”

Section: Random Embeddings Vs Pre-trained Embeddingsmentioning

confidence: 99%

Chinese Medical Question Answer Matching Using End-to-End Character-Level Multi-Scale CNNs

Zhang

Wang

et al. 2017

Applied Sciences

View full text Add to dashboard Cite

This paper focuses mainly on the problem of Chinese medical question answer matching, which is arguably more challenging than open-domain question answer matching in English due to the combination of its domain-restricted nature and the language-specific features of Chinese. We present an end-to-end character-level multi-scale convolutional neural framework in which character embeddings instead of word embeddings are used to avoid Chinese word segmentation in text preprocessing, and multi-scale convolutional neural networks (CNNs) are then introduced to extract contextual information from either question or answer sentences over different scales. The proposed framework can be trained with minimal human supervision and does not require any handcrafted features, rule-based patterns, or external resources. To validate our framework, we create a new text corpus, named cMedQA, by harvesting questions and answers from an online Chinese health and wellness community. The experimental results on the cMedQA dataset show that our framework significantly outperforms several strong baselines, and achieves an improvement of top-1 accuracy by up to 19%.

show abstract

Attention-over-Attention Neural Networks for Reading Comprehension

Cited by 334 publications

References 18 publications

FuRongWang at SemEval-2017 Task 3: Deep Neural Networks for Selecting Relevant Answers in Community Question Answering

FuRongWang at SemEval-2017 Task 3: Deep Neural Networks for Selecting Relevant Answers in Community Question Answering

Chengyu Cloze Test

Chinese Medical Question Answer Matching Using End-to-End Character-Level Multi-Scale CNNs

Contact Info

Product

Resources

About