Deep Generative Model for Joint Alignment and Word Representation
This work addresses the challenge of improving word embeddings for NLP tasks, but it is incremental as it builds on existing methods with a novel integration of alignment and distributional embeddings.
The authors tackled the problem of learning word representations by using translation data as a semantic signal, developing a deep generative model that jointly learns embeddings and alignments, achieving competitive results on benchmarks like natural language inference and paraphrasing.
This work exploits translation data as a source of semantically relevant learning signal for models of word representation. In particular, we exploit equivalence through translation as a form of distributed context and jointly learn how to embed and align with a deep generative model. Our EmbedAlign model embeds words in their complete observed context and learns by marginalisation of latent lexical alignments. Besides, it embeds words as posterior probability densities, rather than point estimates, which allows us to compare words in context using a measure of overlap between distributions (e.g. KL divergence). We investigate our model's performance on a range of lexical semantics tasks achieving competitive results on several standard benchmarks including natural language inference, paraphrasing, and text similarity.