Detecting Multiword Expression Type Helps Lexical Complexity Assessment

Abstract

Multiword expressions (MWEs) represent lexemes that should be treated as single lexical units due to their idiosyncratic nature. Multiple NLP applications have been shown to benefit from MWE identification, however the research on lexical complexity of MWEs is still an under-explored area. In this work, we re-annotate the Complex Word Identification Shared Task 2018 dataset of Yimam et al. ( 2017), which provides complexity scores for a range of lexemes, with the types of MWEs. We release the MWE-annotated dataset with this paper, and we believe this dataset represents a valuable resource for the text simplification community. In addition, we investigate which types of expressions are most problematic for native and non-native readers. Finally, we show that a lexical complexity assessment system benefits from the information about MWE types.

A Phraseology Approach in Developmental Education Placement

“…Still, results seem to signal the importance of using information on MWE in this task. This is in line with the literature findings on similar scenarios [7]. A proper PoS-tagging of MWE, combined with an appropriate classification of MWE types 9 may contribute to improving results and providing more robust insights on DevEd students' writing patterns.…”

“…For the manual identification of MWE, the set of linguistic criteria adopted derived from the literature [3]. The MWE categories of [7] and the caveats by [8] were particularly insightful. Based on these criteria, the annotation of MWE in the corpus included multiple categories, based on traditional classification guidelines and lists available in dictionaries, e.g., compound nouns: golden rule, refresher course; compound adjectives: (stay) tall and straight, (be) on [one's] feet; strong minded ; compound conjunctions and prepositions: as long as, in spite of ; compound adverbs: by the way, back in the old day; verbal idioms: see the bigger picture, knock at your door ; weigh the pros and cons; phrasal verbs: fit in, mess up; support verb constructions: have no clue, make mistakes; among others.…”