基于多头注意力和BiLSTM改进DAM模型的中文问答匹配方法(Chinese question answering method based on multi-head attention and BiLSTM improved DAM model)

no code implementations • CCL 2020 • Hanzhong Qin, Chongchong Yu, Weijie Jiang, Xia Zhao

针对目前检索式多轮对话深度注意力机制模型DAM(Deep Attention Matching Network)候选回复细节不匹配和语义混淆的问题, 本文提出基于多头注意力和双向长短时记忆网络(BiLSTM)改进DAM模型的中文问答匹配方法, 该方法采用多头注意力机制, 使模型有能力建模较长的多轮对话, 更好的处理目标回复与上下文的匹配关系。此外, 本文在特征融合过程中采用BiLSTM模型, 通过捕获多轮对话中的序列依赖关系, 进一步提升选择目标候选回复的准确率。本文在豆瓣和电商两个开放数据集上进行实验, 实验性能均优于DAM基线模型, R10@1指标在含有词向量增强的情况下提升了1. 5%。

Deep Attention Question Answering

Scene Graph Generation: A Comprehensive Survey

no code implementations • 3 Jan 2022 • Guangming Zhu, Liang Zhang, Youliang Jiang, Yixuan Dang, Haoran Hou, Peiyi Shen, Mingtao Feng, Xia Zhao, Qiguang Miao, Syed Afaq Ali Shah, Mohammed Bennamoun

In this paper, we provide a comprehensive survey of recent achievements in this field brought about by deep learning techniques.

Graph Generation object-detection +4

Cross-lingual Data Transformation and Combination for Text Classification

no code implementations • 23 Jun 2019 • Jun Jiang, Shumao Pang, Xia Zhao, Li-Wei Wang, Andrew Wen, Hongfang Liu, Qianjin Feng

In order to train a generalizable model, a large volume of text must be collected.

General Classification Machine Translation +2