mourga / transformer-uncertainty
Code for evaluating uncertainty estimation methods for Transformer-based architectures in natural language understanding tasks.
☆40Updated 3 years ago
Related projects: ⓘ
- Source code for the ACL 2019 paper "Attention-based Conditioning Methods for External Knowledge Integration"☆59Updated 2 years ago
- Code for the EMNLP 2021 Paper "Active Learning by Acquiring Contrastive Examples" & the ACL 2022 Paper "On the Importance of Effectively …☆117Updated 2 years ago
- LSTM and QRNN Language Model Toolkit for PyTorch 1.2.0!☆21Updated 4 years ago
- PyTorch source code of NAACL 2021 paper "Improving the Lexical Ability of Pretrained Language Models for Unsupervised Neural Machine Tran…☆17Updated last year
- EMNLP 2021 - Frustratingly Simple Pretraining Alternatives to Masked Language Modeling☆31Updated 2 years ago
- Python source code for EMNLP 2021 Findings paper: "Subword Mapping and Anchoring Across Languages".☆13Updated 3 years ago
- ☆57Updated 2 years ago
- Code and datasets for the EMNLP 2020 paper "Calibration of Pre-trained Transformers"☆55Updated last year
- Code Repo for the ACL21 paper "Common Sense Beyond English: Evaluating and Improving Multilingual LMs for Commonsense Reasoning"☆22Updated 2 years ago
- ☆29Updated 2 years ago
- ☆37Updated 3 years ago
- Code of NAACL 2022 "Efficient Hierarchical Domain Adaptation for Pretrained Language Models" paper.☆32Updated 11 months ago
- Rationales for Sequential Predictions☆40Updated 2 years ago
- Code for ACL 2022 paper "Expanding Pretrained Models to Thousands More Languages via Lexicon-based Adaptation"☆30Updated 2 years ago
- ☆14Updated 3 years ago
- Measuring the Mixing of Contextual Information in the Transformer☆24Updated last year
- UDapter is a multilingual dependency parser that uses "contextual" adapters together with language-typology features for language-specifi…☆30Updated last year
- ☆27Updated last year
- ☆40Updated 3 years ago
- ACL 2021 paper "Style is NOT a single variable: Case Studies for Cross-Style Language Understanding " by Dongyeop Kang and Eduard Hovy☆13Updated 3 years ago
- Code base for the EMNLP 2021 Findings paper: Cartography Active Learning☆14Updated last year
- Constrained decoding utilities for text generation using Huggingface seq2seq models☆22Updated last year
- The geometry of multilingual language model representations (EMNLP 2022).☆15Updated last year
- Tool to perform paired evaluation of automatic systems☆12Updated 2 years ago
- ☆11Updated 4 years ago
- Code base for " Zero-Shot Cross-Lingual Transfer with Meta Learning" papaer☆33Updated 3 years ago
- ☆20Updated 3 years ago
- ☆23Updated 7 months ago
- ☆40Updated 3 years ago
- Python source code for EMNLP 2020 paper "Reusing a Pretrained Language Model on Languages with Limited Corpora for Unsupervised NMT".☆35Updated 2 years ago