# Improve a NER on multiple labels **URL:** \ **Category:** Uncategorized\ **Tags:** usage, ner\ **Created:** [March 20, 2019, 12:45am UTC](https://support.prodi.gy/t/improve-a-ner-on-multiple-labels/1321 "2019-03-20T00:45:03Z")\ **Posts on this page:** 4\ **Page:** 1
**Author:** ![iero](https://avatars.discourse-cdn.com/v4/letter/i/41988e/32.png) [@iero](https://support.prodi.gy/u/iero)\ **Post date:** [March 20, 2019, 12:45am UTC](https://support.prodi.gy/t/improve-a-ner-on-multiple-labels/1321/1 "2019-03-20T00:45:03Z")
Hello I would like to improve the ‘ORG, PRODUCT, PERSON’ labels for the french model. In the model (fr\_core\_news\_sm) provided, there are only ‘ORG and PER’ and no PRODUCT. So I need to create the PRODUCT label and improve others. I went trough the “Improve a NER” example and several tutorials. I began creating three patterns jsonl files (one for each label) using list of seed words. After that, I concatenated the files into one pattern using ```python cat *.jsonl > all.jsonl ``` I created a global dataset using: ```python prodigy dataset my_great_fr_ds "My dataset" ``` After I extracted sentences that contains the seed words into a trainingset.jsonl file What I plan to do: Teach the model using: ```python prodigy ner.teach my_great_fr_ds fr_core_news_sm trainingset.json --patterns all.jsonl ``` After that, train the model using: ```python prodigy ner.batch-train my_great_fr_ds fr_core_news_sm --output my_model --label "ORG, PRODUCT,PERSON" --eval-split 0.2 --n-iter 10 --batch-size 8 ``` And continue the teach phase and retrain several time to improve the model. Is this the best way to proceed ? Do I need to split the teaching part in 3 separate datasets (one for ORG, one for PRODUCT and one for PERSON) ? If yes, how do I merge them for the final training ? I already trained on one label (ORG) but I’m afraid that if I don’t do PRODUCT and PERSON too before the training, the model will not be good for those 3 labels. Do I need to teach using several batches (ie 1000 sentences per batch) and retrain the model with those batches and compare if it improves ? Thanks for your help ---
**Author:** ![ines](https://sea2.discourse-cdn.com/flex020/user_avatar/support.prodi.gy/ines/32/3_2.png) [@ines](https://support.prodi.gy/u/ines)\ **Post date:** [March 20, 2019, 10:02am UTC](https://support.prodi.gy/t/improve-a-ner-on-multiple-labels/1321/2 "2019-03-20T10:02:31Z")
> [@iero](#): > > Do I need to split the teaching part in 3 separate datasets (one for ORG, one for PRODUCT and one for PERSON) ? If yes, how do I merge them for the final training ? You don't _have to_ – you could also set `--label PERSON,ORG,PRODUCT`. However, we usually recommend working on the labels separately. It makes it easier to focus, since you only ever have to think about one concept at a time. It also makes it easier to run separate experiments per label, and start over if you need to. For example, maybe you realise at some point that you've been annotating `PERSON` slightly wrong. If you have those annotations in a different dataset, you can discard the old ones and start again. Or maybe you find out that the accuracy suddenly gets really bad once you add `PRODUCT` annotations. This could indicate that there's a problem with those examples – but if you have everything in one set, getting to that conclusion would be much harder. Merging several datasets into one is relatively easy – splitting one large dataset is a much more frustrating task. > [@iero](#): > > Do I need to teach using several batches (ie 1000 sentences per batch) and retrain the model with those batches and compare if it improves ? Frequently training your model and comparing the results is always good, yes! You don't want to waste weeks labelling data, only to find out that your model isn't actually learning anything from it. For each training experiment, you usually want to start with the same base model and then update with all the annotations – for example, `fr_core_news_sm` and your entire training set. (If you keep updating the model you've previously trained with new data constantly, you might introduce other side-effects of the frequent updating and potentially end up with confusing results.) ---
**Author:** ![iero](https://avatars.discourse-cdn.com/v4/letter/i/41988e/32.png) [@iero](https://support.prodi.gy/u/iero)\ **Post date:** [March 20, 2019, 7:29pm UTC](https://support.prodi.gy/t/improve-a-ner-on-multiple-labels/1321/3 "2019-03-20T19:29:25Z")
Thanks a lot Ines for this answer So if I understood well, I need to create 3 datasets (ie ds\_org, ds\_product and ds\_person) Then I do teaching on those 3 datasets using : ```python prodigy ner.teach ds_org fr_core_news_sm trainingset_org.json --label ORG prodigy ner.teach ds_product fr_core_news_sm trainingset_prod.json --label PRODUCT prodigy ner.teach ds_person fr_core_news_sm trainingset_person.json --label PERSON ``` After, I need to merge my dataset in one using 3 db-out and one db-in and launch the ner.batch-train or can I pass the three datasets directly ? And after the training, if I want to improve my model with new examples, I relaunch the teach on the same datasets using new data (ie the following line), and I redo the merge and the ‘final’ training on `fr_core_news_sm` , right ? ```python prodigy ner.teach ds_org fr_core_news_sm anothertrainingset_org.json --label ORG ``` ---
**Author:** ![ines](https://sea2.discourse-cdn.com/flex020/user_avatar/support.prodi.gy/ines/32/3_2.png) [@ines](https://support.prodi.gy/u/ines)\ **Post date:** [March 20, 2019, 11:16pm UTC](https://support.prodi.gy/t/improve-a-ner-on-multiple-labels/1321/4 "2019-03-20T23:16:43Z")
Yes, that sounds like a good workflow. And if possible, you might want to keep the merged files somewhere for reference, so you can always go back to a previous state. You can also automate the merging process in Python btw – I've posted a little snippet here: > [@Merging annotations from different datasets](https://support.prodi.gy/t/merging-annotations-from-different-datasets/310/2): > > Each example that comes in is assigned an \_input\_hash – for text-based tasks, that hash is generated from the "text" property. So you can easily check whether annotations refer to the same input text by comparing their input hashes, and then merging their "spans". The NER model comes with a helper function merge\_spans that should do exactly that – however, it’s currently only used internally during updating and we haven’t really tested its isolated usage yet. But you can try the following: fr…