2019/09/12 by Yova Kementchedjhieva, Mareike Hartmann, Kementchedjhieva, Yova +3 · 1 citation
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Natural Language Processing Techniques #Text Readability and Simplification #Topic Modeling #cs.CL
paper · pdf · doi:10.48550/arxiv.1909.05708
Accepted at EMNLP 2019
openalex publication_date 2019/09/12 · arxiv created 2019/09/18 · arxiv updated 2019/09/19 · openalex created_date 2022/07/28 · openalex updated_date 2026/07/28
The task of bilingual dictionary induction (BDI) is commonly used for intrinsic evaluation of cross-lingual word embeddings. The largest dataset for BDI was generated automatically, so its quality is dubious. We study the composition and quality of the test sets for five diverse languages from this dataset, with concerning findings: (1) a quarter of the data consists of proper nouns, which can be hardly indicative of BDI performance, and (2) there are pervasive gaps in the gold-standard targets. These issues appear to affect the ranking between cross-lingual embedding systems on individual languages, and the overall degree to which the systems differ in performance. With proper nouns removed from the data, the margin between the top two systems included in the study grows from 3.4% to 17.2%. Manual verification of the predictions, on the other hand, reveals that gaps in the gold standard targets artificially inflate the margin between the two systems on English to Bulgarian BDI from 0.1% to 6.7%. We thus suggest that future research either avoids drawing conclusions from quantitative results on this BDI dataset, or accompanies such evaluation with rigorous error analysis.