Hyperparticle / udifyLinks
A single model that parses Universal Dependencies across 75 languages. Given a sentence, jointly predicts part-of-speech tags, morphology tags, lemmas, and dependency trees.
☆223Updated 3 years ago
Alternatives and similar repositories for udify
Users that are interested in udify are comparing it to the libraries listed below
Sorting:
- Efficient Low-Memory Aligner☆146Updated last year
- A minimal, pure Python library to interface with CoNLL-U format files.☆153Updated last month
- Disambiguate is a tool for training and using state of the art neural WSD models☆60Updated 6 months ago
- Easier Automatic Sentence Simplification Evaluation☆165Updated 2 years ago
- Text Simplification System and Dataset☆124Updated 2 years ago
- Obtain Word Alignments using Pretrained Language Models (e.g., mBERT)☆385Updated 2 years ago
- UFSAC is a resource containing all WordNet Sense Annotated Corpora, and a Java library for manipulating them☆38Updated 3 years ago
- Scripts to preprocess training and test data and to run fast_align and giza☆107Updated 4 years ago
- A CoNLL-U parser that takes a CoNLL-U formatted string and turns it into a nested python dictionary.☆319Updated last week
- Open-Source Machine Translation Quality Estimation in PyTorch☆231Updated 3 years ago
- Automatic extraction of edited sentences from text edition histories.☆83Updated 3 years ago
- GlossBERT: BERT for Word Sense Disambiguation with Gloss Knowledge (EMNLP 2019)☆97Updated 3 years ago
- Cross-Lingual Alignment of Contextual Word Embeddings☆99Updated 5 years ago
- Unsupervised Statistical Machine Translation☆231Updated 5 years ago
- Massively Multilingual Transfer for NER☆86Updated 4 years ago
- Exploring Neural Text Simplification☆73Updated 7 years ago
- One million English sentences, each split into two sentences that together preserve the original meaning, extracted from Wikipedia edits.☆123Updated 6 years ago
- This is the reference implementation of commonly used coreference metrics.☆76Updated 7 years ago
- Coreference Resolution With Entity Equalization☆41Updated 3 years ago
- Bicleaner is a parallel corpus classifier/cleaner that aims at detecting noisy sentence pairs in a parallel corpus.☆160Updated last year
- Code to reproduce the experiments from the paper.☆103Updated 2 years ago
- Transformer based translation quality estimation☆114Updated 2 years ago
- JFLEG (JHU FLuency-Extended GUG) corpus for Grammatical Error Correction Evaluation☆113Updated 2 years ago
- Interpretable Evaluation for (Almost) All NLP Tasks☆195Updated 3 months ago
- Language Modelling Makes Sense - WSD (and more) with Contextual Embeddings☆96Updated 2 years ago
- Linguistically-Informed Self-Attention implemented in TensorFlow☆203Updated 6 years ago
- Scientific Document Summarization Corpus and Annotations from the WING NUS group.☆215Updated 2 years ago
- OpusFilter - Parallel corpus processing toolkit☆115Updated 3 weeks ago
- The official released annotations, both in .prop pointer format and as conll files. Does not contain the source texts☆144Updated 3 years ago
- A tool for holistic analysis of language generations systems☆471Updated 3 months ago