Learning Analogy-Preserving Sentence Embeddings for Answer Selection
This addresses answer selection in NLP by introducing analogy-based embeddings, offering a novel approach but likely incremental as it builds on existing embedding methods.
The paper tackled answer selection by hypothesizing that question-answer pairs often have analogical relations, proposing a framework for learning sentence embeddings that preserve these properties. The result showed that these embeddings captured analogical properties better than conventional ones and outperformed similarity-based techniques on benchmark datasets.
Answer selection aims at identifying the correct answer for a given question from a set of potentially correct answers. Contrary to previous works, which typically focus on the semantic similarity between a question and its answer, our hypothesis is that question-answer pairs are often in analogical relation to each other. Using analogical inference as our use case, we propose a framework and a neural network architecture for learning dedicated sentence embeddings that preserve analogical properties in the semantic space. We evaluate the proposed method on benchmark datasets for answer selection and demonstrate that our sentence embeddings indeed capture analogical properties better than conventional embeddings, and that analogy-based question answering outperforms a comparable similarity-based technique.