gooofy / transformer-lm
Transformer language model (GPT-2) with sentencepiece tokenizer
☆10Updated 5 years ago
Alternatives and similar repositories for transformer-lm:
Users that are interested in transformer-lm are comparing it to the libraries listed below
- An annotated corpus of argumentative microtexts☆39Updated 2 years ago
- Named Entity Recognition (LSTM + CRF + FastText) with models for [historic] German☆26Updated 3 years ago
- BERT and ELECTRA models trained on Europeana Newspapers☆37Updated 3 years ago
- A python wrapper for the multilingual temporal tagger HeidelTime.☆26Updated 2 years ago
- ☆16Updated 5 years ago
- Alignment and annotation for comparable documents.☆22Updated 6 years ago
- German lemmatization with IWNLP as extension for spaCy☆24Updated last year
- Plan and train German transformer models.☆23Updated 3 years ago
- Experiments with Zalando's flair library☆34Updated last year
- Diagnostic tests for linguistic capacities in language models☆66Updated 2 years ago
- Dutch coreference resolution & dialogue analysis using deterministic rules☆21Updated last year
- UFSAC is a resource containing all WordNet Sense Annotated Corpora, and a Java library for manipulating them☆37Updated 2 years ago
- ☆44Updated 2 years ago
- CONLL-U to Pandas DataFrame☆31Updated 7 years ago
- Repository for rstWeb, a browser based annotation interface for Rhetorical Structure Theory☆41Updated 2 months ago
- Repository with code for MaChAmp: https://aclanthology.org/2021.eacl-demos.22/☆83Updated last week
- Disambiguate is a tool for training and using state of the art neural WSD models☆59Updated 2 years ago
- Analyze Argumentation and Rhetorical Aspects in Scientific Writing.☆19Updated 2 years ago
- ☆64Updated last year
- Appraise evaluation system for manual evaluation of machine translation output☆74Updated 3 years ago
- ☆36Updated 7 years ago
- This repository contains the code for "BERTRAM: Improved Word Embeddings Have Big Impact on Contextualized Representations".☆63Updated 4 years ago
- Extracting scientific claims from biomedical abstracts (powered by AllenNLP)☆140Updated 3 years ago
- German GPT-2 model☆32Updated 3 years ago
- Klexikon: A German Dataset for Joint Summarization and Simplification☆17Updated 2 years ago
- Language Modelling Makes Sense - WSD (and more) with Contextual Embeddings☆95Updated last year
- A set of media framing annotations, along with scripts for obtaining the corresponding news articles☆49Updated 5 years ago
- Code for the paper "Simple, Interpretable and Stable Method for Detecting Words with Usage Change across Corpora", ACL 2020.☆18Updated 4 years ago
- ☆22Updated 3 years ago
- ☆15Updated 6 years ago