Incorporating Behavioral Hypotheses for Query Generation

TL;DR

This paper introduces a method that incorporates behavioral hypotheses into a Transformer-based query generation model, improving the accuracy of predicted user queries by leveraging behavioral signals from user interactions.

Contribution

It proposes a novel approach to integrate behavioral hypotheses into query generation, enhancing performance over existing models like BART.

Findings

Significant improvement in top-$k$ word error rate

Higher Bert F1 Score compared to baseline models

Effective aggregation of behavioral signals in query prediction

Abstract

Generative neural networks have been shown effective on query suggestion. Commonly posed as a conditional generation problem, the task aims to leverage earlier inputs from users in a search session to predict queries that they will likely issue at a later time. User inputs come in various forms such as querying and clicking, each of which can imply different semantic signals channeled through the corresponding behavioral patterns. This paper induces these behavioral biases as hypotheses for query generation, where a generic encoder-decoder Transformer framework is presented to aggregate arbitrary hypotheses of choice. Our experimental results show that the proposed approach leads to significant improvements on top-$k$ word error rate and Bert F1 Score compared to a recent BART model.