# Recommended approaches for combining NER with text calssification **URL:** \ **Category:** Uncategorized\ **Tags:** usage, ner, textcat\ **Created:** [September 26, 2019, 6:17pm UTC](https://support.prodi.gy/t/recommended-approaches-for-combining-ner-with-text-calssification/2047 "2019-09-26T18:17:50Z")\ **Posts on this page:** 3\ **Page:** 1
**Author:** ![cbjrobertson](https://avatars.discourse-cdn.com/v4/letter/c/87869e/32.png) [@cbjrobertson](https://support.prodi.gy/u/cbjrobertson)\ **Post date:** [September 26, 2019, 6:17pm UTC](https://support.prodi.gy/t/recommended-approaches-for-combining-ner-with-text-calssification/2047/1 "2019-09-26T18:17:50Z")
Hi-- Thanks for the great tool:) I have a use case equivalent to the following: I am trying to train a text classifier that classifies whether a length of text evinces positive or negative sentiment with regard to sports teams. Simple enough, but my data often exhibit a single short text in which two teams are mentioned in the same sentence and the sentiment for one is positive while the other is negative, e.g.: ```python "The Bears are way better than the Spurs!" ``` What I'd like to be able to do is train a custom `NER` model to recognize sports teams, and then train a classifier not on the whole text, but on the sentiment associated with each named entity (taking into account the context of the entire text). Do you have any recommendations on approaches that might be useful for this use case? Thank you! ---
**Author:** ![honnibal](https://sea2.discourse-cdn.com/flex020/user_avatar/support.prodi.gy/honnibal/32/35_2.png) [@honnibal](https://support.prodi.gy/u/honnibal)\ **Post date:** [September 30, 2019, 10:27am UTC](https://support.prodi.gy/t/recommended-approaches-for-combining-ner-with-text-calssification/2047/2 "2019-09-30T10:27:53Z")
Perhaps you could have the following categories? 1. Both good 2. First good, second bad 3. First bad, second good 4. Both bad 5. First neutral, second good (etc) If you frequently have sentences matching _three_ sports teams, you can have categories for that as well --- but I suspect those might be rarer. You might also find that they only occur in situations like "The Antelopes are way better than the Tree Frogs or the Otters", in which case the classification scheme would be something like "First good, others bad". This approach is likely to be less annotation, and the model will be able to pick up on _patterns of contrast_, which I think will be much easier than making the decisions individually. ---
**Author:** ![cbjrobertson](https://avatars.discourse-cdn.com/v4/letter/c/87869e/32.png) [@cbjrobertson](https://support.prodi.gy/u/cbjrobertson)\ **Post date:** [October 22, 2019, 5:27pm UTC](https://support.prodi.gy/t/recommended-approaches-for-combining-ner-with-text-calssification/2047/3 "2019-10-22T17:27:30Z")
Hi @honnibal thanks for your reply! Sorry for the delay. I've been busy with other projects, and have been thinking about alternative approaches on the basis of your advice. The problem is really that the range of syntactical diversity is a lot greater than the little toy example I've given you. I've done some digging around and think I've found a solution, but it's a little complicated and I was hoping I could get your advice on whether it is implementable within prodigy. Basically, the problem is I need to classify not in terms of the whole document, but in terms of how categories are applied to specific words (entities) within the document. I've done some digging into how annotations are stored by `prodigy` and it seems that whole documents with different matched patterns are stored as separate entries. To stick with the above example (but keeping in mind that actually examples are much more syntactically diverse), the following would be separate entries in a standard `prodigy` dataset (apols if I have the spans wrong, I just wrote them by hand): ```python {"text":"The Bears are way better than the Spurs.", "spans":[{"text":"Bears","start":4,"end":8,"priority":0.5,"score":0.5,"pattern":10060362}], "label":"GOOD_TEAM", "answer":"accept"} {"text":"The Bears are way better than the Spurs.", "spans":[{"text":"Spurs","start":35,"end":39,"priority":0.5,"score":0.5,"pattern":12309846}], "label":"GOOD_TEAM", ,"answer":"reject"} ``` My idea is that I'll first train a NER model in `prodigy` (in this example it would be trained to recognize named sports teams), and then to write a custom `prodigy` `textcat.teach`-derived recipe which used my `NER` model in place of pattern matching. I could then use some kind of context-sensitive vector representation to pass my annotations to a classifier. I've been playing with `BERT` implementations, and was thinking about starting there. Note than since I want to classify _only_ with reference to the named entities, such an approach would not (could not?) employ active learning. But if you had any recommendations there, I would be happy to hear them. My question is, would such an approach be possible using `spacy/prodigy` models? I see from your [docs](https://spacy.io/models#architecture) that your `NER` model uses context sensitive vector representations, but I can't seem to find documentation about your classification models? Do they represent text in a context sensitive manner? If so, are those embeddings sensitive to the information in the `spans` key of the stream? If not, I would struggle to understand the default behaviour for a dataset exhibiting _span-dependent answers_, since presumably you'd be training your model to predict opposite outputs from identical inputs 😫. If this is the case, I suppose I could just use prodigy to annotate and then use a context-sensitive embedding model to classify, and since I would not be taking advantage of active learning in the classification annotating process, it wouldn't be a huge loss. But if such an approach is possible within the prodigy environment, I'd love to know. Thanks so much for all your work! Much appreciated.