Translation

Researchers pushed the boundaries of language models to address persistent problems of trustworthiness, bias, and updatability.

Most speech-to-speech translation systems use text as an intermediate mode. So how do you build an automated translator for a language that has no standard written form? A new approach trained neural networks to translate a primarily oral language.

Recent work showed that models for multilingual machine translation can increase the number of languages they translate by scraping the web for pairs of equivalent sentences in different languages. A new study radically expanded the language repertoire through training on untranslated web text.

The filmmakers used technology from Flawless AI to clean up the language, enabling the film to earn a rating that welcomes younger viewers.

A startup that automatically translates video voice overs into different languages is ready for its big break. London-based Papercup offers a voice translation service that combines algorithmic translation and voice synthesis with human-in-the-loop quality control.

People granted early access to OpenAI’s latest language model are raving about its way with words — and more. Beta testers of GPT-3 are showing off the model’s ability to write business memos, craft blogs, pen tweets, and even generate computer code.

The words “big” and “large” have similar meanings, but they aren’t always interchangeable: You wouldn’t refer to an older, male sibling as your “large brother” (unless you meant to be cheeky). Choosing among words with similar meanings is critical in language tasks like translation.

Language models can’t correct your misspellings or suggest the next word in a text without knowing what language you’re using. For instance, if you type “tac-,” are you aiming for “taco,” a hand-held meal in Spanish, or “taca,” a crown in Turkish?

Like nurses who can’t decipher a doctor’s handwriting, machine learning models can’t decipher medical scans — without labels. Conveniently, natural language models can read medical records to extract labels for X-ray images.

AI has added an unlikely language to its catalog of translation capabilities: brain waves. Joseph Makin led a group from the University of California San Francisco to render a person’s neural signals as English text while the person while the person read a sentence aloud.

Machine learning promises to streamline handling of tomorrow’s bureaucratic drudgery — and, it turns out, that of 2,500 years ago. Computer vision is helping researchers at the University of Chicago translate a massive collection of ancient records inscribed on clay tablets.

Softmax commonly computes probabilities in a classifier’s output layer. But softmax isn’t always accurate in complex tasks — say, in a natural-language task, when the length of word vectors is much smaller than the number of words in the vocabulary.

In tasks that involve generating natural language, neural networks often map an input sequence of words to an output sequence of words. Facebook researchers used a similar technique on sequences of mathematical symbols, training a model to map math problems to math solutions.

Earlier language models powered by Word2Vec and GloVe embeddings yielded confused chatbots, grammar tools with middle-school reading comprehension, and not-half-bad translations. The latest generation is so good, some people consider it dangerous.

More than 900 indigenous languages are spoken across the Americas, nearly half of all tongues in use worldwide. A website tracks the growing number of resources available for natural language processing researchers interested in studying, learning from, and saving these fading languages.