In community-based question answering (CQA) platforms, automatic answer ranking for a given question is critical for finding potentially popular answers in early times. The mainstream approaches learn to generate answer ranking scores based on the matching degree between question and answer representations as well as the influence of respondents. However, they encounter two main limitations: (1) Correlations between answers in the same question are often overlooked. (2) Question and respondent representations are built independently of specific answers before affecting answer representations. To address the limitations, we devise a novel graph-based tri-attention network, namely GTAN, which has two innovations. First, GTAN proposes to construct a graph for each question and learn answer correlations from each graph through graph neural networks (GNNs). Second, based on the representations learned from GNNs, an alternating tri-attention method is developed to alternatively build target-aware respondent representations, answer-specific question representations, and context-aware answer representations by attention computation. GTAN finally integrates the above representations to generate answer ranking scores. Experiments on three real-world CQA datasets demonstrate GTAN significantly outperforms state-of-the-art answer ranking methods, validating the rationality of the network architecture.
PerCQA: Persian Community Question Answering Dataset
School of Computer Science, Institute for Research in Fundamental Sciences（基础科学研究学院计算机科学系）；School of Electrical and Computer Engineering, College of Engineering, University of Tehran（德黑兰大学工程学院电气与计算机工程系）
Joint Learning of Answer Selection and Answer Summary Generation in Community Question Answering
The Chinese University of Hong Kong（香港中文大学）；Peking University Shenzhen Graduate School（北京大学深圳研究生院）；Alibaba Group（阿里巴巴集团）；Chinese Academy of Sciences（中国科学院）；South China University of Technology（华南理工大学）
IIE-NLP-Eyas at SemEval-2021 Task 4: Enhancing PLM for ReCAM with Special Tokens, Re-Ranking, Siamese Encoders and Back Translation
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络空间安全学院）
Quality and Cost Trade-offs in Passage Re-ranking Task
IHS Markit（埃信华迈）
名为Transformers的深度学习模型在绝大多数NLP任务中实现了最先进的结果，但代价是增加了计算复杂性和高内存消耗。在实时推理中使用Transformer模型在生产中实现时成为一个主要挑战，因为它需要昂贵的计算资源。需要执行的Transformer越多，整体吞吐量就越低，并且切换到较小的编码器会导致精度降低。我们的论文致力于如何选择正确的信息检索管道的排名步骤的架构的问题，使所需的调用的数量最小的Transformer编码器是最大的可实现的排名质量。我们研究了几种后期交互模型，如Colbert和Poly-encoder架构及其修改。此外，我们还考虑了搜索索引的内存占用，并尝试应用学习哈希方法对来自Transformer编码器的输出向量进行二进制化。评估结果使用TREC 2019-2021和MS Marco dev数据集提供。
KG-Rank: Enhancing Large Language Models for Medical QA with Knowledge Graphs and Ranking Techniques
Texas A&M University（德克萨斯农工大学）；The University of Tokyo（东京大学）；Northwestern University（西北大学）；Singapore General Hospital（新加坡中央医院）；Zhejiang University（浙江大学）；Zhejiang Lab（之江实验室）；Yale University（耶鲁大学）；National Institutes of Health（美国国立卫生研究院）；Duke-NUS Medical School（杜克-新加坡国立大学医学院）
Retrieval, Reasoning, Re-ranking: A Context-Enriched Framework for Knowledge Graph Completion
IDEA Research, International Digital Economy Academy（IDEA研究室，国际数字经济学院）；Department of Computer Science & Engineering, The Chinese University of Hong Kong（计算机科学与工程系，香港中文大学）；Artificial Intelligence Thrust, Hong Kong University of Science and Technology (Guangzhou)（人工智能方向，香港科技大学（广州））
