Výsledky vyhledávání - "Ward, Todd A."

Report

Bootstrapping Multilingual AMR with Contextual Word Alignments

Autor: Sheth, Janaki, Lee, Young-Suk, Astudillo, Ramon Fernandez, Naseem, Tahira, Florian, Radu, Roukos, Salim, Ward, Todd

Publikováno v: EACL 2021

We develop high performance multilingualAbstract Meaning Representation (AMR) sys-tems by projecting English AMR annotationsto other languages with weak supervision. Weachieve this goal by bootstrapping transformer-based multilingual word embeddings,

Externí odkaz: http://arxiv.org/abs/2102.02189

Zobrazit plný text záznamu

Report

Multi-Stage Pre-training for Low-Resource Domain Adaptation

Autor: Zhang, Rong, Reddy, Revanth Gangi, Sultan, Md Arafat, Castelli, Vittorio, Ferritto, Anthony, Florian, Radu, Kayi, Efsun Sarioglu, Roukos, Salim, Sil, Avirup, Ward, Todd

Transfer learning techniques are particularly useful in NLP tasks where a sizable amount of high-quality annotated data is difficult to obtain. Current approaches directly adapt a pre-trained language model (LM) on in-domain text before fine-tuning t

Externí odkaz: http://arxiv.org/abs/2010.05904

Zobrazit plný text záznamu

Report

The TechQA Dataset

We introduce TechQA, a domain-adaptation question answering dataset for the technical support domain. The TechQA corpus highlights two real-world issues from the automated customer support domain. First, it contains actual questions posed by users on

Externí odkaz: http://arxiv.org/abs/1911.02984

Zobrazit plný text záznamu

Report

Multilingual Neural Machine Translation with Task-Specific Attention

Autor: Blackwood, Graeme, Ballesteros, Miguel, Ward, Todd

Multilingual machine translation addresses the task of translating between multiple source and target languages. We propose task-specific attention models, a simple but effective technique for improving the quality of sequence-to-sequence neural mult

Externí odkaz: http://arxiv.org/abs/1806.03280

Zobrazit plný text záznamu