Linear Cross-Lingual Mapping of Sentence Embeddings
This work addresses the challenge of semantic representation in multilingual NLP, but it appears incremental as it builds on existing embedding methods without major breakthroughs.
The paper tackled the problem of improving multilingual sentence embeddings by proposing a simple linear cross-lingual mapping to enhance semantic invariance across translations, with results measured by deviation from orthogonality conditions as an indicator of embedding deficiency.
Semantics of a sentence is defined with much less ambiguity than semantics of a single word, and we assume that it should be better preserved by translation to another language. If multilingual sentence embeddings intend to represent sentence semantics, then the similarity between embeddings of any two sentences must be invariant with respect to translation. Based on this suggestion, we consider a simple linear cross-lingual mapping as a possible improvement of the multilingual embeddings. We also consider deviation from orthogonality conditions as a measure of deficiency of the embeddings.