shayneobrien/coreference-resolution
Efficient and clean PyTorch reimplementation of "End-to-end Neural Coreference Resolution" (Lee et al., EMNLP 2017).
This project helps clarify text by identifying all expressions that refer to the same person, place, or thing within a document. You provide a text document, and it outputs grouped mentions of entities (e.g., "Arya Stark," "her," and "Nymeria" are recognized and linked). This is useful for anyone working with unstructured text who needs to understand relationships between words and phrases, such as linguists, content analysts, or researchers.
187 stars. No commits in the last 6 months.
Use this if you need to automatically identify and group all coreferring expressions within your English text documents.
Not ideal if you don't have access to the OntoNotes 5.0 dataset and specific word embeddings, as these are required for data preparation.
Stars
187
Forks
58
Language
Perl
License
—
Category
Last pushed
Jan 11, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/shayneobrien/coreference-resolution"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
facebookresearch/stopes
A library for preparing data for machine translation research (monolingual preprocessing,...
Droidtown/ArticutAPI
API of Articut 中文斷詞 (兼具語意詞性標記)：「斷詞」又稱「分詞」，是中文資訊處理的基礎。Articut 不用機器學習，不需資料模型，只用現代白話中文語法規則，即能達到...
rkcosmos/deepcut
A Thai word tokenization library using Deep Neural Network
fukuball/jieba-php
"結巴"中文分詞：做最好的 PHP 中文分詞、中文斷詞組件。 / "Jieba" (Chinese for "to stutter") Chinese text segmentation:...
pytorch/text
Models, data loaders and abstractions for language processing, powered by PyTorch