DE eng

Search in the Catalogues and Directories

Hits 1 – 6 of 6

1
Explorations in Transfer Learning for OCR Post-Correction ...
BASE
Show details
2
Distributionally Robust Multilingual Machine Translation ...
BASE
Show details
3
When is Wall a Pared and when a Muro?: Extracting Rules Governing Lexical Selection ...
BASE
Show details
4
Lexically-Aware Semi-Supervised Learning for OCR Post-Correction ...
BASE
Show details
5
Phrase-level Active Learning for Neural Machine Translation ...
Abstract: Neural machine translation (NMT) is sensitive to domain shift. In this paper, we address this problem in an active learning setting where we can spend a given budget on translating in-domain data, and gradually fine-tune a pre-trained out-of-domain NMT model on the newly translated data. Existing active learning methods for NMT usually select sentences based on uncertainty scores, but these methods require costly translation of full sentences even when only one or two key phrases within the sentence are informative. To address this limitation, we re-examine previous work from the phrase-based machine translation (PBMT) era that selected not full sentences, but rather individual phrases. However, while incorporating these phrases into PBMT systems was relatively simple, it is less trivial for NMT systems, which need to be trained on full sequences to capture larger structural properties of sentences unique to the new domain. To overcome these hurdles, we propose to select both full sentences and individual ...
Keyword: Bilingual Lexicon Induction; Computational Linguistics; Language Models; Machine Learning; Machine Learning and Data Mining; Machine translation; Natural Language Processing
URL: https://dx.doi.org/10.48448/a5he-ja64
https://underline.io/lecture/39477-phrase-level-active-learning-for-neural-machine-translation
BASE
Hide details
6
Dependency Induction Through the Lens of Visual Perception ...
BASE
Show details

Catalogues
0
0
0
0
0
0
0
Bibliographies
0
0
0
0
0
0
0
0
0
Linked Open Data catalogues
0
Online resources
0
0
0
0
Open access documents
6
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern