Combining Graph-Based Dependency Features with Convolutional Neural Network for Answer Triggering

Deepak Gupta, Sarah Kohail, Pushpak Bhattacharyya

Abstract: Answer triggering is the task of selecting the best-suited answer for a given question from a set of candidate answers if it exists. This paper presents a hybrid deep learning model for answer triggering, which combines several dependency graph-based alignment features, namely graph edit distance, graph-based similarity, and dependency graph coverage, with dense vector embeddings from a Convolutional Neural Network (CNN). Our experiments on the WikiQA dataset show that such a combination can more accurately trigger a candidate answer compared to the previous state-of-the-art models. Comparative study on WikiQA data set shows \(5.86\%\) absolute F-score improvement at the question level.

External IDs:dblp:conf/cicling/GuptaKB18