Predicting Pronouns across Languages with Continuous Word Spaces
Ngoc-Quan Pham, Lonneke van der Plas · 2015
Predicting pronouns across languages from a language with less variation to one with much more is a hard task that requires many different types of information, such as morpho-syntactic information as well as lexical semantics and coreference. We assumed that continuous word spaces fed into a multi-layer perceptron enriched with morphological tags and coreference resolution would be able to capture many of the linguistic regularities we found. Our results show that the model captures most of the linguistic generalisations. Its macro-averaged F-score is among the top-3 systems submitted to the DiscoMT shared task reaching 56.5%.