What do character-level models learn about morphology? The case of dependency parsing
원문 초록
When parsing morphologically-rich languages with neural models, it is beneficial to model input at the character level, and it has been claimed that this is because character-level models learn morphology. We test these claims by comparing character-level models to an oracle with access to explicit morphological analysis on twelve languages with varying morphological typologies. Our results highlight many strengths of character-level models, but also show that they are poor at disambiguating some words, particularly in the face of case syncretism. We then demonstrate that explicitly modeling morphological case improves our best model, showing that character-level models can benefit from targeted forms of explicit morphological modeling.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
ÚFAL LatinPipe at EvaLatin 2024: Morphosyntactic Analysis of Latin
NLPre: a revised approach towards language-centric benchmarking of Natural Language Preprocessing systems
COMBO: State-of-the-Art Morphosyntactic Analysis
Step-by-step Instructions and a Simple Tabular Output Format Improve the Dependency Parsing Accuracy of LLMs
Hierarchical Bracketing Encodings for Dependency Parsing as Tagging
An Aspect Extraction Framework using Different Embedding Types, Learning Models, and Dependency Structure
토론
이 논문과 연결된 포럼 글이 아직 없습니다.