A Multilingual Approach for Unsupervised Search Task Identification
Authors:
Open Access
- 25 July 2020
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 2041-2044
Abstract
Users convert their information needs to search queries, which are then run on available search engines. Query logs registered by search engines enable the automatic identification of the search tasks that users perform to fulfill their information needs. Search engine logs contain queries in multiple languages, but most existing methods for search task identification are not multilingual. Some methods rely on search context training of custom embeddings or external indexed collections that support a single language, making it challenging to support the multiple languages of queries run in search engines. Other methods depend on supervised components and user identifiers to model search tasks. The supervised components require labeled collections, which are difficult and costly to get in multiple languages. Also, the need for user identifiers renders these methods unfeasible in user agnostic scenarios. Hence, we propose an unsupervised multilingual approach for search task identification. The proposed approach is user agnostic, enabling its use in both user-independent and personalized scenarios. Furthermore, the multilingual query representation enables us to address the existing trade-off when mapping new queries to the identified search tasks.Keywords
This publication has 11 references indexed in Scilit:
- CA-LSTM2018
- Universal Sentence Encoder for English2018
- Tempo-Lexical Context Driven Word Embedding for Cross-Session Search Task Extraction2018
- Word Embedding Causes Topic Shifting; Exploit Global Context!2017
- Extracting Hierarchies of Search Tasks & Subtasks via a Bayesian Nonparametric Approach2017
- Learning to extract cross-session search tasks2013
- Spectral methods for graph clustering – A surveyEuropean Journal of Operational Research, 2011
- Identifying task-based sessions in search engine query logs2011
- Search User Interfaces2009
- A survey on session detection methods in query logs and a proposal for future evaluationInformation Sciences, 2009