QueryNER: Segmentation of E-commerce Queries
This work addresses query segmentation for e-commerce applications, but it is incremental as it builds on prior sequence labeling methods with a new dataset and focus.
The authors tackled the problem of segmenting e-commerce queries into meaningful chunks by introducing QueryNER, a manually-annotated dataset and model, achieving baseline tagging results and improved robustness to noise through data augmentation techniques.
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.