Query-Response Interactions by Multi-tasks in Semantic Search for Chatbot Candidate Retrieval
This addresses an important yet neglected problem in retrieval-based chatbots for improving candidate selection efficiency, though it appears incremental in method.
The paper tackles the problem of semantic search for candidate retrieval in retrieval-based chatbots by proposing a multitask-based neural network (MSSNN) to enable rich query-response interactions and efficient online inference, with experimental studies showing its potential.
Semantic search for candidate retrieval is an important yet neglected problem in retrieval-based Chatbots, which aims to select a bunch of candidate responses efficiently from a large pool. The existing bottleneck is to ensure the model architecture having two points: 1) rich interactions between a query and a response to produce query-relevant responses; 2) ability of separately projecting the query and the response into latent spaces to apply efficiently in semantic search during online inference. To tackle this problem, we propose a novel approach, called Multitask-based Semantic Search Neural Network (MSSNN) for candidate retrieval, which accomplishes query-response interactions through multi-tasks. The method employs a Seq2Seq modeling task to learn a good query encoder, and then performs a word prediction task to build response embeddings, finally conducts a simple matching model to form the dot-product scorer. Experimental studies have demonstrated the potential of the proposed approach.