Social media giant Meta proposes new metric to enable more consistency in human evaluation of machine translation; addresses big challenge in translation QA for low-resource language pairs.
To be fair, this is the first-ever multilingual model to win the international machine translation contest. But major tech companies have been exploring multilingual models for years.
As machine translation gets better, the problem of bias — especially gender bias — remains a source of embarrassment for the industry. Why MT bias matters and how major players are trying to fix it.
Researchers tracked CO2 emissions from training German, French, and English machine translation engines, and found this language pair to be most carbon-intensive.
Combing through papers released from 2010 to 2020, researchers identify overreliance on metric BLEU to the exclusion of 100+ alternatives — a major weak point.
Facebook, Naver, and George Mason University release open-sourced metric based on Covid-19 terms; hope to bridge gap between academia and industry.
Scientists propose new system to standardize automatic evaluation of NLP systems by adding humans in the loop; encourage fellow researchers to submit text generation models for evaluation.
Though beam search can boost BLEU scores, it can also lead to high rates of misgendered pronouns, even when translating between two gendered languages.
The most-cited neural machine translation research papers show how NMT came to dominate the field — and how academia and industry’s interests have evolved.
Google study shows human-paraphrased reference translations and new evaluation metric, BLEUP, produce better translations. Findings to be integrated into consumer-facing products.
Facebook AI invites developers to improve a speech translation dataset and a open sources a toolkit that evaluates simultaneous speech and text translation.
Association for Computational Linguistics names Best Research Papers of 2020 from a field of more than 3,000 submissions; paper that argues for retiring BLEU is runner-up.
As machine translation quality improves, precision-based metrics struggle to identify the best systems. Why have newer metrics not ousted longtime standard BLEU?
As the language industry transitions to an operating model where the first draft is mostly generated by machines, many are looking for ways to quantify linguists' value-add. Edit-distance can help.
Google has admitted machine translated content is a challenge to ranking algorithms. Researchers at the University of Tokyo may have found a solution: back-translation.
NVIDIA Senior Deep Learning Engineer Chip Huyen details progress on MT challenges, including data requirements, sentence-length limitations, and imperfect quality evaluation techniques.
Facebook has been granted a patent for its machine translation quality evaluation system, which relies on user engagement data to decide which translation users prefer.
At SlatorCon London 2019, Systran CEO Jean Senellart outlined the latest in NMT developments, called out some myths from vendors, and pointed out what’s missing from the industry.
August 2018 became the busiest month ever for neural machine translation research as more papers call for improved evaluation methods and big tech companies step up the number of submissions.
Microsoft’s “human parity” claims drew skepticism from a team of neural machine translation researchers as they found that much of the research and industry community is looking at the problem from the wrong angle.
Your information will never be shared with third parties. No Spam.