Summary of On Translating Technical Terminology: a Translation Workflow For Machine-translated Acronyms, by Richard Yue et al.
On Translating Technical Terminology: A Translation Workflow for Machine-Translated Acronyms
by Richard Yue, John E. Ortega, Kenneth Ward Church
First submitted to arxiv on: 26 Sep 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper proposes an approach to improve machine translation systems by addressing the problem of acronym disambiguation. Typically, professional translators translate documents from their source language to a target language, whereas language models in NLP predict the next word in a series. While high-resource languages like English and French achieve near-human parity using metrics like BLEU and COMET, the paper highlights the importance of translating technical terms, specifically acronyms. Current state-of-the-art machine translation systems, such as Google Translate, can be erroneous when dealing with acronyms, with an error rate of up to 50% in our findings. The proposed approach involves creating a new acronym corpus and experimenting with a search-based thresholding algorithm that achieves a nearly 10% increase compared to existing systems like Google Translate and OpusMT. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper is about making machine translation better by solving a problem called acronym disambiguation. Usually, people who translate documents don’t worry too much about words that are shortened versions of longer phrases. But computers that translate languages often get these short words wrong, which can be a big deal. The researchers found that even popular translation systems like Google Translate can make mistakes with these short words, getting them wrong up to 50% of the time. To fix this problem, the paper suggests creating a new collection of short words and using an algorithm to help computers translate them correctly. This could improve translations by about 10%. |
Keywords
» Artificial intelligence » Bleu » Nlp » Translation
