Improving Rare Word Translation With Dictionaries and Attention Masking
Not on the map. Why?
Abstract (arXiv)
In machine translation, rare words continue to be a problem for the dominant encoder-decoder architecture, especially in low-resource and out-of-domain translation settings. Human translators solve this problem with monolingual or bilingual dictionaries. In this paper, we propose appending definitions from a bilingual dictionary to source sentences and using attention masking to link together rare words with their definitions. We find that including definitions for rare words improves performance by up to 1.0 BLEU and 1.6 MacroF1.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 12 of its 29 references that are in the map. First posted on arXiv 17 Aug 2024.
Builds on
12 of 29 references.
References · 12
- 2017Attention Is All You Needcited by 59,932
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
- 2018A Call for Clarity in Reporting BLEU Scorescited by 1,790
- 2018Fast Lexically Constrained Decoding with Dynamic Beam Allocation for Neural Machine Translationcited by 181
- 2019Transformers without Tears: Improving the Normalization of Self-Attentioncited by 153
- 2017Data Augmentation for Low-Resource Neural Machine Translationcited by 139
- 2023A Paradigm Shift in Machine Translation: Boosting Translation Performance of Large Language Modelscited by 88
- 2019Training Neural Machine Translation To Apply Terminology Constraintscited by 73
- 2017DiSAN: Directional Self-Attention Network for RNN/CNN-Free Language Understandingcited by 71
- 2016Bridging Neural Machine Translation and Bilingual Dictionariescited by 18
- 2021Continuous Learning in Neural Machine Translation using Bilingual Dictionariescited by 11
- 2021Macro-Average: Rare Types Are Important Toocited by 4
Built on by
Citing papers per year: 2024: 1; 2025: 1.
2 papers.