Attention-based CNN Matching Net

نویسندگان

  • Tzu-Chien Liu
  • Yu-Hsueh Wu
  • Hung-yi Lee
چکیده

In this paper, we introduce attention-based CNN matching net (ACM-Net), an end-to-end neural network for question answering. ACM-Net matches between the given passage, query and multiple answer choices, and then it extracts features from passage and choices based on query information. We also propose a two-staged CNN architecture and a query-based attention mechanism in our model. These two component can effectively find out the most important parts in passage according to the query. Finally, we extract features from those important parts and find out the most possible answer choice. We conduct this model on the MovieQA dataset [1] using Plot Synopses only, and achieve 79.99% accuracy which is the state of the art on the dataset.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Adaptive Deep Pyramid Matching for Remote Sensing Scene Classification

Convolutional neural networks (CNNs) have attracted increasing attention in the remote sensing community. Most CNNs only take the last fully-connected layers as features for the classification of remotely sensed images, discarding the other convolutional layer features which may also be helpful for classification purposes. In this paper, we propose a new adaptive deep pyramid matching (ADPM) mo...

متن کامل

DiSAN: Directional Self-Attention Network for RNN/CNN-free Language Understanding

Recurrent neural nets (RNN) and convolutional neural nets (CNN) are widely used in NLP tasks to capture the longterm and local dependencies respectively. Attention mechanisms have recently attracted enormous interest due to their highly parallelizable computation, significantly less training time, and flexibility in modeling dependencies. We propose a novel attention mechanism in which the atte...

متن کامل

PN-Net: Conjoined Triple Deep Network for Learning Local Image Descriptors

In this paper we propose a new approach for learning local descriptors for matching image patches. It has recently been demonstrated that descriptors based on convolutional neural networks (CNN) can significantly improve the matching performance. Unfortunately their computational complexity is prohibitive for any practical application. We address this problem and propose a CNN based descriptor ...

متن کامل

Learning Oriented Region-based Convolutional Neural Networks for Building Detection in Satellite Remote Sensing Images

The automated building detection in aerial images is a fundamental problem encountered in aerial and satellite images analysis. Recently, thanks to the advances in feature descriptions, Region-based CNN model (R-CNN) for object detection is receiving an increasing attention. Despite the excellent performance in object detection, it is problematic to directly leverage the features of R-CNN model...

متن کامل

EdgeStereo: A Context Integrated Residual Pyramid Network for Stereo Matching

Recently convolutional neural network (CNN) promotes the development of stereo matching greatly. Especially those end-to-end stereo methods achieve best performance. However less attention is paid on encoding context information, simplifying two-stage disparity learning pipeline and improving details in disparity maps. Differently we focus on these problems. Firstly, we propose an one-stage con...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:
  • CoRR

دوره abs/1709.05036  شماره 

صفحات  -

تاریخ انتشار 2017