Pun location is to identify the punning word (usually a word or a phrase that makes the text ambiguous) in a given short text, and pun interpretation is to find out two different meanings of the punning word. Most previous studies adopt limited word senses obtained by WSD(Word Sense Disambiguation) technique or pronunciation information in isolation to address pun location. For the task of pun interpretation, related work pays attention to various WSD algorithms. In this paper, a model called DANN (Dual-Attentive Neural Network) is proposed for pun location, effectively integrates word senses and pronunciation with context information to address two kinds of pun at the same time. Furthermore, we treat pun interpretation as a classification task and construct pungloss pairs as processing data to solve this task. Experiments on the two benchmark datasets show that our proposed methods achieve new state-of-the-art results. Our source code is available in the public code repository.
翻译:Pun 位置是在给定的简短文本中识别点字词(通常是一个词或一个使文本模糊不清的词句),而Pun 解释则是要找出点字词的两个不同含义。 大多数先前的研究都采用WSD(Word Sense Disamdiguation)技术或发音信息单独获得的有限字感, 以定位 pun 位置 。 关于点解的任务, 相关工作关注各种 WSD 算法。 本文为点字位置提议了一个名为 DANN( Daual- Attention Neal 网络) 的模式, 有效地将字感和发音与上下文信息结合, 以同时处理两种语句。 此外, 我们把 pun 解释作为分类任务, 构建 pungloss 配对作为处理此任务的数据。 在两个基准数据集上进行实验显示, 我们提出的方法取得了新的状态- 艺术结果。 我们的源代码可以在公共代码存储处查阅 。