Skip to content

Commit

Permalink
GH-28: ner, pos and chunking models
Browse files Browse the repository at this point in the history
  • Loading branch information
aakbik committed Aug 1, 2018
1 parent 4d214c8 commit 623ca21
Show file tree
Hide file tree
Showing 2 changed files with 37 additions and 16 deletions.
15 changes: 15 additions & 0 deletions flair/embeddings.py
Original file line number Diff line number Diff line change
Expand Up @@ -144,6 +144,11 @@ def __init__(self, embeddings):
cached_path(os.path.join(base_path, 'glove.gensim.vectors.npy'), cache_dir='embeddings')
embeddings = cached_path(os.path.join(base_path, 'glove.gensim'), cache_dir='embeddings')

# twitter embeddings
if embeddings.lower() == 'twitter' or embeddings.lower() == 'en-twitter':
cached_path(os.path.join(base_path, 'twitter.gensim.vectors.npy'), cache_dir='embeddings')
embeddings = cached_path(os.path.join(base_path, 'twitter.gensim'), cache_dir='embeddings')

# KOMNIOS embeddings
if embeddings.lower() == 'extvec' or embeddings.lower() == 'en-extvec':
cached_path(os.path.join(base_path, 'extvec.gensim.vectors.npy'), cache_dir='embeddings')
Expand Down Expand Up @@ -329,6 +334,16 @@ def __init__(self, model, detach: bool = True):
base_path = 'https://s3.eu-central-1.amazonaws.com/alan-nlp/resources/embeddings/lm-news-english-backward-v0.2rc.pt'
model = cached_path(base_path, cache_dir='embeddings')

# news-english-forward
if model.lower() == 'news-forward-fast':
base_path = 'https://s3.eu-central-1.amazonaws.com/alan-nlp/resources/embeddings/lm-news-english-forward-1024-v0.2rc.pt'
model = cached_path(base_path, cache_dir='embeddings')

# news-english-backward
if model.lower() == 'news-backward-fast':
base_path = 'https://s3.eu-central-1.amazonaws.com/alan-nlp/resources/embeddings/lm-news-english-backward-1024-v0.2rc.pt'
model = cached_path(base_path, cache_dir='embeddings')

# mix-english-forward
if model.lower() == 'mix-forward':
base_path = 'https://s3.eu-central-1.amazonaws.com/alan-nlp/resources/embeddings/lm-mix-english-forward-v0.2rc.pt'
Expand Down
38 changes: 22 additions & 16 deletions flair/models/sequence_tagger_model.py
Original file line number Diff line number Diff line change
Expand Up @@ -407,16 +407,28 @@ def load(model: str):
'en-ner-conll03-v0.2.pt'])
model_file = cached_path(base_path, cache_dir='models')

if model.lower() == 'ner-fast':
base_path = '/'.join([aws_resource_path,
'NER-conll03--h256-l1-b32-experimental--fast-v0.2',
'en-ner-fast-conll03-v0.2.pt'])
model_file = cached_path(base_path, cache_dir='models')

if model.lower() == 'frame':
base_path = '/'.join([aws_resource_path,
'FRAME-conll12--h256-l1-b8-%2Bnews%2Bnews-forward%2Bnews-backward--v0.2',
'en-frame-ontonotes-v0.2.pt'])
model_file = cached_path(base_path, cache_dir='models')

if model.lower() == 'ner-ontonotes':
base_path = '/'.join([aws_resource_path,
'NER-ontoner--h256-l1-b32-%2Bft-crawl%2Bnews-forward%2Bnews-backward--anneal',
'en-ner-ontonotes-v0.1.pt'])
'NER-ontoner--h256-l1-b32-%2Bcrawl%2Bnews-forward%2Bnews-backward--v0.2',
'en-ner-ontonotes-v0.2.pt'])
model_file = cached_path(base_path, cache_dir='models')

if model.lower() == 'chunk':
base_path = '/'.join([aws_resource_path,
'NP-conll2000--h256-l1-b32-%2Bnews-forward%2Bnews-backward--anneal',
'en-chunk-conll2000-v0.1.pt'])
'NP-conll2000--h256-l1-b32-%2Bnews-forward%2Bnews-backward--v0.2',
'en-chunk-conll2000-v0.2.pt'])
model_file = cached_path(base_path, cache_dir='models')

if model.lower() == 'pos':
Expand All @@ -425,28 +437,22 @@ def load(model: str):
'en-pos-ontonotes-v0.1.pt'])
model_file = cached_path(base_path, cache_dir='models')

if model.lower() == 'frame':
base_path = '/'.join([aws_resource_path,
'FRAME-conll12--h256-l1-b8-%2Bnews%2Bnews-forward%2Bnews-backward--anneal',
'en-frame-ontonotes-v0.1.pt'])
model_file = cached_path(base_path, cache_dir='models')

if model.lower() == 'de-pos':
base_path = '/'.join([aws_resource_path,
'UPOS-udgerman--h256-l1-b8-%2Bgerman-forward%2Bgerman-backward--anneal',
'de-pos-ud-v0.1.pt'])
'UPOS-udgerman--h256-l1-b8-%2Bgerman-forward%2Bgerman-backward--v0.2',
'de-pos-ud-v0.2.pt'])
model_file = cached_path(base_path, cache_dir='models')

if model.lower() == 'de-ner':
base_path = '/'.join([aws_resource_path,
'NER-conll03ger--h256-l1-b32-%2Bde-fasttext%2Bgerman-forward%2Bgerman-backward--anneal',
'de-ner-conll03-v0.1.pt'])
'NER-conll03ger--h256-l1-b32-%2Bde-fasttext%2Bgerman-forward%2Bgerman-backward--v0.2',
'de-ner-conll03-v0.2.pt'])
model_file = cached_path(base_path, cache_dir='models')

if model.lower() == 'de-ner-germeval':
base_path = '/'.join([aws_resource_path,
'NER-germeval--h256-l1-b32-%2Bde-fasttext%2Bgerman-forward%2Bgerman-backward--anneal',
'de-ner-germeval-v0.1.pt'])
'NER-germeval--h256-l1-b32-%2Bde-fasttext%2Bgerman-forward%2Bgerman-backward--v0.2',
'de-ner-germeval-v0.2.pt'])
model_file = cached_path(base_path, cache_dir='models')

if model_file is not None:
Expand Down

0 comments on commit 623ca21

Please sign in to comment.