arXiv:2003.04419
Combining Pretrained High-Resource Embeddings and Subword Representations for Low-Resource Languages
원문 초록
The contrast between the need for large amounts of data for current Natural Language Processing (NLP) techniques, and the lack thereof, is accentuated in the case of African languages, most of which are considered low-resource. To help circumvent this issue, we explore techniques exploiting the qualities of morphologically rich languages (MRLs), while leveraging pretrained word vectors in well-resourced languages. In our exploration, we show that a meta-embedding approach combining both pretrained and morphologically-informed word embeddings performs best in the downstream task of Xhosa-English translation.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Speak2Sign3D: A Multi-modal Pipeline for English Speech to American Sign Language Animation
CycleVAR: Repurposing Autoregressive Model for Unsupervised One-Step Image Translation
CycleDistill: Bootstrapping Machine Translation using LLMs with Cyclical Distillation
Characterizing Linguistic Shifts in Croatian News via Diachronic Word Embeddings
Gender Bias in English-to-Greek Machine Translation
Mutual-Supervised Learning for Sequential-to-Parallel Code Translation
토론
이 논문과 연결된 포럼 글이 아직 없습니다.