timoschick / one-token-approximationLinks
This repository contains the code for applying One-Token Approximation to a pretrained language model using subword-level tokenization.
☆11Updated 5 years ago
Alternatives and similar repositories for one-token-approximation
Users that are interested in one-token-approximation are comparing it to the libraries listed below
Sorting:
- ☆46Updated 6 years ago
- This repository contains the code for "BERTRAM: Improved Word Embeddings Have Big Impact on Contextualized Representations".☆64Updated 5 years ago
- Research code for the paper "How Good is Your Tokenizer? On the Monolingual Performance of Multilingual Language Models"☆28Updated 4 years ago
- EMNLP 2021 Tutorial: Multi-Domain Multilingual Question Answering☆38Updated 4 years ago
- Code and data for the paper "Soft Gazetteers for Low-resource Named Entity Recognition"☆19Updated 5 years ago
- Analyzing mBERT's multilinguality in a small laboratory setting☆13Updated 2 years ago
- Hyperparameter Search for AllenNLP☆140Updated 11 months ago
- SUPERT: Unsupervised multi-document summarization evaluation & generation☆96Updated 3 years ago
- ☆13Updated 4 years ago
- Repository with code for MaChAmp: https://aclanthology.org/2021.eacl-demos.22/☆90Updated this week
- ☆51Updated 3 years ago
- ☆68Updated 9 months ago
- We are creating a challenging new benchmark MultiReQA: A Cross-Domain Evaluation for Retrieval Question Answering Models. Retrieval quest…☆31Updated 5 years ago
- SacreROUGE is a library dedicated to the use and development of text generation evaluation metrics with an emphasis on summarization.☆148Updated 3 years ago
- A coreference evaluation package for the CoNLL and ARRAU datasets☆41Updated 5 years ago
- Tool to perform paired evaluation of automatic systems☆13Updated 4 years ago
- Fine-tuned Transformers compatible BERT models for Sequence Tagging☆40Updated 5 years ago
- Codebase for probing and visualizing multilingual models.☆49Updated 5 years ago
- ☆92Updated 4 years ago
- Code and data for: Low Resource Grammatical Error Correction Using Wikipedia Edits (WNUT 2018)☆17Updated last year
- The NLPStatTest project☆12Updated 3 years ago
- Code to support the paper "Question and Answer Test-Train Overlap in Open-Domain Question Answering Datasets"☆65Updated 4 years ago
- Pytorch implementation of Highly Parallel Autoregressive Entity Linking with Discriminative Correction☆66Updated 3 years ago
- ☆75Updated 4 years ago
- PyTorch implementation of NAACL 2021 paper "Multi-view Subword Regularization"☆26Updated 4 years ago
- REALSumm: Re-evaluating Evaluation in Text Summarization☆73Updated 4 months ago
- ACL'2020: Contextualized Sparse Representations for Real-Time Open-Domain Question Answering☆49Updated 5 years ago
- Code for papers "A Surprisingly Robust Trick for Winograd Schema Challenge" and "WikiCREM: A Large Unsupervised Corpus for Coreference Re…☆71Updated 3 years ago
- Code for our TSD paper "TOKEN is a MASK: Few-shot Named Entity Recognition with Pre-trained Language Models"☆14Updated 3 years ago
- [ACL 20] Probing Linguistic Features of Sentence-level Representations in Neural Relation Extraction☆13Updated 5 years ago