Abstract
Typological knowledge bases (KBs) such as WALS (Dryer and Haspelmath, 2013) contain information about linguistic properties of the world’s languages. They have been shown to be useful for downstream applications, including cross-lingual transfer learning and linguistic probing. A major drawback hampering broader adoption of typological KBs is that they are sparsely populated, in the sense that most languages only have annotations for some features, and skewed, in that few features have wide coverage. As typological features often correlate with one another, it is possible to predict them and thus automatically populate typological KBs, which is also the focus of this shared task. Overall, the task attracted 8 submissions from 5 teams, out of which the most successful methods make use of such feature correlations. However, our error analysis reveals that even the strongest submitted systems struggle with predicting feature values for languages where few features are known.
Original language | English |
---|---|
Title of host publication | Proceedings of the Second Workshop on Computational Research in Linguistic Typology |
Number of pages | 11 |
Place of Publication | Online |
Publisher | Association for Computational Linguistics |
Publication date | 1 Nov 2020 |
Pages | 1-11 |
DOIs | |
Publication status | Published - 1 Nov 2020 |
Event | The Second Workshop on Computational Research in Linguistic Typology - Duration: 19 Nov 2020 → 20 Nov 2020 |
Workshop
Workshop | The Second Workshop on Computational Research in Linguistic Typology |
---|---|
Period | 19/11/2020 → 20/11/2020 |
Keywords
- Natural Language Processing