A Bilingual Generative Transformer for Semantic Sentence Embedding

John Wieting, Graham Neubig, Taylor Berg-Kirkpatrick

Abstract: Semantic sentence embedding models take natural language sentences and turn them into vectors, such that similar vectors indicate similarity in the semantics between the sentences. Bilingual data offers a useful signal for learning such embeddings: properties shared by both sentences in a translation pair are likely semantic, while divergent properties are likely stylistic or language-specific. We propose a deep latent variable model that attempts to perform source separation on parallel sentences, isolating what they have in common in a latent semantic vector, and explaining what is left over with language-specific latent vectors. Our proposed approach differs from past work on semantic sentence encoding in two ways. First, by using a variational probabilistic framework, we introduce priors that encourage source separation, and can use our model’s posterior to predict sentence embeddings for monolingual data at test time. Second, we use high- capacity transformers as both data generating distributions and inference networks – contrasting with most past work on sentence embeddings. In experiments, our approach substantially outperforms the state-of-the-art on a standard suite of se- mantic similarity evaluations. Further, we demonstrate that our approach yields the largest gains on more difficult subsets of test where simple word overlap is not a good indicator of similarity.

Keywords: sentence embedding, semantic similarity, multilingual, latent variables, vae

Community Implementations: [ 2 code implementations](https://www.catalyzex.com/paper/arxiv:1911.03895/code)