about
Linspector Web: A Multilingual Probing Suite for Word Representations (arxiv.org)
2 points by sel1 on Jul 30, 2019 | hide | past | pdf | discuss on HN

In plain words: A free web tool checks word embeddings with simple language tests—gender, case, tense—across 28 languages, then shows what the vectors capture in a chart and table. Unlike English-only inspectors, it runs in a browser or offline for low-resource languages.

Abstract · LINSPECTOR WEB: A Multilingual Probing Suite for Word Representations

We present LINSPECTOR WEB, an open source multilingual inspector to analyze word representations. Our system provides researchers working in low-resource settings with an easily accessible web based probing tool to gain quick insights into their word embeddings especially outside of the English language. To do this we employ 16 simple linguistic probing tasks such as gender, case marking, and tense for a diverse set of 28 languages. We support probing of static word embeddings along with pretrained AllenNLP models that are commonly used for NLP downstream tasks such as named entity recognition, natural language inference and dependency parsing. The results are visualized in a polar chart and also provided as a table. LINSPECTOR WEB is available as an offline tool or at https://linspector.ukp.informatik.tu-darmstadt.de.

Max Eichler, Gözde Gül Şahin, Iryna Gurevych
arXiv:1907.11438 · cs.CL · submitted Jul 26, 2019 · updated Oct 15, 2019
abstract · pdf · html · Accepted at EMNLP 2019 System Demonstrations

add comment on HN