Artificially Evolved Chunks for Morphosyntactic Analysis
원문 초록
We introduce a language-agnostic evolutionary technique for automatically extracting chunks from dependency treebanks. We evaluate these chunks on a number of morphosyntactic tasks, namely POS tagging, morphological feature tagging, and dependency parsing. We test the utility of these chunks in a host of different ways. We first learn chunking as one task in a shared multi-task framework together with POS and morphological feature tagging. The predictions from this network are then used as input to augment sequence-labelling dependency parsing. Finally, we investigate the impact chunks have on dependency parsing in a multi-task framework. Our results from these analyses show that these chunks improve performance at different levels of syntactic abstraction on English UD treebanks and a small, diverse subset of non-English UD treebanks.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
J2N -- Nominal Adjective Identification and its Application
Open-Source Web Service with Morphological Dictionary-Supplemented Deep Learning for Morphosyntactic Analysis of Czech
calamanCy: A Tagalog Natural Language Processing Toolkit
FiLLM -- A Filipino-optimized Large Language Model based on Southeast Asia Large Language Model (SEALLM)
Analyzing the Effect of Linguistic Similarity on Cross-Lingual Transfer: Tasks and Experimental Setups Matter
MRL Parsing Without Tears: The Case of Hebrew
토론
이 논문과 연결된 포럼 글이 아직 없습니다.