arXiv:1808.09733
공식 코드 · Papers with Code
Distant Supervision from Disparate Sources for Low-Resource Part-of-Speech Tagging
원문 초록
We introduce DsDs: a cross-lingual neural part-of-speech tagger that learns from disparate sources of distant supervision, and realistically scales to hundreds of low-resource languages. The model exploits annotation projection, instance selection, tag dictionaries, morphological lexicons, and distributed representations, all in a uniform framework. The approach is simple, yet surprisingly effective, resulting in a new state of the art without access to any gold annotated data.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
J2N -- Nominal Adjective Identification and its Application
myNER: Contextualized Burmese Named Entity Recognition with Bidirectional LSTM and fastText Embeddings via Joint Training with POS Tagging
Comparative Study of Zero-Shot Cross-Lingual Transfer for Bodo POS and NER Tagging Using Gemini 2.0 Flash Thinking Experimental Model
Author-Specific Linguistic Patterns Unveiled: A Deep Learning Study on Word Class Distributions
Bangla Parts-of-Speech Tagging using Bangla Stemmer and Rule based Analyzer
MBT: A Memory-Based Part of Speech Tagger-Generator
토론
이 논문과 연결된 포럼 글이 아직 없습니다.