Advanced NLP with spaCy v3
course.spacy.io
Advanced NLP with spaCy v3
1–10 of 40 posts
Re: Advanced NLP with spaCy v3
#2We've been using spaCy a lot for the past few months.
Mostly for non-production use cases, however, I can say that it is the most robust framework for NLP at the moment.
V3 added support for transformers: that's a killer feature as many models from https://huggingface.co/docs/transformers/index work great out of the box.
At the same time, I found NER models provided by spaCy to have a low accuracy while working with real data: we deal with news articles https://demo.newscatcherapi.com/
Also, while I see how much attention ML models get from the crowd, I think that many problems can be solved with rule-based approach: and spaCy is just amazing for these.
Btw, we recently wrote a blog post comparing spaCy to NLTK for text normalization task: https://newscatcherapi.com/blog/spacy-vs-nltk-text-normaliza...
Re: Advanced NLP with spaCy v3
#3We've been using spaCy a lot for the past few months. Mostly for non-production use cases, however, I can say that it is the most robust framework for NLP at the moment. V3 added support for transformers: that's a killer feature as many models from https://huggingface.co/docs/transformers/index work great out of the box. At the same time, I found NER models provided by spaCy to have a low accuracy while working with…
Also I have an article about spaCy NER: https://newscatcherapi.com/blog/named-entity-recognition-wit...
The conclusion I came up with:
"A few notes on my Spacy NER accuracy with "real world" data
Low accuracy with sentences without a proper casing
1. Low accuracy overall, even with a large model
2. You'd need to fine-tune your model if you want to use it in production
3. Overall, there's no open-source high accuracy NER model that you can use out-of-a-box"
Re: Advanced NLP with spaCy v3
#4A relatively underdiscussed quirk of the rise of superlarge language models like GPT-3 for certain NLP tasks is that since those models have incorporated so much real world grammar, there's no need to do advanced preprocessing and can just YOLO and work with generated embeddings instead without going into spaCy's (excellent) parsing/NER features.
OpenAI recently released an Embeddings API for GPT-3 with good demos and explanations: https://beta.openai.com/docs/guides/embeddings
Hugging Face Transformers makes this easier (and for free) as most models can be configured to return a "last_hidden_state" which will return the aggregated embedding. Just use DistilBERT uncased/cased (which is fast enough to run on consumer CPUs) and you're probably good to go.
Re: Advanced NLP with spaCy v3
#5We've been using spaCy a lot for the past few months. Mostly for non-production use cases, however, I can say that it is the most robust framework for NLP at the moment. V3 added support for transformers: that's a killer feature as many models from https://huggingface.co/docs/transformers/index work great out of the box. At the same time, I found NER models provided by spaCy to have a low accuracy while working with…
We use spaCy at work for (mostly) news articles as well. We've been pretty impressed with it overall for detecting larger trends using the NER models. I've been contemplating whether it might be useful to make a spaCy module that uses a Count-Min Sketch to track the top N of each of the NER categories partitioned on a daily (or weekly etc.) time.
Think it could be an interesting use case to get sort of similar results to Google's search trends.
Re: Advanced NLP with spaCy v3
#6We've been using spaCy a lot for the past few months. Mostly for non-production use cases, however, I can say that it is the most robust framework for NLP at the moment. V3 added support for transformers: that's a killer feature as many models from https://huggingface.co/docs/transformers/index work great out of the box. At the same time, I found NER models provided by spaCy to have a low accuracy while working with…
We use spaCy at work for (mostly) news articles as well. We've been pretty impressed with it overall for detecting larger trends using the NER models. I've been contemplating whether it might be useful to make a spaCy module that uses a Count-Min Sketch to track the top N of each of the NER categories partitioned on a daily (or weekly etc.) time. Think it could be an interesting use case to get sort of similar result…
I'd really love to chat about that. Any chance to connect? email in bio
Re: Advanced NLP with spaCy v3
#7We've been using spaCy a lot for the past few months. Mostly for non-production use cases, however, I can say that it is the most robust framework for NLP at the moment. V3 added support for transformers: that's a killer feature as many models from https://huggingface.co/docs/transformers/index work great out of the box. At the same time, I found NER models provided by spaCy to have a low accuracy while working with…
Also I have an article about spaCy NER: https://newscatcherapi.com/blog/named-entity-recognition-wit... The conclusion I came up with: "A few notes on my Spacy NER accuracy with "real world" data Low accuracy with sentences without a proper casing 1. Low accuracy overall, even with a large model 2. You'd need to fine-tune your model if you want to use it in production 3. Overall, there's no open-source high accuracy…
I assume your product does some kind of entity disambiguation and/or link to an ontology? Spacy doesn't provide this out of the box either, AFAICT. Can you share more info about how you do it?
Re: Advanced NLP with spaCy v3
#8Earlier quoted context omitted.
Also I have an article about spaCy NER: https://newscatcherapi.com/blog/named-entity-recognition-wit... The conclusion I came up with: "A few notes on my Spacy NER accuracy with "real world" data Low accuracy with sentences without a proper casing 1. Low accuracy overall, even with a large model 2. You'd need to fine-tune your model if you want to use it in production 3. Overall, there's no open-source high accuracy…
I assume your product does some kind of entity disambiguation and/or link to an ontology? Spacy doesn't provide this out of the box either, AFAICT. Can you share more info about how you do it?
We don't provide entity disambiguation out of a box. It's more of a on request for Enterprise clients.
But overall, entity disambiguation is one of the most useful and difficult tasks in the NLP.
SpaCy supports entity linking via knowledge base: https://spacy.io/api/entitylinker
Re: Advanced NLP with spaCy v3
#9A relatively underdiscussed quirk of the rise of superlarge language models like GPT-3 for certain NLP tasks is that since those models have incorporated so much real world grammar, there's no need to do advanced preprocessing and can just YOLO and work with generated embeddings instead without going into spaCy's (excellent) parsing/NER features. OpenAI recently released an Embeddings API for GPT-3 with good demos an…
I imagine it being very useful to understand what you just said
Re: Advanced NLP with spaCy v3
#10No post body was provided.