What We’re Reading: Single-Queue Decoding for Neural Machine Translation

by Spence Green
1 Minute Read

The most popular way of finding a translation for a source sentence with a neural sequence-to-sequence model is a simple beam search. The target sentence is predicted one word at a time and after each prediction, a fixed number of possibilities (typically between 4 and 10) is retained for further exploration. This strategy can be suboptimal as these local hard decisions do not take the remainder of the translation into account and can not be reverted later on.

In this paper, the authors propose to tackle this problem by keeping a single stack of partial hypotheses with different lengths alive. If a previous decision turns out to be sub-optimal a few words later, it is now possible to revisit them. To make the determination the authors use an additional tiny neural network to predict the expected sentence length, for each source sentence and each partial translation. If the two differ significantly it is considered an indicator that a previous decision should be revisited.

Paper: Single-Queue Decoding for Neural Machine Translation
Authors: Raphael Shu, Hideki Nakayama
Venue: University of Tokyo

null

Keeping Your Data Secure in Lilt

2 Minute Read

In a world where data hacks and breaches seem to make front-page news more often than we’d like, a common question translators and businesses have about Lilt is usually: is my data safe? No need to worry. Lilt was built with that concern in mind. Read the answers below to some common questions about security in Lilt. Is my data shared with anyone? Your data is private to your Lilt account. It is never shared with other accounts and/or users. When you upload a translation memory or translate a document, those translations are only associated with your account. For Business customers, translation memories can be shared across your projects, but they are not shared with other users or third parties.

Read More

Build a Comprehensive AI Translation Strategy with Lilt + AWS: Webinar Recap

5 Minute Read

In today's globalized world, businesses are expected to communicate with customers in their native languages. With the help of AI, modern translation technology has made it easier to attain quicker, better quality, and more efficient results than ever before. In this webinar, we discuss how Lilt and AWS can help you build a comprehensive AI translation strategy. We cover the benefits of using AI for translation, how Lilt and AWS can work together, the different features and capabilities of Amazon Translate, Lilt's Verified Translation Solution and AI Data Studio, and security and compliance considerations. Below are three takeaways from the 40-minute webinar, which you can watch in full here.

Read More