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 2 years ago
Alternatives and similar repositories for udify
Users that are interested in udify are comparing it to the libraries listed below
Sorting:
- Easier Automatic Sentence Simplification Evaluation☆161Updated last year
- Obtain Word Alignments using Pretrained Language Models (e.g., mBERT)☆361Updated last year
- A CoNLL-U parser that takes a CoNLL-U formatted string and turns it into a nested python dictionary.☆316Updated 3 months ago
- Unsupervised Statistical Machine Translation☆229Updated 4 years ago
- OpusFilter - Parallel corpus processing toolkit☆104Updated 2 months ago
- Interpretable Evaluation for (Almost) All NLP Tasks☆195Updated 2 years ago
- A tool for holistic analysis of language generations systems☆468Updated 3 years ago
- Bicleaner is a parallel corpus classifier/cleaner that aims at detecting noisy sentence pairs in a parallel corpus.☆157Updated 11 months ago
- Scripts to preprocess training and test data and to run fast_align and giza☆108Updated 3 years ago
- Fast + Non-Autoregressive Grammatical Error Correction using BERT. Code and Pre-trained models for paper "Parallel Iterative Edit Models …☆230Updated 2 years ago
- This is a CoNLL formatted version of the OntoNotes 5.0 release.☆189Updated 10 years ago
- Efficient Low-Memory Aligner☆144Updated 4 months ago
- JFLEG (JHU FLuency-Extended GUG) corpus for Grammatical Error Correction Evaluation☆113Updated last year
- Language Modelling Makes Sense - WSD (and more) with Contextual Embeddings☆95Updated last year
- Disambiguate is a tool for training and using state of the art neural WSD models☆60Updated 3 years ago
- Linguistically-Informed Self-Attention implemented in TensorFlow☆203Updated 6 years ago
- Automatic extraction of edited sentences from text edition histories.☆83Updated 3 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
- Text Simplification System and Dataset☆122Updated last year
- This is the reference implementation of commonly used coreference metrics.☆74Updated 7 years ago
- GlossBERT: BERT for Word Sense Disambiguation with Gloss Knowledge (EMNLP 2019)☆95Updated 2 years ago
- Annotated dataset of 100 works of fiction to support tasks in natural language processing and the computational humanities.☆357Updated 2 years ago
- Robust and Fast tokenizations alignment library for Rust and Python https://tamuhey.github.io/tokenizations/☆192Updated last year
- A neural word aligner based on multilingual BERT☆348Updated 3 years ago
- Coreference Resolution With Entity Equalization☆40Updated 2 years ago
- A minimal, pure Python library to interface with CoNLL-U format files.☆151Updated last year
- Massively Multilingual Transfer for NER☆86Updated 3 years ago
- Code to reproduce the experiments from the paper.☆101Updated last year
- The Benchmark of Linguistic Minimal Pairs☆150Updated 2 years ago
- Text tokenization and sentence segmentation (segtok v2)☆205Updated 3 years ago