QueryNER: Segmentation of E-commerce Queries

TL;DR

QueryNER introduces a new dataset and model for segmenting e-commerce queries into meaningful chunks, improving robustness with data augmentation and addressing limitations of previous aspect-value extraction methods.

Contribution

The paper provides the first manually-annotated dataset for broad e-commerce query segmentation and evaluates baseline models with techniques to enhance noise robustness.

Findings

Data augmentation improves model robustness to noise.

Baseline models achieve promising segmentation performance.

Challenging test sets reveal areas for future improvement.

Abstract

We present QueryNER, a manually-annotated dataset and accompanying model for e-commerce query segmentation. Prior work in sequence labeling for e-commerce has largely addressed aspect-value extraction which focuses on extracting portions of a product title or query for narrowly defined aspects. Our work instead focuses on the goal of dividing a query into meaningful chunks with broadly applicable types. We report baseline tagging results and conduct experiments comparing token and entity dropping for null and low recall query recovery. Challenging test sets are created using automatic transformations and show how simple data augmentation techniques can make the models more robust to noise. We make the QueryNER dataset publicly available.