实验室两篇论文被Web Conference2019(WWW2019)录取为长文
新闻来源:IR实验室       发布时间:2019/1/26 22:51:13

  近日,Web Conference2019(即WWW2019)公布了论文录取情况,实验室张冬瑜和刁宇峰的两篇论文被录取为长文,主要讨论双关语的识别问题和人脸表情对于社会网络中心性的影响。


  WWW会议在CCF推荐的会议列表中属于A类,是鼓励广大研究人员进行突破的顶级会议。今年的会议投稿综述为1247,录取225篇,录取率为18%。


  论文1:#667: Heterographic Pun Recognition via Pronunciation and Spelling Understanding Gated Attention Network

  【摘要】Heterographic pun plays a critical role in human writing and literature, which usually has a similar sounding or spelling structure. It is important and difficult research to recognize the heterographic pun because of the ambiguity. However, most existing methods for this task focus only on designing features with rule-based or machine learning methods. In this paper, we propose an end-to-end computational approach – Pronunciation Spelling Understanding Gated Attention (PSUGA) network. For pronunciation, we exploit the hierarchical attention model with phoneme embedding. While for spelling, we consider the character-level, word-level, tag-level, position-level and contextual-level embedding with attention model. To deal with the two parts, we propose a gated attention mechanism to control the information integration. We have conducted extensive experiments on SemEval2017 task7 and Pun of the Day datasets. Experimental results show that our approach significantly outperforms state-of-the-art methods.


  论文2:#814: Judging a Book by Its Cover: The Effect of Facial Perception  on Centrality in Social Networks

  【摘要】Facial appearance matters in social networks. Individuals frequently make trait judgments from facial clues. Although these face-based impressions lack the evidence to determine validity, they are of vital importance, because they may relate to human network-based social behavior, such as seeking certain individuals for help, advice, dating, and cooperation, and thus they may relate to centrality in social networks. However, little to no work has investigated the apparent facial traits that influence network centrality, despite the large amount of research on attributions of th