Convolutional-Match Networks for Question Answering
نویسندگان
چکیده
In this paper, we present a simple, yet effective, attention and memory mechanism that is reminiscent of Memory Networks and we demonstrate it in question-answering scenarios. Our mechanism is based on four simple premises: a) memories can be formed from word sequences by using convolutional networks; b) distance measurements can be taken at a neuronal level; c) a recursive softmax function can be used for attention; d) extensive weight sharing can help profoundly. We achieve state-of-the-art results in the bAbI tasks, outperforming Memory Networks and the Differentiable Neural Computer, both in terms of accuracy and stability (i.e. variance) of results.
منابع مشابه
Convolutional Deep Neural Networks for Document-Based Question Answering
Document-based Question Answering aims to compute the similarity or relevance between two texts: question and answer. It is a typical and core task and considered as a touchstone of natural language understanding. In this article, we present a convolutional neural network based architecture to learn feature representations of each questionanswer pair and compute its match score. By taking the i...
متن کاملLearning Convolutional Text Representations for Visual Question Answering
Visual question answering is a recently proposed articial intelligence task that requires a deep understanding of both images and texts. In deep learning, images are typically modeled through convolutional neural networks, and texts are typically modeled through recurrent neural networks. While the requirement for modeling images is similar to traditional computer vision tasks, such as object ...
متن کاملQuestion Answering Based on Distributional Semantics
An NLP application for question answering provides an insight into computer’s understanding of human language. Many areas of NLP have recently built on deep learning and distributional semantic representation. This paper seeks to apply distributional semantic models and convolutional neural networks to the question answering task.
متن کاملSimple Question Answering by Attentive Convolutional Neural Network
This work focuses on answering single-relation factoid questions over Freebase. Each question can acquire the answer from a single fact of form (subject, predicate, object) in Freebase. This task, simple question answering (SimpleQA), can be addressed via a two-step pipeline: entity linking and fact selection. In fact selection, we match the subject entity in a fact candidate with the entity me...
متن کاملConvolutional Encoding in Bidirectional Attention Flow for Question Answering
Deep learning systems for complex natural language processing tasks like question answering are often large, cumbersome models that require excessive computational power and time. We seek to address this issue by exploring efficient and parallelizable alternatives to the more computationally expensive components of one of the top-performing question-answering architectures. In particular, we ex...
متن کامل