Neural Machine Translation in Linear Time · HackerPapers discussions

Neural Machine Translation in Linear Time — mentioned by talolard

Tue, 31 Jan 2023 10:08:01 GMT

I'm a native Hebrew speaker, where we have wild word morphology, and also worked on NLP at a large bank where we trained models to anlyze Bloomberg chats (that are almost english but behave like a DSL). In both cases, "token-free" has been the way to go for extractive tasks like entity recognition. It's unfortunately a technique that is off the beaten path, so a lot of extra engineering effort needs to be paid down. For example, when dealing with spans but embedding the text at the byte level, one needs to account for multi-byte codepoints that can throw off the alignment between "encoded"…

Paper and discussion history. A mention is not an endorsement.

Neural Machine Translation in Linear Time — mentioned by dharma1

Fri, 11 Nov 2016 15:34:51 GMT

Really like what you're doing with SpaCy and explosionAI, good stuff :) What do you think about dilated convolutional encoder/decoder networks [1]? Useful for NLP beyond machine translation? [1] https://arxiv.org/abs/1610.10099, https://github.com/paarthneekhara/byteNet-tensorflow

Paper and discussion history. A mention is not an endorsement.

Neural Machine Translation in Linear Time — HN submission

Tue, 01 Nov 2016 15:21:05 GMT

Neural Machine Translation in Linear Time

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Neural Machine Translation in Linear Time — HN submission

Tue, 01 Nov 2016 05:31:33 GMT

Neural Machine Translation in Linear Time

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.