MaiNLP at SemEval-2024 Task 1: Analyzing Source Language Selection in Cross-Lingual Textual Relatedness
원문 초록
This paper presents our system developed for the SemEval-2024 Task 1: Semantic Textual Relatedness (STR), on Track C: Cross-lingual. The task aims to detect semantic relatedness of two sentences in a given target language without access to direct supervision (i.e. zero-shot cross-lingual transfer). To this end, we focus on different source language selection strategies on two different pre-trained languages models: XLM-R and Furina. We experiment with 1) single-source transfer and select source languages based on typological similarity, 2) augmenting English training data with the two nearest-neighbor source languages, and 3) multi-source transfer where we compare selecting on all training languages against languages from the same family. We further study machine translation-based data augmentation and the impact of script differences. Our submission achieved the first place in the C8 (Kinyarwanda) test set.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Limited-Resource Adapters Are Regularizers, Not Linguists
Building a Functional Machine Translation Corpus for Kpelle
DeFTX: Denoised Sparse Fine-Tuning for Zero-Shot Cross-Lingual Transfer
Cross-Linguistic Transfer in Multilingual NLP: The Role of Language Families and Morphology
Data-Efficient Hate Speech Detection via Cross-Lingual Nearest Neighbor Retrieval with Limited Labeled Data
Towards Cultural Bridge by Bahnaric-Vietnamese Translation Using Transfer Learning of Sequence-To-Sequence Pre-training Language Model
토론
이 논문과 연결된 포럼 글이 아직 없습니다.