Best NLP engineering experiment: Authorless Topic Models: Biasing Models Away from Known Structure, by Laure Thompson and David Mimno
Best position paper: Arguments and Adjuncts in Universal Dependencies, by Adam Przepiórkowski and Agnieszka Patejuk
Best reproduction paper: Neural Network Models for Paraphrase Identification, Semantic Textual Similarity, Natural Language Inference, and Question Answering, by Wuwei Lan and Wei Xu
Best resource paper: AnlamVer: Semantic Model Evaluation Dataset for Turkish – Word Similarity and Relatedness, by Gökhan Ercan and Olcay Taner Yıldız
Best survey paper: A Survey on Open Information Extraction, by Christina Niklaus, Matthias Cetto, André Freitas and Siegfried Handschuh
Most reproducible: Design Challenges and Misconceptions in Neural Sequence Labeling, by Jie Yang, Shuailong Liang and Yue Zhang
人工智能重要会议COLING 2018最佳论文公布(会议级别CCF,B类)。请注意,正如去年宣布的那样,对于开放的科学和可重复性,COLING 2018没有授予最佳论文奖,因为这些论文无法通过相机准备好时间公开提供代码/资源。这意味着您现在可以向最好的论文作者询问关联的数据和程序,他们应该能够为您提供链接。此外,我们还要注意以下文章作为“区域主席最爱”,由评审员提名并被主席认可为优秀。
Visual Question Answering Dataset for Bilingual Image Understanding: A study of cross-lingual transfer using attention maps. Nobuyuki S