Coattention Answer-Pointer Networks for Question Answering
نویسندگان
چکیده
Machine comprehension (MC) and question answering (QA) are crucial tasks in natural language understanding. Training deep neural network-based QA models has become practical upon the recent release of the Stanford Question Answering Dataset (SQuAD), a significantly larger dataset of question-answer pairs created by humans on a set of Wikipedia articles [1]. In this paper, we propose an end-to-end neural architecture for this task. The architecture consists of a Dynamic Coattention Network (DCN) encoder and a Match-LSTM decoder. On the hidden SQuAD test set, our model achieves 68.92% F1 and 57.56% EM.
منابع مشابه
Dynamic Coattention Networks For Question Answering
Several deep learning models have been proposed for question answering. However, due to their single-pass nature, they have no way to recover from local maxima corresponding to incorrect answers. To address this problem, we introduce the Dynamic Coattention Network (DCN) for question answering. The DCN first fuses co-dependent representations of the question and the document in order to focus o...
متن کاملCoattention Model for Question Answering
The recently released Stanford Question Answering Dataset (SQuAD) provides a unique version of the question-answer problem that more closely relates to the complex structure of natural language, and thus lends itself to the expressive power of neural networks. We explore combining tested techniques within an encoder-decoder architecture in an attempt to achieve a model that is both accurate and...
متن کاملReading Comprehension with Coattention Encoders
We present an end-to-end network architecture for question answering task given a real-world paragraph context. Using SQuAD dataset composed of 100K pairs, we train a coattention encoder to obtain a knowledge representation of the question and context data. This in turn is given as input to the decoder, which generates answer spans within the context. The prediction ...
متن کاملDecoding Coattention Encodings for Question Answering
An encoder-decoder architecture with recurrent neural networks in both the encoder and decoder is a standard approach to the question-answering problem (finding answers to a given question in a piece of text). The Dynamic Coattention[1] encoder is a highly effective encoder for the problem; we evaluated the effectiveness of different decoder when paired with the Dynamic Coattention encoder. We ...
متن کاملQuestion Answering System using Dynamic Coattention Networks
We tackle the difficult problem of building a question answering system by building an end-to-end recurrent neural using network sequence-to-sequence model. We use the coattention encoder and explore three different decoders: linear, single layer maxout, and highway maxout network. We train and evaluate our model using the recently published Stanford Question and Answering Dataset (SQuAD). Out ...
متن کامل