Question Answering System using Dynamic Coattention Networks
نویسندگان
چکیده
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 best result is achieved by using linear decoder with an F1 score of 54.93%.
منابع مشابه
Decoding 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 کاملDynamic 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 کاملDcn+: Mixed Objective and Deep Residual Coattention for Question Answering
Traditional models for question answering optimize using cross entropy loss, which encourages exact answers at the cost of penalizing nearby or overlapping answers that are sometimes equally accurate. We propose a mixed objective that combines cross entropy loss with self-critical policy learning. The objective uses rewards derived from word overlap to solve the misalignment between evaluation ...
متن کاملDCN+: Mixed Objective and Deep Residual Coattention for Question Answering
Traditional models for question answering optimize using cross entropy loss, which encourages exact answers at the cost of penalizing nearby or overlapping answers that are sometimes equally accurate. We propose a mixed objective that combines cross entropy loss with self-critical policy learning. The objective uses rewards derived from word overlap to solve the misalignment between evaluation ...
متن کاملCoattention Answer-Pointer Networks for Question Answering
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-e...
متن کامل