john-hewitt / embed-init
Rough codebase for exploring initialization strategies for new word embeddings in pretrained LMs
☆14Updated 2 years ago
Related projects ⓘ
Alternatives and complementary repositories for embed-init
- ☆28Updated 2 years ago
- Code and pre-trained models for "ReasonBert: Pre-trained to Reason with Distant Supervision", EMNLP'2021☆29Updated last year
- Official repository for our EACL 2023 paper "LongEval: Guidelines for Human Evaluation of Faithfulness in Long-form Summarization" (https…☆43Updated 3 months ago
- ☆12Updated 3 years ago
- EMNLP 2021 Adapting Language Models for Zero-shot Learning by Meta-tuning on Dataset and Prompt Collections☆49Updated 3 years ago
- ☆46Updated 2 years ago
- ☆14Updated last month
- We are creating a challenging new benchmark MultiReQA: A Cross-Domain Evaluation for Retrieval Question Answering Models. Retrieval quest…☆30Updated 4 years ago
- Repo for ICML23 "Why do Nearest Neighbor Language Models Work?"☆56Updated last year
- Learning to Model Editing Processes☆26Updated 2 years ago
- A repository for experiments in quality-aware decoding☆15Updated 2 years ago
- Exploring Few-Shot Adaptation of Language Models with Tables☆23Updated 2 years ago
- Efficient Memory-Augmented Transformers☆34Updated last year
- WebRED is a large and diverse manually annotated dataset for extracting relationships from a variety of text found on the World Wide Web.☆22Updated 3 years ago
- Code for our TSD paper "TOKEN is a MASK: Few-shot Named Entity Recognition with Pre-trained Language Models"☆14Updated 2 years ago
- Explicit Alignment Objectives for Multilingual Bidirectional Encoders☆13Updated 3 years ago
- CCQA A New Web-Scale Question Answering Dataset for Model Pre-Training☆32Updated 2 years ago
- Adding new tasks to T0 without catastrophic forgetting☆30Updated 2 years ago
- ☆37Updated last year
- A Controllable Model of Grounded Response Generation (AAAI 21)☆13Updated 2 years ago
- ☆12Updated 10 months ago
- A method for evaluating the high-level coherence of machine-generated texts. Identifies high-level coherence issues in transformer-based …☆11Updated last year
- Unifew: Unified Fewshot Learning Model☆18Updated 3 years ago
- ReCross: Unsupervised Cross-Task Generalization via Retrieval Augmentation☆22Updated 2 years ago
- Code for the paper "A Theoretical Analysis of the Repetition Problem in Text Generation" in AAAI 2021.☆51Updated 2 years ago
- Consistent dialogue generation☆16Updated 2 years ago
- Suite of 500 procedurally-generated NLP tasks to study language model adaptability☆21Updated 2 years ago
- Implementation of the paper 'Sentence Bottleneck Autoencoders from Transformer Language Models'☆17Updated 2 years ago
- Code and data for the paper "Soft Gazetteers for Low-resource Named Entity Recognition"☆19Updated 4 years ago