Published May 12, 2020
| Version v1
Conference paper
Open
Implementation of Supervised Training Approaches forMonolingual Word Sense Alignment:ACDH-CH System Description for the MWSA Shared Task at GlobaLex 2020
Description
This paper describes the ACDH-CH system for monolingual sense alignment across dictionaries. The task of monolingual word sense alignment is presented as a task of predicting the relationship between two senses. We present two solutions, one based on supervised machine learning, and the other based on pre-trained neural network language model, specifically BERT. Our models perform competitively for binary classification, reporting high scores for almost all languages.
Files
Monolingual_WSA-4.pdf
Files
(151.7 kB)
Name | Size | Download all |
---|---|---|
md5:41804821989f52596b122fa164f57820
|
151.7 kB | Preview Download |