SENSEABLE SEARCH: Selective Query Disambiguation
نویسندگان
چکیده
We present a method for detecting and resolving lexical ambiguity in information retrieval queries. Leveraging existing word sense disambiguation tools, we define a measure of query term ambiguity based on the distribution of word senses in the relevant document set. If a query term is ambiguous, we allow the user to select the correct sense of the query term, in the style of Google’s spelling correction. Secondly, we present a method for results diversification, where one word sense dominates the top results, but there is a sizable number of documents with a second sense. We present a successful qualitative evaluation of our methods which demonstrates the plausibility and applicability of the approach.
منابع مشابه
Utilizing User-input Contextual Terms for Query Disambiguation
Precision-oriented search results such as those typically returned by the major search engines are vulnerable to issues of polysemy. When the same term refers to different things, the dominant sense is preferred in the rankings of search results. In this paper, we propose a novel technique in the context of web search that utilizes contextual terms provided by users for query disambiguation, ma...
متن کاملSemEval-2013 Task 11: Word Sense Induction and Disambiguation within an End-User Application
In this paper we describe our Semeval-2013 task on Word Sense Induction and Disambiguation within an end-user application, namely Web search result clustering and diversification. Given a target query, induction and disambiguation systems are requested to cluster and diversify the search results returned by a search engine for that query. The task enables the end-to-end evaluation and compariso...
متن کاملMixed Language Query Disambiguation
We propose a mixed language query disambiguation approach by using co-occurrence information from monolingual data only. A mixed language query consists of words in a primary language and a secondary language. Our method translates the query into monolingual queries in either language. Two novel features for disambiguation, namely contextual word voting and 1-best contextual word, are introduce...
متن کاملUnderstanding Users Intent by Deducing Domain Knowledge Hidden in Web Search Query Keywords
Search Engines are used by people on a daily basis to retrieve information from the web. When an ambiguous word is present in a query, specific sense of the keyword is not considered during the search process. Search engines return a large amount of web pages as results from all the possible contexts. Users tend to browse only few pages. Improving quality of retrieved results is a challenge and...
متن کاملCrowdQ: A Search Engine with Crowdsourced Query Understanding
Providing direct answers to web search queries rather than links to related documents has been shown to increase user satisfaction [3]. However, most search engines only provide answers to a few simple query types and keyword queries provide little semantic information. To support direct answers for more complex and less common queries, we have developed CrowdQ, a novel hybrid human-machine sys...
متن کامل