Zobrazeno 1 - 10
of 193
pro vyhledávání: '"ZENG Jiali"'
Large language models (LLMs) have achieved reasonable quality improvements in machine translation (MT). However, most current research on MT-LLMs still faces significant challenges in maintaining translation consistency and accuracy when processing e
Externí odkaz:
http://arxiv.org/abs/2410.08143
Large language models (LLMs) have exhibited remarkable performance in various natural language processing tasks. Techniques like instruction tuning have effectively enhanced the proficiency of LLMs in the downstream task of machine translation. Howev
Externí odkaz:
http://arxiv.org/abs/2406.08434
Publikováno v:
EMNLP2024 Findings
The fine-tuning of open-source large language models (LLMs) for machine translation has recently received considerable attention, marking a shift towards data-centric research from traditional neural machine translation. However, the area of data col
Externí odkaz:
http://arxiv.org/abs/2406.01441
Neural Machine Translation (NMT) has made remarkable progress over the past years. However, under-translation and over-translation remain two challenging problems in state-of-the-art NMT systems. In this work, we conduct an in-depth analysis on the u
Externí odkaz:
http://arxiv.org/abs/2405.18922
Contemporary translation engines based on the encoder-decoder framework have made significant strides in development. However, the emergence of Large Language Models (LLMs) has disrupted their position by presenting the potential for achieving superi
Externí odkaz:
http://arxiv.org/abs/2311.02851
Open-sourced large language models (LLMs) have demonstrated remarkable efficacy in various tasks with instruction tuning. However, these models can sometimes struggle with tasks that require more specialized knowledge such as translation. One possibl
Externí odkaz:
http://arxiv.org/abs/2307.04408
Autor:
Zeng, Jiali, Jiang, Yufan, Yin, Yongjing, Jing, Yi, Meng, Fandong, Lin, Binghuai, Cao, Yunbo, Zhou, Jie
Multilingual pre-trained language models have demonstrated impressive (zero-shot) cross-lingual transfer abilities, however, their performance is hindered when the target language has distant typology from source languages or when pre-training data i
Externí odkaz:
http://arxiv.org/abs/2306.07610
We present DualNER, a simple and effective framework to make full use of both annotated source language corpus and unlabeled target language text for zero-shot cross-lingual named entity recognition (NER). In particular, we combine two complementary
Externí odkaz:
http://arxiv.org/abs/2211.08104
Contrastive learning has become a new paradigm for unsupervised sentence embeddings. Previous studies focus on instance-wise contrastive learning, attempting to construct positive pairs with textual data augmentation. In this paper, we propose a nove
Externí odkaz:
http://arxiv.org/abs/2211.03348
Unsupervised summarization methods have achieved remarkable results by incorporating representations from pre-trained language models. However, existing methods fail to consider efficiency and effectiveness at the same time when the input document is
Externí odkaz:
http://arxiv.org/abs/2208.08253