2022/05/30 by Verna Dankers, Dankers, Verna, Christopher G. Lucas +3 · 2 citations
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Natural Language Processing Techniques
paper · pdf · doi:10.48550/arxiv.2205.15301
openalex publication_date 2022/05/30 · openalex created_date 2022/06/13 · openalex updated_date 2026/07/28
Unlike literal expressions, idioms' meanings do not directly follow from their parts, posing a challenge for neural machine translation (NMT). NMT models are often unable to translate idioms accurately and over-generate compositional, literal translations. In this work, we investigate whether the non-compositionality of idioms is reflected in the mechanics of the dominant NMT model, Transformer, by analysing the hidden states and attention patterns for models with English as source language and one of seven European languages as target language. When Transformer emits a non-literal translation - i.e. identifies the expression as idiomatic - the encoder processes idioms more strongly as single lexical units compared to literal expressions. This manifests in idioms' parts being grouped through attention and in reduced interaction between idioms and their context. In the decoder's cross-attention, figurative inputs result in reduced attention on source-side tokens. These results suggest that Transformer's tendency to process idioms as compositional expressions contributes to literal translations of idioms.