Strong Baselines for Complex Word Identification across Multiple Languages
This work provides strong baselines for CWI, a task important for improving text accessibility for non-native speakers or learners, but it is incremental as it builds on existing shared task data and methods.
The paper tackles the problem of Complex Word Identification (CWI) across monolingual and cross-lingual settings by developing models that achieve state-of-the-art performance, matching or surpassing most entries in a recent shared task, using carefully selected features and simple learning methods.
Complex Word Identification (CWI) is the task of identifying which words or phrases in a sentence are difficult to understand by a target audience. The latest CWI Shared Task released data for two settings: monolingual (i.e. train and test in the same language) and cross-lingual (i.e. test in a language not seen during training). The best monolingual models relied on language-dependent features, which do not generalise in the cross-lingual setting, while the best cross-lingual model used neural networks with multi-task learning. In this paper, we present monolingual and cross-lingual CWI models that perform as well as (or better than) most models submitted to the latest CWI Shared Task. We show that carefully selected features and simple learning models can achieve state-of-the-art performance, and result in strong baselines for future development in this area. Finally, we discuss how inconsistencies in the annotation of the data can explain some of the results obtained.