Abstract
Evaluating the complexity of a target word in a sentential context is the aim of the Lexical Complexity Prediction task at SemEval-2021. This paper presents the system created to assess single words lexical complexity, combining linguistic and psycholinguistic variables in a set of experiments involving random forest and XGboost regressors. Beyond encoding out-of-context information about the lemma, we implemented features based on pre-trained language models to model the target word’s in-context complexity.
Highlights
1 Introduction psycholinguistic variables, using a random forest regressor and an XGboost regressor
We experiment with different language models in a masked word prediction framework, taking into account the first ten most probable words occurring in that context
We introduce the system used to assess single English words lexical complexity at SemEval-2021 Lexical Complexity Prediction task (Shardlow et al, 2021)
Summary
A wide range of approaches has been used for lexical complexity prediction in past evaluation campaigns. If we frame lexical complexity as a measure strongly dependent on words’ psycholinguistic properties, we should recognize that past computational efforts for predicting word norms did not take into account the role of context (Russo, 2020; Charbonnier and Wartena, 2019) Static word embeddings such as word2vec have been used to predict values of psycholinguist norms usually assessed in experimental settings (Ljubesicet al., 2018; Rothe and Schutze, 2016). In LCP2021 lexical complexity is a continuous property, and the task consists of predicting the complexity score for each target word in context. Sub-task 1: predicting the complexity score of single words; Sentences are extracted from three domains: the Bible, the English part of the European Parliament proceedings, and a biomedical corpus composed of scientific papers. The age of acquisition of words is another variable strongly correlated with the complexity of the target words (r=0.55)
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
