2020/01/31 by Parker Riley, Riley, Parker, Daniel Gildea +1 · 3 citations
Computer Science · #Artificial intelligence #Computation and Language (cs.CL) #Computer science #FOS: Computer and information sciences #Lexicon #Linguistics #Natural Language Processing Techniques #Natural language processing #Philosophy #Speech Recognition and Synthesis #Topic Modeling #cs.CL
paper · pdf · doi:10.48550/arxiv.2002.00037
published in arXiv (Cornell University) (Cornell University)
arxiv created 2020/01/31 · openalex publication_date 2020/01/31 · arxiv updated 2020/02/04 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Recent embedding-based methods in unsupervised bilingual lexicon induction have shown good results, but generally have not leveraged orthographic (spelling) information, which can be helpful for pairs of related languages. This work augments a state-of-the-art method with orthographic features, and extends prior work in this space by proposing methods that can learn and utilize orthographic correspondences even between languages with different scripts. We demonstrate this by experimenting on three language pairs with different scripts and varying degrees of lexical similarity.