# Learning Analogy-Preserving Sentence Embeddings for Answer Selection Source: [Learning Analogy-Preserving Sentence Embeddings for Answer Selection]() Collection index: [llms.txt]() Data updated: 2026-01-04T03:11:22.412Z Authors: Aissatou Diallo, Markus Zopf, Johannes F\\"urnkranz Published: 2019-10-11T17:22:19.000Z ## Abstract 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. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Analogical Question Answering on WikiQA (test)](): Analogical Question Answering; WikiQA (test); MAP: 0.677. - [Answer Selection on WikiQA (test)](): Answer Selection; WikiQA (test); MAP: not recorded. ## Original sources and implementation [Original paper]() [PDF]()