Retrofitting Multilingual Sentence Embeddings with Abstract Meaning Representation
This work addresses the challenge of enhancing multilingual sentence embeddings for applications like semantic similarity and downstream tasks, but it is incremental as it builds on existing embeddings.
The authors tackled the problem of improving multilingual sentence embeddings by incorporating Abstract Meaning Representation (AMR), a structured semantic representation, and achieved better state-of-the-art performance on semantic textual similarity and transfer tasks.
We introduce a new method to improve existing multilingual sentence embeddings with Abstract Meaning Representation (AMR). Compared with the original textual input, AMR is a structured semantic representation that presents the core concepts and relations in a sentence explicitly and unambiguously. It also helps reduce surface variations across different expressions and languages. Unlike most prior work that only evaluates the ability to measure semantic similarity, we present a thorough evaluation of existing multilingual sentence embeddings and our improved versions, which include a collection of five transfer tasks in different downstream applications. Experiment results show that retrofitting multilingual sentence embeddings with AMR leads to better state-of-the-art performance on both semantic textual similarity and transfer tasks. Our codebase and evaluation scripts can be found at \url{https://github.com/jcyk/MSE-AMR}.