# Crossing Variational Autoencoders for Answer Retrieval

arXiv: https://arxiv.org/abs/2005.02557 · HTML: https://mlsanity.com/paper/2005.02557/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 May 2020.

## Built on by (most cited first, 5 of 5)

- [Generate rather than Retrieve: Large Language Models are Strong Context Generators](https://mlsanity.com/paper/2209.10063/) (2022)
- [A Survey of Multi-task Learning in Natural Language Processing: Regarding Task Relatedness and Training Methods](https://mlsanity.com/paper/2204.03508/) (2022)
- [A Neural Question Answering System for Basic Questions about Subroutines](https://mlsanity.com/paper/2101.03999/) (2021)
- [Enhancing Dual-Encoders with Question and Answer Cross-Embeddings for Answer Retrieval](https://mlsanity.com/paper/2206.02978/) (2022)
- [A Conditional Generative Matching Model for Multi-lingual Reply Suggestion](https://mlsanity.com/paper/2109.07046/) (2021)

## Abstract (arXiv)

Answer retrieval is to find the most aligned answer from a large set of candidates given a question. Learning vector representations of questions/answers is the key factor. Question-answer alignment and question/answer semantics are two important signals for learning the representations. Existing methods learned semantic representations with dual encoders or dual variational auto-encoders. The semantic information was learned from language models or question-to-question (answer-to-answer) generative processes. However, the alignment and semantics were too separate to capture the aligned semantics between question and answer. In this work, we propose to cross variational auto-encoders by generating questions with aligned answers and generating answers with aligned questions. Experiments show that our method outperforms the state-of-the-art answer retrieval method on SQuAD.