Query Understanding via Entity Attribute Identification

Abstract

Understanding searchers' queries is an essential component of semantic search systems. In many cases, search queries involve specific attributes of an entity in a knowledge base (KB), which can be further used to find query answers. In this study, we aim to move forward the understanding of queries by identifying their related entity attributes from a knowledge base. To this end, we introduce the task of entity attribute identification and propose two methods to address it: (i) a model based on Markov Random Field, and (ii) a learning to rank model. We develop a human annotated test collection and show that our proposed methods can bring significant improvements over the baseline methods.

A Latent Model for Ad Hoc Table Retrieval

“…Topics: We employ the 60 topics that accompany the table corpus to perform our experiments. We annotate the queries using TagMe as done in [4][5][6]. Baselines: The state of the art include the methods in [16].…”

Conversational Entity Linking: Problem Definition and Datasets

“…In this realm, understanding user utterances plays a crucial role in holding meaningful conversations with users-this process is handled by the natural language understanding (NLU) component in traditional task-oriented dialogue systems [30]. A popular text understanding method, which has proven to be effective in various downstream tasks [19,22,33,34,51,59], is entity linking (EL): the task of recognizing mentions of entities in text and identifying their corresponding entries in a knowledge graph [4]. In this paper, we aim to investigate the role of entity linking in conversational systems.…”