Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

SpaCy 3.0

github.com

Post reply on HN
Print view View original

51–60 of 82 posts

Re: SpaCy 3.0

#51

Post by hantusk »

tedivm wrote: post #31
syllogism wrote: post #25

Earlier quoted context omitted.

Thanks for the love :). For the record yes we've been working hard, but also yes, we've been doing well from it. I will say that people are using spaCy for free because that is what we asked them to do. I chose to make the library free and open-source when I first released it because I had the idea that I would be able to make that work out for me, if I could make this thing that would be useful to people and if they…

The only thing that Prodigy is missing is a team based workflow. We've been on the beta list for awhile for it, and are excited for it to come out- but without having a concept of users we've had to use other tools that aren't as polished on the annotation side but which hit our compliance needs.

This. Wholly agree. Currently running a large labelling task with 12 labelers.

Using Amazon ground truth which works fine (although seems quite MVP outside the core functionality e.g wrt reporting or user creation).

What tool have you had success with?

Re: SpaCy 3.0

#52

Post by svlandeg »

Xenoamorphous wrote: post #39

I think I read somewhere that spaCy was going to have named entity disambiguation at some point, with named entities having links to knowledge bases like Wikidata or DBpedia. That’s something that paid NER services but that I haven’t found in open source libs, and would be really interesting IMO.

There's a component for Entity Linking available in spaCy, but you have to train it yourself, as the use-cases (type of entities, type of knowledge base etc) can vary greatly. See more here: https://spacy.io/api/entitylinker

Re: SpaCy 3.0

#53

Post by binarymax »

microtonal wrote: post #14
binarymax wrote: post #6

Earlier quoted context omitted.

I have lots of experience with both, and I use both together for different use cases. SpaCy fills the need of predictable/explainable pattern matching and NER - and is very fast and reasonably accurate on a CPU. Huggingface fills the need for task based prediction when you have a GPU.

Huggingface fills the need for task based prediction when you have a GPU. With model distillation, you can make models that annotate hundreds of sentences per second on a single CPU with a library like Huggingface Transformers. For instance, one of my distilled Dutch multi-task syntax models (UD POS, language-specific POS, lemmatization, morphology, dependency parsing) annotates 316 sentences per second with 4 thread…

Interesting. Did you start from a Distilled base model (like DistilRoBerta), or did you distill your fine-tuned model?

Re: SpaCy 3.0

#54

Post by liminal »

I'm curious what sort of NLP use cases people are solving. How are people finding business value in these models and pipelines? We have looked at a number of uses and have found it hard to make a case for ROI. Wondering what's been working for folks.

Re: SpaCy 3.0

#55

Post by slow_donkey »

joshklein wrote: post #30
syllogism wrote: post #25

Earlier quoted context omitted.

Thanks for the love :). For the record yes we've been working hard, but also yes, we've been doing well from it. I will say that people are using spaCy for free because that is what we asked them to do. I chose to make the library free and open-source when I first released it because I had the idea that I would be able to make that work out for me, if I could make this thing that would be useful to people and if they…

I want to personally thank you for your work, and let you know I couldn’t have done an important project of mine if spaCy didn’t exist, and if it were not a free resource. Your project was 1 of the 2 instrumental tools in my project to structure the transcripts of every word said on the floor of the New York State Senate over the past ~30 years in order to develop a topic-based “proximity” heuristic (based on CorEx,…

This sounds super cool, is there a public link to your work? I'd love to check it out

Re: SpaCy 3.0

#56

Post by aabhay »

liminal wrote: post #54

I'm curious what sort of NLP use cases people are solving. How are people finding business value in these models and pipelines? We have looked at a number of uses and have found it hard to make a case for ROI. Wondering what's been working for folks.

Agreed. The larger and deeper the model, the more the use cases seem to become negative ROI. I think for business use there will have to be an effort to compress the architecture considerably

Re: SpaCy 3.0

#57

Post by aabhay »

microtonal wrote: post #14
binarymax wrote: post #6

Earlier quoted context omitted.

I have lots of experience with both, and I use both together for different use cases. SpaCy fills the need of predictable/explainable pattern matching and NER - and is very fast and reasonably accurate on a CPU. Huggingface fills the need for task based prediction when you have a GPU.

Huggingface fills the need for task based prediction when you have a GPU. With model distillation, you can make models that annotate hundreds of sentences per second on a single CPU with a library like Huggingface Transformers. For instance, one of my distilled Dutch multi-task syntax models (UD POS, language-specific POS, lemmatization, morphology, dependency parsing) annotates 316 sentences per second with 4 thread…

Is there a standard template for creating a distilled model? I didn’t see a public hugging face implementation, just the models

Re: SpaCy 3.0

#58

Post by kthejoker2 »

drran wrote: post #45
JPKab wrote: post #19

Earlier quoted context omitted.

Everything in the above paragraph sounds like a hyped overstatement. None of it is. As someone that's worked on some rather intensive NLP implementations, Spacy 3.0 and HuggingFace both represent the culmination of a technological leap in NLP that started a few years ago with the advent of transfer learning in NLP. The level of accessibility to the masses these libraries offer is game-changing and democratizing.

Can you help, please? I want to use AI to translate (localize) messages for free software, in my case, Ukrainian language. My plan to improve quality of automated translation is to translate from similar languages in parallel, i.e. give a same message in English, Russian, Polish, and expect message in Ukrainian as output. Where I should start? Which libraries to use? How to connect them? How to train them?

MarianMT has a lot of pre-trained models from one language to another, here is one for Polish to Ukrainian

https://huggingface.co/Helsinki-NLP/opus-mt-pl-uk

and English to Ukrainian

https://huggingface.co/Helsinki-NLP/opus-mt-en-uk

You can test the models with the form input on the right-hand side

And here's a site with docs and code examples for basic usage in your app

https://huggingface.co/transformers/model_doc/marian.html

You can also use Marian's training code on PyTorch with custom source and target texts.

Re: SpaCy 3.0

#59

Post by joshklein »

slow_donkey wrote: post #55
joshklein wrote: post #30

Earlier quoted context omitted.

I want to personally thank you for your work, and let you know I couldn’t have done an important project of mine if spaCy didn’t exist, and if it were not a free resource. Your project was 1 of the 2 instrumental tools in my project to structure the transcripts of every word said on the floor of the New York State Senate over the past ~30 years in order to develop a topic-based “proximity” heuristic (based on CorEx,…

This sounds super cool, is there a public link to your work? I'd love to check it out

I haven’t written about it or made results publicly available yet, but I do intend to. I can make a note of the email in your profile and ping you with a link when it is available if you’d like.

Re: SpaCy 3.0

#60

Post by bertomart »

screye wrote: post #13

I have been using Spacy3 nightly for a while now. This is game changing. Spacy3 practically covers 90% of NLP use-cases with near SOTA performance. The only reason to not use it would be if you are literally pushing the boundaries of NLP or building something super specialized. Hugging Face and Spacy (also Pytorch, but duh) are saving millions of dollars in man hours for companies around the world. They've been a rev…

Does it have a question/answering component that's trainable/finetune-able on custom datasets?
Post reply on HN