Workshop on Intelligent Systems for Information Exploration and Access (iSEA)

在过去的几十年里，我们在搜索和推荐领域取得了许多进步。然而，解决信息获取问题仍然存在挑战和机遇，这些问题涉及为各种不同的用户解决任务和实现目标。具体地说，我们缺乏智能系统，这些系统不仅可以检测用户正在发出的请求(什么)，而且可以在提供信息的同时理解和利用意图(为什么)和策略(如何)。搜索、推荐系统和人工智能领域的许多学者已经认识到提取和理解用户的任务以及执行该任务背后的意图的重要性，以便更好地为他们服务。然而，我们仍在努力摆脱单一查询或单一回合的互动。与智能手机和智能扬声器集成的智能代理的激增为信息交互开辟了新的方式。但这些代理需要能够更智能地工作，以理解上下文并在任务级别帮助用户。在过去的几年里，围绕这一主题发生了几个事件，表明学者们的兴趣不断增强，但也突显了做更多工作的必要性。这次在西雅图地区举行的为期两天的研讨会将汇集在该领域工作或感兴趣的学者、学生和领导人。参与者将被邀请来自不同的学科，包括但不限于搜索和人工智能。研讨会将有三个主要目标：(1)学习和分享关于解决任务的信息获取的智能系统的学术现状；(2)找出我们在这一领域开发新模型、理论和系统的知识差距和机会；以及(3)通过编写一份报告，将这些讨论和见解整合到更广泛的受众中。本次研讨会的结果将包括一份会议记录、一份技术报告和一份课程，用于向本科生和研究生讲授本研讨会所涵盖的主题。该奖项反映了NSF的法定使命，并通过使用基金会的智力优势和更广泛的影响审查标准进行评估，被认为是值得支持的。

We have made many advancements in the field of search and recommendation over the last few decades. However, there are still challenges and opportunities to address information access issues that involve solving tasks and accomplishing goals for a wide variety of users. Specifically, we lack intelligent systems that can detect not only the request a user is making (what), but also understand and utilize the intention (why) and strategies (how) while providing information. Many scholars in the fields of search, Recommender Systems, and AI have recognized the importance of extracting and understanding a user’s task and the intention behind doing that task in order to serve them better. However, we are still struggling to get out of single-query or single-turn interactions. The proliferation of intelligent agents that come integrated with smartphones and smart speakers has opened up new modality for interacting with information. But these agents will need to be able to work more intelligently in understanding the context and helping the users at the task level. Several events have taken place over the past few years around this topic, indicating continual and increased interest by scholars, but also highlighting the need for doing more.This two-day workshop in the Seattle area will bring together scholars, students, and leaders working or interested in this domain. The participants will be invited from different disciplines that include but not limited to search and AI. The workshop will have three primary goals: (1) learn and share about the current state of scholarship around intelligent systems for information access for solving tasks; (2) identify gaps in our knowledge and opportunities for developing new models, theories, and systems in this space; and (3) consolidate these discussions and insights to broader audiences through compilation of a report. The outcomes of this workshop will include a proceedings, a technical report, and a curriculum for teaching the topics covered through this workshop to undergraduate and graduate students.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.