An Investigation of the Interactions Between Pre-Trained Word Embeddings, Character Models and POS Tags in Dependency Parsing
원문 초록
We provide a comprehensive analysis of the interactions between pre-trained word embeddings, character models and POS tags in a transition-based dependency parser. While previous studies have shown POS information to be less important in the presence of character models, we show that in fact there are complex interactions between all three techniques. In isolation each produces large improvements over a baseline system using randomly initialised word embeddings only, but combining them quickly leads to diminishing returns. We categorise words by frequency, POS tag and language in order to systematically investigate how each of the techniques affects parsing quality. For many word categories, applying any two of the three techniques is almost as good as the full combined system. Character models tend to be more important for low-frequency open-class words, especially in morphologically rich languages, while POS tags can help disambiguate high-frequency function words. We also show that large character embedding sizes help even for languages with small character sets, especially in morphologically rich languages.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
myNER: Contextualized Burmese Named Entity Recognition with Bidirectional LSTM and fastText Embeddings via Joint Training with POS Tagging
A Comparative Analysis of Static Word Embeddings for Hungarian
AthDGC: An Open Diachronic Greek Treebank with Indo-European Parallels
LingoLoop Attack: Trapping MLLMs via Linguistic Context and State Entrapment into Endless Loops
FiLLM -- A Filipino-optimized Large Language Model based on Southeast Asia Large Language Model (SEALLM)
Comparative Study of Zero-Shot Cross-Lingual Transfer for Bodo POS and NER Tagging Using Gemini 2.0 Flash Thinking Experimental Model
토론
이 논문과 연결된 포럼 글이 아직 없습니다.