Personalized Language Model for Query Auto-Completion

Aaron Jaech, Mari Ostendorf
4/25/2018
cs.CLcs.IR

Official code: ajaech/query_completion (27 stars, Apache-2.0, last commit 2020-11-21).

Abstract

Query auto-completion is a search engine feature whereby the system suggests completed queries as the user types. Recently, the use of a recurrent neural network language model was suggested as a method of generating query completions. We show how an adaptable language model can be used to generate personalized completions and how the model can use online updating to make predictions for users not seen during training. The personalized predictions are significantly better than a baseline that uses no user information.

View on arXivView PDF

Code Implementations(1)

ajaech/query_completionOfficial100%
Apache-2.0

Personalized Query Completion

277PythonNov 15, 20175 years agoApache-2.0
deeplearninginformation-retrievallanguage-model

Similar Papers

Trie-NLG: Trie Context Augmentation to Improve Personalized Query Auto-Completion for Short and Unseen Prefixes

84% match2023

DocQAC: Adaptive Trie-Guided Decoding for Effective In-Document Query Auto-Completion

82% match1 repo12026

Seasonality Based Reranking of E-commerce Autocomplete Using Natural Language Queries

80% match2023

Synthetic Prefixes to Mitigate Bias in Real-Time Neural Query Autocomplete

80% match2025

A Learnable Agent Collaboration Network Framework for Personalized Multimodal AI Search Engine

79% match2024

Less Is Personal: Learning Minimal Sufficient User Profiles for Personalized Language Models

79% match2026

Cite this paper

@article{jaech2018personalized,
  title  = {Personalized Language Model for Query Auto-Completion},
  author = {Aaron Jaech and Mari Ostendorf},
  year   = {2018},
  eprint = {1804.09661},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1804.09661}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1804.09661.svg)](https://codeofpaper.com/paper/1804.09661)

Discussion