7 papers
Better heads do not guarantee better binarized constituency parsing
Zeyao Qi, Yige Chen, Eitan Klinger +2
We revisit punctuation-aware tree binarization for constituency parsing and ask whether dependency-induced headedness improves binary parser supervision. Although learned heads sub…
Learning Constituent Headedness
Zeyao Qi, Yige Chen, KyungTae Lim +2
Headedness is widely used as an organizing device in syntactic analysis, yet constituency treebanks rarely encode it explicitly and most processing pipelines recover it procedurall…
A Formal Framework for Fluency-based Multi-Reference Evaluation in Grammatical Error Correction
Eitan Klinger, Zihao Huang, Tran Minh Nguyen +7
Evaluating grammatical error correction requires metrics that reflect the diversity of valid human corrections rather than privileging a single reference. Existing frameworks, larg…
Parsing Through Boundaries in Chinese Word Segmentation
Yige Chen, Zelong Li, Cindy Zhang +7
Chinese word segmentation is a foundational task in natural language processing (NLP), with far-reaching effects on syntactic analysis. Unlike alphabetic languages like English, Ch…
Unlocking Korean Verbs: A User-Friendly Exploration into the Verb Lexicon
Seohyun Song, Eunkyul Leah Jo, Yige Chen +7
The Sejong dictionary dataset offers a valuable resource, providing extensive coverage of morphology, syntax, and semantic representation. This dataset can be utilized to explore l…
Enhancing Korean Dependency Parsing with Morphosyntactic Features
Jungyeul Park, Yige Chen, Kyuwon Kim +2
This paper introduces UniDive for Korean, an integrated framework that bridges Universal Dependencies (UD) and Universal Morphology (UniMorph) to enhance the representation and pro…