Syntactic complexity of Web search queries through the lenses of language models, networks and users

作者:

Highlights:

• We present a holistic view on the syntactic complexity of Web search queries.

• We use three perspectives: statistical language modeling, complex network analysis, and “native speaker” intuition.

• The three complementary viewpoints show that the syntactic structure of Web queries is more complex than what n-grams can capture, but simpler than natural language.

• Queries, thus, seem to represent an intermediate stage between syntactic and non-syntactic communication.

摘要

•We present a holistic view on the syntactic complexity of Web search queries.•We use three perspectives: statistical language modeling, complex network analysis, and “native speaker” intuition.•The three complementary viewpoints show that the syntactic structure of Web queries is more complex than what n-grams can capture, but simpler than natural language.•Queries, thus, seem to represent an intermediate stage between syntactic and non-syntactic communication.

论文关键词:Query complexity,Statistical language models,Word co-occurrence networks,Crowd-sourcing

论文评审过程:Received 17 February 2015, Revised 17 February 2016, Accepted 5 April 2016, Available online 23 April 2016, Version of Record 22 July 2016.

论文官网地址:https://doi.org/10.1016/j.ipm.2016.04.002