Skip to content
Open
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
37 changes: 35 additions & 2 deletions website/meta/universe.json
Original file line number Diff line number Diff line change
Expand Up @@ -69,6 +69,40 @@
"dbpedia"
]
},
{
"id": "hashformers",
"title": "Hashformers",
"slogan": "Word segmentation with transformers and beam search",
"description": "Hashformers uses transformers and beam search to segment text without spaces into words. It fills the gap between heuristic-based splitters and LLM prompt-based segmentation, supporting any Hugging Face model. Recognized as state-of-the-art for hashtag segmentation at LREC 2022.",
"github": "ruanchaves/hashformers",
"pip": "hashformers[spacy]",
"code_example": [
"import spacy",
"import hashformers.spacy # registers the 'hashformers' component",
"",
"nlp = spacy.blank('en')",
"nlp.add_pipe('hashformers', config={'model': 'distilgpt2'})",
"",
"doc = nlp('#weneedanationalpark')",
"print(doc._.segmented) # 'we need a national park'"
],
"code_language": "python",
"url": "https://github.com/ruanchaves/hashformers",
"author": "Ruan Chaves Rodrigues",
"author_links": {
"github": "ruanchaves"
},
"category": [
"pipeline",
"standalone"
],
"tags": [
"word-segmentation",
"hashtags",
"transformers",
"beam-search"
]
},
{
"id": "spacy-vscode",
"title": "spaCy Visual Studio Code Extension",
Expand Down Expand Up @@ -2739,7 +2773,6 @@
"courses"
]
},

{
"type": "education",
"id": "video-spacys-ner-model",
Expand Down Expand Up @@ -5814,4 +5847,4 @@
]
}
]
}
}