Generative models for Information Retrieval, where ranking of documents is viewed as the task of generating a query from a document's language model, were very successful in various IR tasks in the past. However, with the advent of modern deep neural networks, attention has shifted to discriminative ranking functions that model the semantic similarity of documents and queries instead. Recently, deep generative models such as GPT2 and BART have been shown to be excellent text generators, but their effectiveness as rankers have not been demonstrated yet. In this work, we revisit the generative framework for information retrieval and show that our generative approaches are as effective as state-of-the-art semantic similarity-based discriminative models for the answer selection task. Additionally, we demonstrate the effectiveness of unlikelihood losses for IR.
Pretrained Transformers for Text Ranking: BERT and Beyond
David R. Cheriton School of Computer Science, University of Waterloo（滑铁卢大学大卫·切里顿计算机科学学院）；University of Amsterdam（阿姆斯特丹大学）；Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）
Beyond Topical Similarity: Contrastive Evidence Retrieval with Interpretable Attention Alignment in RAG
University of Chile（智利大学）；São Paulo State University（圣保罗州立大学）；Saarland University（萨尔兰州立大学）；University of Munich（慕尼黑大学）；Portland State University（波特兰州立大学）；Idiap Research Institute（Idiap研究机构）
Beyond Relevance-Centric Retrieval: Rubric-Oriented Document Set Selection and Ranking
University of Science and Technology of China（中国科学技术大学）；Yuanbao Team, Tencent（腾讯元宝团队）；University of Chinese Academy of Sciences（中国科学院大学）；Shandong University（山东大学）
Response Ranking with Deep Matching Networks and External Knowledge in Information-seeking Conversation Systems
Center for Intelligent Information Retrieval, University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校智能信息检索中心）；Alibaba Group（阿里巴巴集团）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；Dept. of Computer Science, Rutgers University（罗格斯大学计算机科学系）
