# \#pos **URL:** https://support.prodi.gy/tag/pos/28.md [Latest](https://support.prodi.gy/latest.md) · [Categories](https://support.prodi.gy/categories.md) · [Tags](https://support.prodi.gy/tags.md) --- ## [Implications of "answer": "accept" being automatically added to all imported examples with db-in](https://support.prodi.gy/t/implications-of-answer-accept-being-automatically-added-to-all-imported-examples-with-db-in/6447)
**Author:** [@Gruff](https://support.prodi.gy/u/Gruff)\ **Replies:** 4\ **Last updated:** [March 21, 2023, 1:53pm UTC](https://support.prodi.gy/t/implications-of-answer-accept-being-automatically-added-to-all-imported-examples-with-db-in/6447 "2023-03-21T13:53:26Z")
Edit: I've now determined that the issues I initially reported are not down to the data, so I've removed those references. I'll ask about those particular issues on the spaCy discussion board. Hi, I've been trying to m… --- ## [Modifying a document based on POS and DEP](https://support.prodi.gy/t/modifying-a-document-based-on-pos-and-dep/4741)
**Author:** [@dsr2021](https://support.prodi.gy/u/dsr2021)\ **Replies:** 1\ **Last updated:** [October 4, 2021, 11:48am UTC](https://support.prodi.gy/t/modifying-a-document-based-on-pos-and-dep/4741 "2021-10-04T11:48:23Z")
I would like to preprocess a document so as to make it less ambiguous and easier for annotation later in the pipeline. For example, I would like to use the POS and DEP information to change fragments like "large and med… --- ## [help - first process of annotation](https://support.prodi.gy/t/help-first-process-of-annotation/4156)
**Author:** [@Lize](https://support.prodi.gy/u/Lize)\ **Replies:** 15\ **Last updated:** [August 7, 2021, 3:31am UTC](https://support.prodi.gy/t/help-first-process-of-annotation/4156 "2021-08-07T03:31:18Z")
English version below :blush: Bonjour à tous. Je poste ce message afin d’avoir des avis sur la méthodologie que nous souhaitons mettre en œuvre pour annoter notre corpus. Notre objectif est de constituer un corpus anno… --- ## [Pipeline for POS corrections and dep corrections](https://support.prodi.gy/t/pipeline-for-pos-corrections-and-dep-corrections/4086)
**Author:** [@jmankewitz](https://support.prodi.gy/u/jmankewitz)\ **Replies:** 1\ **Last updated:** [March 31, 2021, 5:54pm UTC](https://support.prodi.gy/t/pipeline-for-pos-corrections-and-dep-corrections/4086 "2021-03-31T17:54:54Z")
Hello! New Prodigy user here! We have some large corpora of conversational speech we'd like to eventually parse with spacy and correct with prodigy. However, the nature of the corpora (child-produced speech) means some … --- ## [Using custom tag\_map in prodigy?](https://support.prodi.gy/t/using-custom-tag-map-in-prodigy/3726)
**Author:** [@PeterG](https://support.prodi.gy/u/PeterG)\ **Replies:** 2\ **Last updated:** [December 30, 2020, 9:26am UTC](https://support.prodi.gy/t/using-custom-tag-map-in-prodigy/3726 "2020-12-30T09:26:05Z")
I've trained a model for Luxembourgish using a tag\_map oriented on the German Tiger tagset: TAG\_MAP = { "$(": {POS: PUNCT, "PunctType": "brck"}, "$,": {POS: PUNCT, "PunctType": "comm"}, "$.": {POS: PUNCT, "P… --- ## [Is it possible to find uncertainties of spaCy POS tags?](https://support.prodi.gy/t/is-it-possible-to-find-uncertainties-of-spacy-pos-tags/3719)
**Author:** [@Joeytje50](https://support.prodi.gy/u/Joeytje50)\ **Replies:** 0\ **Last updated:** [December 9, 2020, 6:00pm UTC](https://support.prodi.gy/t/is-it-possible-to-find-uncertainties-of-spacy-pos-tags/3719 "2020-12-09T18:00:41Z")
(originally posted on https://stackoverflow.com/questions/65218606/is-it-possible-to-find-uncertainties-of-spacy-pos-tags) I am looking for a way to figure out the probabilities of certain tags set by spacy. So far, wit… --- ## [prodigy train tagger not working](https://support.prodi.gy/t/prodigy-train-tagger-not-working/3557)
**Author:** [@meatball\_nlp](https://support.prodi.gy/u/meatball_nlp)\ **Replies:** 3\ **Last updated:** [November 10, 2020, 3:51am UTC](https://support.prodi.gy/t/prodigy-train-tagger-not-working/3557 "2020-11-10T03:51:52Z")
I am using prodigy to train a pos tagger. However when I try to run the train command I get the following results: Created and merged data for 0 total examples Using 0 train / 0 eval (split 50%) ValueError: not enough v… --- ## [Problem creating a new language to serve as a base model for further improvement in Prodigy](https://support.prodi.gy/t/problem-creating-a-new-language-to-serve-as-a-base-model-for-further-improvement-in-prodigy/3296)
**Author:** [@Gruff](https://support.prodi.gy/u/Gruff)\ **Replies:** 3\ **Last updated:** [August 17, 2020, 4:12pm UTC](https://support.prodi.gy/t/problem-creating-a-new-language-to-serve-as-a-base-model-for-further-improvement-in-prodigy/3296 "2020-08-17T16:12:32Z")
Hi, In an attempt to bootstrap a model that we can improve in Prodigy, I've trained a Welsh model from scratch using the simple training format. It has a functional tagger, lemmatizer, vectors and tokenizer, but no pars… --- ## [Two Layers of Annotation](https://support.prodi.gy/t/two-layers-of-annotation/3066)
**Author:** [@aanifh](https://support.prodi.gy/u/aanifh)\ **Replies:** 2\ **Last updated:** [June 24, 2020, 1:21pm UTC](https://support.prodi.gy/t/two-layers-of-annotation/3066 "2020-06-24T13:21:39Z")
Hi, I'd like to annotate text with POS tags, and then another more specific Features Tag on top of that. For example, "I eat apples", "eat" would get a \[VERB\] POS tag and the annotator could also add another layer of tag… --- ## [Documentation NER](https://support.prodi.gy/t/documentation-ner/2946)
**Author:** [@KiranParasa](https://support.prodi.gy/u/KiranParasa)\ **Replies:** 4\ **Last updated:** [May 29, 2020, 5:39pm UTC](https://support.prodi.gy/t/documentation-ner/2946 "2020-05-29T17:39:18Z")
Hi, Finding little difficulty with NER. I believe the system finds verbs and part of speech from the English dictionary.. But for some reason very basic nouns ( which in most cases can't be anything else) were being tag… --- ## [Dependency Parser and POS tagger for unsupported language](https://support.prodi.gy/t/dependency-parser-and-pos-tagger-for-unsupported-language/2627)
**Author:** [@Ari](https://support.prodi.gy/u/Ari)\ **Replies:** 2\ **Last updated:** [March 9, 2020, 7:29am UTC](https://support.prodi.gy/t/dependency-parser-and-pos-tagger-for-unsupported-language/2627 "2020-03-09T07:29:26Z")
Hi there, Thanks for the great library! I'm looking to create a dependency parser and POS tagger for Afrikaans (and later, other South African languages). I have a labelled treebank corpus but am not certain how to proc… --- ## [How to do POS tagging with this tool?](https://support.prodi.gy/t/how-to-do-pos-tagging-with-this-tool/2312)
**Author:** [@westofpluto](https://support.prodi.gy/u/westofpluto)\ **Replies:** 1\ **Last updated:** [December 13, 2019, 9:55am UTC](https://support.prodi.gy/t/how-to-do-pos-tagging-with-this-tool/2312 "2019-12-13T09:55:01Z")
I have downloaded the en\_core\_web\_lg model and I have my own input JSONL text data in a new domain (medical/clinical). Now I want to use Prodigy to train a POS tagger that works well on my domain (which of course include… --- ## [Training POS Tager for Indonesian Language](https://support.prodi.gy/t/training-pos-tager-for-indonesian-language/2226)
**Author:** [@daniseyy](https://support.prodi.gy/u/daniseyy)\ **Replies:** 5\ **Last updated:** [November 20, 2019, 12:02pm UTC](https://support.prodi.gy/t/training-pos-tager-for-indonesian-language/2226 "2019-11-20T12:02:24Z")
Hi, i'm currenltly trying to train my own spacy model for POS Tagging in Indonesian Model in which doesn't have any pretrained model like the "en\_core\_web" so which step for pos should i use to train a new model, is it t… --- ## [How to compute tag SCORE in pos.teach?](https://support.prodi.gy/t/how-to-compute-tag-score-in-pos-teach/1179)
**Author:** [@Jeff](https://support.prodi.gy/u/Jeff)\ **Replies:** 4\ **Last updated:** [March 8, 2019, 2:25pm UTC](https://support.prodi.gy/t/how-to-compute-tag-score-in-pos-teach/1179 "2019-03-08T14:25:56Z")
With pos.teach, you show a score in the bottom right corner that indicates the confidence in the highlighted tag. Could you let me know how this is computed? I tried: math.exp(doc\[0\].prob) since the docs describe Tok… --- ## [Is it possible to train a tagger with custom labels?](https://support.prodi.gy/t/is-it-possible-to-train-a-tagger-with-custom-labels/1213)
**Author:** [@plusepsilon](https://support.prodi.gy/u/plusepsilon)\ **Replies:** 4\ **Last updated:** [February 26, 2019, 10:56am UTC](https://support.prodi.gy/t/is-it-possible-to-train-a-tagger-with-custom-labels/1213 "2019-02-26T10:56:46Z")
For ner training, we can provide custom labels completely independent of the original labels. It doesn’t seem like it’s possible for taggers. TAG\_MAP = { 'N': {'pos': 'NOUN'}, # change this 'V': {'pos': 'VERB'}… --- ## [Understanding and improving POS training.](https://support.prodi.gy/t/understanding-and-improving-pos-training/1191)
**Author:** [@adwaraki](https://support.prodi.gy/u/adwaraki)\ **Replies:** 1\ **Last updated:** [February 6, 2019, 8:28am UTC](https://support.prodi.gy/t/understanding-and-improving-pos-training/1191 "2019-02-06T08:28:24Z")
Hi @ines, I am working side by side on the NER aspect and the POS tagging. I was doing some annotating and training last night with the POS tags for PROPN and VERB since I noticed that they were off in some cases. I am … --- ## [Not understanding how pos.make-gold works](https://support.prodi.gy/t/not-understanding-how-pos-make-gold-works/1168)
**Author:** [@Jeff](https://support.prodi.gy/u/Jeff)\ **Replies:** 3\ **Last updated:** [February 2, 2019, 9:48pm UTC](https://support.prodi.gy/t/not-understanding-how-pos-make-gold-works/1168 "2019-02-02T21:48:54Z")
I’m trying to use pos.make-gold. Per the recommendations in the docs, I’m doing a subset of tags at a time. Here is an example sequence: prodigy dataset test "Just testing" prodigy pos.make-gold test en\_core\_web\_sm t… --- ## [pos.teach stops unexpectedly](https://support.prodi.gy/t/pos-teach-stops-unexpectedly/1169)
**Author:** [@Jeff](https://support.prodi.gy/u/Jeff)\ **Replies:** 1\ **Last updated:** [January 30, 2019, 12:12pm UTC](https://support.prodi.gy/t/pos-teach-stops-unexpectedly/1169 "2019-01-30T12:12:36Z")
I’m using pos.teach on a dataset of 114 separate sentences. After about 10 annotations, it stops and says No tasks available. If I stop the server and restart it, it will work again, but this isn’t a good scenario when… --- ## [Python error with pos.teach](https://support.prodi.gy/t/python-error-with-pos-teach/1162)
**Author:** [@Jeff](https://support.prodi.gy/u/Jeff)\ **Replies:** 3\ **Last updated:** [January 29, 2019, 4:46pm UTC](https://support.prodi.gy/t/python-error-with-pos-teach/1162 "2019-01-29T16:46:43Z")
Hello, I'm just getting started and am getting an error with pos.teach. I'd appreciate your help in getting this working. Note that pos.make-gold is working so the error is specific to pos.teach. Here is my command to… --- ## [colloquial pronouns not labeled as pron](https://support.prodi.gy/t/colloquial-pronouns-not-labeled-as-pron/1165)
**Author:** [@aph61](https://support.prodi.gy/u/aph61)\ **Replies:** 1\ **Last updated:** [January 29, 2019, 4:28pm UTC](https://support.prodi.gy/t/colloquial-pronouns-not-labeled-as-pron/1165 "2019-01-29T16:28:17Z")
currently I use spacy only for lemmatization/parsing of colloquial language, without word vector capabilities. I have a problem with the POS-tagging. my code tokens = \[tok.lemma\_.lower().strip() for tok in doc if tok.po… --- ## [Custom POS tag model and errors](https://support.prodi.gy/t/custom-pos-tag-model-and-errors/1123)
**Author:** [@asdf](https://support.prodi.gy/u/asdf)\ **Replies:** 3\ **Last updated:** [January 16, 2019, 2:45am UTC](https://support.prodi.gy/t/custom-pos-tag-model-and-errors/1123 "2019-01-16T02:45:34Z")
I've enjoyed extending prodigy at my medium-sized startup, and most things have been pretty smooth. Unfortunately, I've run into some snags with extending POS tags. I'm making a truecaser which will have 3 tags: lower, … --- ## [Train POS on new Language](https://support.prodi.gy/t/train-pos-on-new-language/1093)
**Author:** [@helmiruza](https://support.prodi.gy/u/helmiruza)\ **Replies:** 2\ **Last updated:** [December 30, 2018, 8:00pm UTC](https://support.prodi.gy/t/train-pos-on-new-language/1093 "2018-12-30T20:00:42Z")
Hi, I’m training a new language from Word2Vec vectors. What is the best way to train POS? Should I be doing this in spaCy or can I do it in Prodigy? Thanks --- ## [Disambiguate POS Tags](https://support.prodi.gy/t/disambiguate-pos-tags/831)
**Author:** [@stefan](https://support.prodi.gy/u/stefan)\ **Replies:** 1\ **Last updated:** [September 21, 2018, 9:04pm UTC](https://support.prodi.gy/t/disambiguate-pos-tags/831 "2018-09-21T21:04:44Z")
Hi :slight\_smile: thanks for activating my research licence - I’m soo exited! I want to use prodigy for disambiguating part of speech tags (for a low-resource European language). That means I already have a nice pos ta… --- ## [Errors with pos.teach and pos.batch-train.](https://support.prodi.gy/t/errors-with-pos-teach-and-pos-batch-train/599)
**Author:** [@adwaraki](https://support.prodi.gy/u/adwaraki)\ **Replies:** 18\ **Last updated:** [July 20, 2018, 6:55pm UTC](https://support.prodi.gy/t/errors-with-pos-teach-and-pos-batch-train/599 "2018-07-20T18:55:13Z")
Hi, I am getting some errors when I try and run pos.teach and pos.batch-train. I am not quite sure if I am doing something wrong, because ner.teach, ner.manual and ner.batch-train all worked out pretty well and I could … --- ## [saved model doesn't work after saving or updating the model to local area](https://support.prodi.gy/t/saved-model-doesnt-work-after-saving-or-updating-the-model-to-local-area/636)
**Author:** [@han](https://support.prodi.gy/u/han)\ **Replies:** 4\ **Last updated:** [June 25, 2018, 2:29am UTC](https://support.prodi.gy/t/saved-model-doesnt-work-after-saving-or-updating-the-model-to-local-area/636 "2018-06-25T02:29:42Z")
\[56\] Hi, I have tried to train a tagger which based on ‘en’ model. It seems works fine like below when it just finished training from given data. \[29\] But, the thing is whenever trying to load that saved model from t… --- ## [Error occur with execution pos.batch\_train, pos.train\_curve](https://support.prodi.gy/t/error-occur-with-execution-pos-batch-train-pos-train-curve/622)
**Author:** [@han](https://support.prodi.gy/u/han)\ **Replies:** 2\ **Last updated:** [June 19, 2018, 4:11pm UTC](https://support.prodi.gy/t/error-occur-with-execution-pos-batch-train-pos-train-curve/622 "2018-06-19T16:11:36Z")
Hi, I’ve made successful pos.teach, pos.make-gold, pos.gold-to-spacy results into dataset. But suddenly when I tried to train a model using pos.batch-train, or pos.train-curve, it wasn’t working at all with the same err…