chrishokamp / dynamic-transformer-ensembles
Dynamic ensemble decoding with transformer-based models
☆29Updated last year
Related projects ⓘ
Alternatives and complementary repositories for dynamic-transformer-ensembles
- On Generating Extended Summaries of Long Documents☆77Updated 3 years ago
- This repository contains the code for "BERTRAM: Improved Word Embeddings Have Big Impact on Contextualized Representations".☆63Updated 4 years ago
- Source code for our AAAI 2020 paper P-SIF: Document Embeddings using Partition Averaging☆35Updated 4 years ago
- A repository for our AAAI-2020 Cross-lingual-NER paper. Code will be updated shortly.☆46Updated last year
- Code for the paper: Saying No is An Art: Contextualized Fallback Responses for Unanswerable Dialogue Queries☆19Updated 2 years ago
- A embed able annotation tool for end to end cross document co-reference☆41Updated last year
- SUPERT: Unsupervised multi-document summarization evaluation & generation☆91Updated last year
- ☆30Updated 3 years ago
- Fine-tune transformers with pytorch-lightning☆44Updated 2 years ago
- ☆73Updated 3 years ago
- LongSumm - Scientific Document Summarization Task☆74Updated 2 years ago
- Use BERT to Fill in the Blanks☆82Updated 2 years ago
- QED: A Framework and Dataset for Explanations in Question Answering☆115Updated 3 years ago
- ☆56Updated 3 months ago
- Massively Multilingual Transfer for NER☆85Updated 3 years ago
- Implementation, trained models and result data for the paper "Aspect-based Document Similarity for Research Papers" #COLING2020☆62Updated 6 months ago
- [EMNLP-Findings 2020] Adapting BERT for Word Sense Disambiguation with Gloss Selection Objective and Example Sentences☆62Updated 6 months ago
- ☆56Updated 3 years ago
- The implementation of the papers on dual learning of natural language understanding and generation. (ACL2019,2020; Findings of EMNLP 2020…☆66Updated 4 years ago
- ☆33Updated last year
- The NewSHead dataset is a multi-doc headline dataset used in NHNet for training a headline summarization model.☆36Updated 2 years ago
- Examples for aligning, padding and batching sequence labeling data (NER) for use with pre-trained transformer models☆65Updated last year
- This repository contains the code for the Form-Context Model and its Attentive Mimicking variant.☆31Updated 4 years ago
- BERT models for many languages created from Wikipedia texts☆34Updated 4 years ago
- Corresponding code repo for the paper at COLING 2020 - ARGMIN 2020: "DebateSum: A large-scale argument mining and summarization dataset"☆53Updated 2 years ago
- Codebase, data and models for the Keep it Simple paper at ACL2021☆36Updated last year
- Lexical Simplification with Pretrained Encoders☆69Updated 3 years ago
- Introduction to the recently released T5 model from the paper - Exploring the Limits of Transfer Learning with a Unified Text-to-Text Tra…☆35Updated 4 years ago
- State of the art Semantic Sentence Embeddings☆98Updated 2 years ago
- KitanaQA: Adversarial training and data augmentation for neural question-answering models☆57Updated last year