Zobrazeno 1 - 10
of 24
pro vyhledávání: '"Renduchintala, Adithya"'
Autor:
Roth, Holger R., Xu, Ziyue, Hsieh, Yuan-Ting, Renduchintala, Adithya, Yang, Isaac, Zhang, Zhihong, Wen, Yuhong, Yang, Sean, Lu, Kevin, Kersten, Kristopher, Ricketts, Camir, Xu, Daguang, Chen, Chester, Cheng, Yan, Feng, Andrew
In the ever-evolving landscape of artificial intelligence (AI) and large language models (LLMs), handling and leveraging data effectively has become a critical challenge. Most state-of-the-art machine learning algorithms are data-centric. However, as
Externí odkaz:
http://arxiv.org/abs/2402.07792
We introduce Tied-LoRA, a novel paradigm leveraging weight tying and selective training to enhance the parameter efficiency of Low-rank Adaptation (LoRA). Our exploration encompasses different plausible combinations of parameter training and freezing
Externí odkaz:
http://arxiv.org/abs/2311.09578
Recent work in multilingual translation advances translation quality surpassing bilingual baselines using deep transformer models with increased capacity. However, the extra latency and memory costs introduced by this approach may make it unacceptabl
Externí odkaz:
http://arxiv.org/abs/2206.02079
Is bias amplified when neural machine translation (NMT) models are optimized for speed and evaluated on generic test sets using BLEU? We investigate architectures and techniques commonly used to speed up decoding in Transformer-based models, such as
Externí odkaz:
http://arxiv.org/abs/2106.00169
Autor:
Ko, Wei-Jen, El-Kishky, Ahmed, Renduchintala, Adithya, Chaudhary, Vishrav, Goyal, Naman, Guzmán, Francisco, Fung, Pascale, Koehn, Philipp, Diab, Mona
The scarcity of parallel data is a major obstacle for training high-quality machine translation systems for low-resource languages. Fortunately, some low-resource languages are linguistically related or similar to high-resource languages; these relat
Externí odkaz:
http://arxiv.org/abs/2105.15071
Cross-lingual named-entity lexica are an important resource to multilingual NLP tasks such as machine translation and cross-lingual wikification. While knowledge bases contain a large number of entities in high-resource languages such as English and
Externí odkaz:
http://arxiv.org/abs/2104.08597
Transformer based models are the modern work horses for neural machine translation (NMT), reaching state of the art across several benchmarks. Despite their impressive accuracy, we observe a systemic and rudimentary class of errors made by transforme
Externí odkaz:
http://arxiv.org/abs/2104.07838
Autor:
Tuan, Yi-Lin, El-Kishky, Ahmed, Renduchintala, Adithya, Chaudhary, Vishrav, Guzmán, Francisco, Specia, Lucia
Quality estimation aims to measure the quality of translated content without access to a reference translation. This is crucial for machine translation systems in real-world scenarios where high-quality translation is needed. While many approaches ex
Externí odkaz:
http://arxiv.org/abs/2102.04020
Active learning (AL) algorithms may achieve better performance with fewer data because the model guides the data selection process. While many algorithms have been proposed, there is little study on what the optimal AL algorithm looks like, which wou
Externí odkaz:
http://arxiv.org/abs/2101.00977
Most neural machine translation systems are built upon subword units extracted by methods such as Byte-Pair Encoding (BPE) or wordpiece. However, the choice of number of merge operations is generally made by following existing recipes. In this paper,
Externí odkaz:
http://arxiv.org/abs/1905.10453