Entity Linking for Queries by Searching Wikipedia Sentences

Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 68–77 Copenhagen, Denmark, September 7–11, 2017. c⃝2017 Association for Computational Linguistics Entity Linking for Queries by Searching Wikipedia Sentences Chuanqi Tan† ∗ Furu Wei‡ Pengjie Ren+ Weifeng Lv† Ming Zhou‡ †State Key Laboratory of Software Development Environment, Beihang University, China ‡Microsoft Research +Shandong University †tanchuanqi@nlsde.buaa.edu.cn ‡{fuwei, mingzhou}@microsoft.com+jay.ren@outlook.com †lwf@buaa.edu.cn Abstract We present a simple yet effective approach for linking entities in queries. The key idea is to search sentences similar to a query from Wikipedia articles and directly use the human-annotated entities in the simi- lar sentences as candidate entities for the query. Then, we employ a rich set of features, such as link-probability, context- matching, word embeddings, and related- ness among candidate entities as well as their related entities, to rank the candi- dates under a regression based framework. The advantages of our approach lie in two aspects, which contribute to the ranking process and final linking result. First, it can greatly reduce the number of candi- date entities by filtering out irrelevant en- tities with the words in the query. Second, we can obtain the query sensitive prior probability in addition to the static link- probability derived from all Wikipedia ar- ticles. We conduct experiments on two benchmark datasets on entity linking for queries, namely the ERD14 dataset and the GERDAQ dataset. Experimental re- sults show that our method outperforms state-of-the-art systems and yields 75.0% in F1 on the ERD14 dataset and 56.9% on the GERDAQ dataset. 1 Introduction Query understanding has been an important re- search area in information retrieval and natural language processing (Croft et al., 2010). A key part of this problem is entity linking, which aims to annotate the entities in the query and link them to a knowledge base such as Freebase and ∗Contribution during internship at Microsoft Research. Wikipedia. This problem has been extensively studied over the recent years (Ling et al., 2015; Usbeck et al., 2015; Cornolti et al., 2016). The mainstream methods of entity linking for queries can be summed up in three steps: mention detection, candidate generation, and entity disam- biguation. The first step is to recognize candidate mentions in the query. The most common method to detect mentions is to search a dictionary col- lected by the entity alias in a knowledge base and the human-maintained information in Wikipedia (such as anchors, titles and redirects) (Laclavik et al., 2014). The second step is to generate candidates by mapping mentions to entities. usually uses all possible senses of detected men-It tions as candidates. Hereafter, we refer to these two steps of generating candidate entities as entity search. Finally, they disambiguate and prune can- didate entities, which is usually implemented with a ranking framework. There are two main issues in entity search. First, a mention may be linked to many entities. The methods using entity search usually leverage little context information in the query. Therefore it may generate many completely irrelevant entities for the query, which brings challenges …

Content truncated to 500 words