Modeling Relational Information in Question-Answer Pairs with Convolutional Neural Networks
This work addresses answer selection for question-answering systems, but it is incremental as it builds on existing methods with a focus on relational information.
The paper tackled the problem of answer sentence selection by modeling relational information between question-answer pairs using convolutional neural networks, resulting in a significant boost in accuracy that approaches state-of-the-art performance on two benchmarks.
In this paper, we propose convolutional neural networks for learning an optimal representation of question and answer sentences. Their main aspect is the use of relational information given by the matches between words from the two members of the pair. The matches are encoded as embeddings with additional parameters (dimensions), which are tuned by the network. These allows for better capturing interactions between questions and answers, resulting in a significant boost in accuracy. We test our models on two widely used answer sentence selection benchmarks. The results clearly show the effectiveness of our relational information, which allows our relatively simple network to approach the state of the art.