Identifying the Names of Complex Search Tasks with Task-Related Entities

Computational Linguistics and Chinese Language Processing Vol. 21, No. 1, June 2016, pp. 69-90 69  The Association for Computational Linguistics and Chinese Language Processing Identifying the Names of Complex Search Tasks with Task-Related Entities Ting-Xuan Wang and Wen-Hsiang Lu Abstract Conventional search engines usually consider a search query corresponding only to a simple task. Nevertheless, due to the explosive growth of web usage in recent years, more and more queries are driven by complex tasks. A complex task may consist of multiple sub-tasks. To accomplish a complex task, users may need to obtain information of various task-related entities corresponding to the sub-tasks. Users usually have to issue a series of queries for each entity during searching a complex search task. For example, the complex task “travel to Beijing” may involve several task-related entities, such as “hotel room,” “flight tickets,” and “maps”. Understanding complex tasks with task-related entities can allow a search engine to suggest integrated search results for each sub-task simultaneously. To understand and improve user behavior when searching a complex task, we propose an entity-driven complex task model (ECTM) based on exploiting microblogs and query logs. Experimental results show that our ECTM is effective in identifying the comprehensive task-related entities for a complex task and generates good quality complex task names based on the identified task-related entities. Keywords: Complex Search Task, Task Name Identification, Task-related Entity. 1. Introduction Conventional search engines usually consider single queries corresponding only to a simple search need. In reality, however, more and more queries are driven by complex search tasks (Guo & Agichtein, 2010; Jones & Klinkner, 2008). Generally, a real-life complex search task usually has more than one sub-task to be accomplished. Therefore, users usually cannot accomplish a complex search task by submitting only a single query. Some researchers have worked to try to identify sub-tasks in order to help users deal with complex search tasks (Tan  Departmenr of Computer Science and Information Engineering, National Cheng Kung University, Tainan, Taiwan E-mail: playif@gmail.com; whlu@mail.ncku.edu.tw 70 Ting-Xuan Wang and Wen-Hsiang Lu et al., 2006; MacKay et al., 2008; Ji et al., 2011; Kotov et al., 2011; Yamamoto et al., 2012). Nevertheless, only identifying sub-tasks in a complex search task is not sufficient to help users who want to search the complex task name directly e.g., “北京旅遊 (travel to Beijing)”. Understanding complex task names for complex search tasks can help search engines deal with complex-task-based queries. A complex search task can be represented by a task event and a task topic. For example, as shown in Figure 1, a complex task “travel to Beijing,” which is composed of a task topic “Beijing” and a task event “travel,” has at least three sub-tasks, including “book flight ticket,” “reserve hotel room,” and “survey maps”. Users need to issue at least three queries for each sub-task including “Beijing flight ticket,” “Beijing hotel,” and “Beijing map”. The queries targeting a sub-task usually focus on a task-related entity, such as “flight ticket,” “hotel room,” and “maps”. Therefore, understanding task-related …

Content truncated to 500 words