A Python package that includes many state-of-the-art syntactic/semantic parsers (with pretrained models for more than 19 languages), as well as highly-parallelized implementations of several well-known and effective structured prediction algorithms.
- Dependency Parser
- Biaffine (Dozat and Manning, 2017)
- CRF/MatrixTree (Koo et al., 2007; Ma and Hovy, 2017)
- CRF2o (Zhang et al., 2020a)
- Constituency Parser
- CRF (Zhang et al., 2020b)
- Semantic Dependency Parser
- Biaffine (Dozat and Manning, 2018)
- MFVI/LBP (Wang et al, 2019)
SuPar can be installed via pip:
$ pip install -U suparOr installing from source is also permitted:
$ git clone https://github.com/yzhangcs/parser && cd parser
$ python setup.py installAs a prerequisite, the following requirements should be satisfied:
python: >= 3.7pytorch: >= 1.7transformers: >= 4.0
SuPar provides pretrained models for English, Chinese and 17 other languages.
The tables below list the performance and parsing speed of pretrained models for different tasks.
All results are tested on the machine with Intel(R) Xeon(R) CPU E5-2650 v4 @ 2.20GHz and Nvidia GeForce GTX 1080 Ti GPU.
English and Chinese dependency parsing models are trained on PTB and CTB7 respectively.
For each parser, we provide pretrained models that take BiLSTM as encoder.
We also provide models trained by finetuning pretrained language models from Huggingface Transformers.
We use robert-large for English and hfl/chinese-electra-180g-large-discriminator for Chinese.
During evaluation, punctuation is ignored in all metrics for PTB.
| Name | UAS | LAS | Sents/s |
|---|---|---|---|
biaffine-dep-en |
96.01 | 94.41 | 1831.91 |
crf2o-dep-en |
96.07 | 94.51 | 531.59 |
biaffine-dep-roberta-en |
97.33 | 95.86 | 271.80 |
biaffine-dep-zh |
88.64 | 85.47 | 1180.57 |
crf2o-dep-zh |
89.22 | 86.15 | 237.40 |
biaffine-dep-electra-zh |
92.45 | 89.55 | 160.56 |
The multilingual dependency parsing model, named biaffine-dep-xlmr, is trained on merged 12 selected treebanks from Universal Dependencies (UD) v2.3 dataset by finetuning xlm-roberta-large.
The following table lists results of each treebank.
Languages are represented by ISO 639-1 Language Codes.
| Language | UAS | LAS | Sents/s |
|---|---|---|---|
bg |
96.95 | 94.24 | 343.96 |
ca |
95.57 | 94.20 | 184.88 |
cs |
95.79 | 93.83 | 245.68 |
de |
89.74 | 85.59 | 283.53 |
en |
93.37 | 91.27 | 269.16 |
es |
94.78 | 93.29 | 192.00 |
fr |
94.56 | 91.90 | 219.35 |
it |
96.29 | 94.47 | 254.82 |
nl |
96.04 | 93.76 | 268.57 |
no |
95.64 | 94.45 | 318.00 |
ro |
94.59 | 89.79 | 216.45 |
ru |
96.37 | 95.24 | 243.56 |
We use PTB and CTB7 datasets to train English and Chinese constituency parsing models. Below are the results.
| Name | P | R | F1 | Sents/s |
|---|---|---|---|---|
crf-con-en |
94.16 | 93.98 | 94.07 | 841.88 |
crf-con-roberta-en |
96.42 | 96.13 | 96.28 | 233.34 |
crf-con-zh |
88.82 | 88.42 | 88.62 | 590.05 |
crf-con-electra-zh |
92.18 | 91.66 | 91.92 | 140.45 |
The multilingual model crf-con-xlmr is trained on SPMRL dataset by finetuning xlm-roberta-large.
We follow instructions of Benepar to preprocess the data.
For simplicity, we then directly merge train/dev/test treebanks of all languages in SPMRL into big ones to train the model.
The results of each treebank are as follows.
| Language | P | R | F1 | Sents/s |
|---|---|---|---|---|
eu |
93.40 | 94.19 | 93.79 | 266.96 |
fr |
88.77 | 88.84 | 88.81 | 149.34 |
de |
93.68 | 92.18 | 92.92 | 200.31 |
he |
94.65 | 95.20 | 94.93 | 172.50 |
hu |
96.70 | 96.81 | 96.76 | 186.58 |
ko |
91.75 | 92.46 | 92.11 | 234.86 |
pl |
97.33 | 97.27 | 97.30 | 310.86 |
sv |
92.51 | 92.50 | 92.50 | 235.49 |
English semantic dependency parsing models are trained on DM data introduced in SemEval-2014 task 8, while Chinese models are trained on NEWS domain data of corpora from SemEval-2016 Task 9. Our data preprocessing steps follow Second_Order_SDP.
| Name | P | R | F1 | Sents/s |
|---|---|---|---|---|
biaffine-sdp-en |
94.35 | 93.12 | 93.73 | 1067.06 |
vi-sdp-en |
94.36 | 93.52 | 93.94 | 821.73 |
vi-sdp-roberta-en |
95.18 | 95.20 | 95.19 | 264.13 |
biaffine-sdp-zh |
72.93 | 66.29 | 69.45 | 523.36 |
vi-sdp-zh |
72.05 | 67.97 | 69.95 | 411.94 |
vi-sdp-electra-zh |
73.29 | 70.53 | 71.89 | 139.52 |
SuPar allows you to download the pretrained model and parse sentences with a few lines of code:
>>> from supar import Parser
>>> parser = Parser.load('biaffine-dep-en')
>>> dataset = parser.predict('I saw Sarah with a telescope.', lang='en', prob=True, verbose=False)By default, we use stanza internally to tokenize plain texts for parsing.
You only need to specify the language code lang for tokenization.
The call to parser.predict will return an instance of supar.utils.Dataset containing the predicted results.
You can either access each sentence held in dataset or an individual field of all results.
Probabilities can be returned along with the results if prob=True.
>>> dataset[0]
1 I _ _ _ _ 2 nsubj _ _
2 saw _ _ _ _ 0 root _ _
3 Sarah _ _ _ _ 2 dobj _ _
4 with _ _ _ _ 2 prep _ _
5 a _ _ _ _ 6 det _ _
6 telescope _ _ _ _ 4 pobj _ _
7 . _ _ _ _ 2 punct _ _
>>> print(f"arcs: {dataset.arcs[0]}\n"
f"rels: {dataset.rels[0]}\n"
f"probs: {dataset.probs[0].gather(1,torch.tensor(dataset.arcs[0]).unsqueeze(1)).squeeze(-1)}")
arcs: [2, 0, 2, 2, 6, 4, 2]
rels: ['nsubj', 'root', 'dobj', 'prep', 'det', 'pobj', 'punct']
probs: tensor([1.0000, 0.9999, 0.9966, 0.8944, 1.0000, 1.0000, 0.9999])SuPar also supports parsing from tokenized sentences or from file.
For BiLSTM-based semantic dependency parsing models, lemmas and POS tags are needed.
>>> import os
>>> import tempfile
>>> dep = Parser.load('biaffine-dep-en')
>>> dep.predict(['I', 'saw', 'Sarah', 'with', 'a', 'telescope', '.'], verbose=False)[0]
1 I _ _ _ _ 2 nsubj _ _
2 saw _ _ _ _ 0 root _ _
3 Sarah _ _ _ _ 2 dobj _ _
4 with _ _ _ _ 2 prep _ _
5 a _ _ _ _ 6 det _ _
6 telescope _ _ _ _ 4 pobj _ _
7 . _ _ _ _ 2 punct _ _
>>> path = os.path.join(tempfile.mkdtemp(), 'data.conllx')
>>> with open(path, 'w') as f:
... f.write('''# text = But I found the location wonderful and the neighbors very kind.
1\tBut\t_\t_\t_\t_\t_\t_\t_\t_
2\tI\t_\t_\t_\t_\t_\t_\t_\t_
3\tfound\t_\t_\t_\t_\t_\t_\t_\t_
4\tthe\t_\t_\t_\t_\t_\t_\t_\t_
5\tlocation\t_\t_\t_\t_\t_\t_\t_\t_
6\twonderful\t_\t_\t_\t_\t_\t_\t_\t_
7\tand\t_\t_\t_\t_\t_\t_\t_\t_
7.1\tfound\t_\t_\t_\t_\t_\t_\t_\t_
8\tthe\t_\t_\t_\t_\t_\t_\t_\t_
9\tneighbors\t_\t_\t_\t_\t_\t_\t_\t_
10\tvery\t_\t_\t_\t_\t_\t_\t_\t_
11\tkind\t_\t_\t_\t_\t_\t_\t_\t_
12\t.\t_\t_\t_\t_\t_\t_\t_\t_
''')
...
>>> dep.predict(path, pred='pred.conllx', verbose=False)[0]
# text = But I found the location wonderful and the neighbors very kind.
1 But _ _ _ _ 3 cc _ _
2 I _ _ _ _ 3 nsubj _ _
3 found _ _ _ _ 0 root _ _
4 the _ _ _ _ 5 det _ _
5 location _ _ _ _ 6 nsubj _ _
6 wonderful _ _ _ _ 3 xcomp _ _
7 and _ _ _ _ 6 cc _ _
7.1 found _ _ _ _ _ _ _ _
8 the _ _ _ _ 9 det _ _
9 neighbors _ _ _ _ 11 dep _ _
10 very _ _ _ _ 11 advmod _ _
11 kind _ _ _ _ 6 conj _ _
12 . _ _ _ _ 3 punct _ _
>>> con = Parser.load('crf-con-en')
>>> con.predict(['I', 'saw', 'Sarah', 'with', 'a', 'telescope', '.'], verbose=False)[0].pretty_print()
TOP
|
S
_____________|______________________
| VP |
| _________|____ |
| | | PP |
| | | ____|___ |
NP | NP | NP |
| | | | ___|______ |
_ _ _ _ _ _ _
| | | | | | |
I saw Sarah with a telescope .
>>> sdp = Parser.load('biaffine-sdp-en')
>>> sdp.predict([[('I','I','PRP'), ('saw','see','VBD'), ('Sarah','Sarah','NNP'), ('with','with','IN'),
('a','a','DT'), ('telescope','telescope','NN'), ('.','_','.')]],
verbose=False)[0]
1 I I PRP _ _ _ _ 2:ARG1 _
2 saw see VBD _ _ _ _ 0:root|4:ARG1 _
3 Sarah Sarah NNP _ _ _ _ 2:ARG2 _
4 with with IN _ _ _ _ _ _
5 a a DT _ _ _ _ _ _
6 telescope telescope NN _ _ _ _ 4:ARG2|5:BV _
7 . _ . _ _ _ _ _ _To train a model from scratch, it is preferred to use the command-line option, which is more flexible and customizable. Below is an example of training Biaffine Dependency Parser:
$ python -m supar.cmds.biaffine_dep train -b -d 0 -c biaffine-dep-en -p model -f charAlternatively, SuPar provides some equivalent command entry points registered in setup.py:
biaffine-dep, crf2o-dep, crf-con and biaffine-sdp, etc.
$ biaffine-dep train -b -d 0 -c biaffine-dep-en -p model -f charTo accommodate large models, distributed training is also supported:
$ python -m torch.distributed.launch --nproc_per_node=4 --master_port=10000 \
-m supar.cmds.biaffine_dep train -b -c biaffine-dep-en -d 0,1,2,3 -p model -f charYou can consult the PyTorch documentation and tutorials for more details.
The evaluation process resembles prediction:
>>> loss, metric = Parser.load('biaffine-dep-en').evaluate('ptb/test.conllx', verbose=False)
>>> print(loss, metric)
0.24214034126355097 UCM: 60.51% LCM: 50.37% UAS: 96.01% LAS: 94.41%See EXAMPLES for more instructions on training and evaluation.
The CRF models for Dependency/Constituency parsing are our recent works published in ACL 2020 and IJCAI 2020 respectively. If you are interested in them, please cite:
@inproceedings{zhang-etal-2020-efficient,
title = {Efficient Second-Order {T}ree{CRF} for Neural Dependency Parsing},
author = {Zhang, Yu and Li, Zhenghua and Zhang Min},
booktitle = {Proceedings of ACL},
year = {2020},
url = {https://www.aclweb.org/anthology/2020.acl-main.302},
pages = {3295--3305}
}
@inproceedings{zhang-etal-2020-fast,
title = {Fast and Accurate Neural {CRF} Constituency Parsing},
author = {Zhang, Yu and Zhou, Houquan and Li, Zhenghua},
booktitle = {Proceedings of IJCAI},
year = {2020},
doi = {10.24963/ijcai.2020/560},
url = {https://doi.org/10.24963/ijcai.2020/560},
pages = {4046--4053}
}