Comments (6)
Thanks for noticing that, I was getting crazy thinking I made something wrong. These are the results for 0.70:
>>> toks = nlp("They ate the pizza with anchovies.")
>>> printDeps(toks)
They SUB PRON [] []
ate ROOT VERB ['They'] ['.', 'with', 'pizza']
the NMOD DET [] []
pizza OBJ NOUN ['the'] []
with VMOD ADP [] ['anchovies']
anchovies PMOD NOUN [] []
. P PUNCT [] []
>>> toks = nlp("i don't have other assistance")
>>> printDeps(toks)
i SUB PRON [] []
do ROOT VERB ['i'] ['have', "n't"]
n't VMOD ADV [] []
have VC VERB [] ['assistance']
other NMOD ADJ [] []
assistance OBJ NOUN ['other'] []
>>> toks = nlp("I have no other financial assistance available and he certainly won't provide support.")
>>> printDeps(toks)
I SUB PRON [] []
have VMOD VERB ['I'] ['assistance']
no NMOD DET [] []
other NMOD ADJ [] []
financial NMOD ADJ [] []
assistance OBJ NOUN ['no', 'other', 'financial'] ['available']
available NMOD ADJ [] []
and VMOD CONJ [] []
he SUB PRON [] []
certainly VMOD ADV [] []
wo ROOT VERB ['have', 'and', 'he', 'certainly'] ['.', 'provide', "n't"]
n't VMOD ADV [] []
provide VC VERB [] ['support']
support OBJ NOUN [] []
. P PUNCT [] []
# with a comma
>>> toks = nlp("I have no other financial assistance available, and he certainly won't provide support.")
>>> printDeps(toks)
I SUB PRON [] []
have VMOD VERB ['I'] ['assistance']
no NMOD DET [] []
other NMOD ADJ [] []
financial NMOD ADJ [] []
assistance OBJ NOUN ['no', 'other', 'financial'] ['available']
available NMOD ADJ [] []
, P PUNCT [] []
and VMOD CONJ [] []
he SUB PRON [] []
certainly VMOD ADV [] []
wo ROOT VERB ['have', ',', 'and', 'he', 'certainly'] ['.', 'provide', "n't"]
n't VMOD ADV [] []
provide VC VERB [] ['support']
support OBJ NOUN [] []
. P PUNCT [] []
from spacy.
Comparing with version 0.70 it looks like when dependencies are missing in 0.83, they are ROOT in 0.70.
from spacy.
Okay, I've got the root label bug sorted out.
I've also investigated a potential loss of parse quality. I've fixed some bugs that were long present, and parse quality is actually up slightly over previous metrics. However, the specific eat/pizza/anchovies case is a difficult PP attachment example, and the model may get any individual case such as this incorrect.
Do you have evidence of aggregate performance degradation for your use, outside of the ROOT-label bug?
from spacy.
I don't. It seems that most of the problems I was experiencing were related to the ROOT bug.
from spacy.
Fix for the ROOT bug rolled out in v0.84. Please remember to re-download the data, as bug fixes to the feature calculation mean that the old model will be out-of-sync with the new feature calculation code. Please re-open this issue if the problem does not seem to be resolved.
from spacy.
This thread has been automatically locked since there has not been any recent activity after it was closed. Please open a new issue for related bugs.
from spacy.
Related Issues (20)
- Incorrect detection of sentence boundaries, if last sentence missing eos symbol for trf model
- Enable override of existing custom pipe HOT 1
- Check that filter_spans input is a Span HOT 3
- Tokenizer Incorrectly Splitting "M1M" HOT 1
- Version incompatibility between Spacy, Cuda, Pytorch and Python HOT 3
- Accessing private transformer models HOT 1
- Problems converting Doc object to/from json HOT 1
- The word transitions to the wrong prototype HOT 1
- Fuzzy Matching not working HOT 1
- Unable to finetune transformer based ner model after initial tuning
- Undesired whitespace normalization of Korean text
- Suggestion: Normalize or Translate the parsing labels for German and English dependency labelling
- Code example discrepancy for `Span.lemma_` in API docs HOT 1
- Signature docs error in API docs for `MorphAnalysis.__contains__` HOT 2
- Import broken python 3.9 HOT 1
- Luminous
- Converting into exe file through pyinstaller-> spacy cannot find factory for 'curated transformer' HOT 1
- Spacy problem with whitespace or punctuation HOT 1
- config.cfg error from spacy init config command
- Possible ORG misidentification HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from spacy.