nlpods / LayerAttPoolerLinks
Don't Judge a Language Model by Its Last Layer: Contrastive Learning with Layer-Wise Attention Pooling
☆9Updated 2 years ago
Alternatives and similar repositories for LayerAttPooler
Users that are interested in LayerAttPooler are comparing it to the libraries listed below
Sorting:
- 🤖 Code for our EMNLP 2022 paper: "BotsTalk: Machine-sourced Framework for Automatic Curation of Large-scale Multi-skill Dialogue Dataset…☆16Updated 7 months ago
- KETOD Knowledge-Enriched Task-Oriented Dialogue☆32Updated 2 years ago
- Efficient Pre-training of Masked Language Model via Concept-based Curriculum Masking☆13Updated 2 years ago
- We construct and introduce DIALFACT, a testing benchmark dataset crowd-annotated conversational claims, paired with pieces of evidence fr…☆41Updated 2 years ago
- PyTorch reimplementation of the paper "SimCLS: A Simple Framework for Contrastive Learning of Abstractive Summarization"☆16Updated 3 years ago
- code for the table-based open domain question answering project, with paper title: "Reasoning over Hybrid Chain for Table-and-Text Open D…☆12Updated 2 years ago
- NeuralWOZ: Learning to Collect Task-Oriented Dialogue via Model-based Simulation (ACL-IJCNLP 2021)☆36Updated 3 years ago
- Supervised Contrastive Learning for Downstream Optimized Sequence Representations☆27Updated 3 years ago
- MetricEval: A framework that conceptualizes and operationalizes four main components of metric evaluation, in terms of reliability and va…☆11Updated last year
- ☆33Updated 2 months ago
- [NAACL 2024] Official repository for "KTRL+F: Knowledge-Augmented In-Document Search"☆23Updated 7 months ago
- Saving Dense Retriever from Shortcut Dependency in Conversational Search (EMNLP 2022)☆18Updated 2 years ago
- The contrastive token loss function for reducing generative repetition of autoregressive neural language models.☆13Updated 3 years ago
- ☆21Updated last year
- IntructIR, a novel benchmark specifically designed to evaluate the instruction following ability in information retrieval models. Our foc…☆32Updated 11 months ago
- Code for EMNLP 2021 paper: Improving Sequence-to-Sequence Pre-training via Sequence Span Rewriting☆17Updated 3 years ago
- ACL22 paper: Imputing Out-of-Vocabulary Embeddings with LOVE Makes Language Models Robust with Little Cost☆41Updated last year
- TBC☆27Updated 2 years ago
- Pytorch Implementation of EncT5: Fine-tuning T5 Encoder for Non-autoregressive Tasks☆63Updated 3 years ago
- ACL 2023 short: Balancing Lexical and Semantic Quality in Abstractive Summarization☆15Updated last year
- ☆35Updated 2 years ago
- ☆15Updated 3 years ago
- A Benchmark for Robust, Multi-evidence, Multi-answer Question Answering☆16Updated 2 years ago
- The official implemetation of "Evidentiality-guided Generation for Knowledge-Intensive NLP Tasks" (NAACL 2022).☆43Updated 2 years ago
- ☆6Updated 3 years ago
- Keep Me Updated! Memory Management in Long-term Conversations (Findings of EMNLP 2022)☆30Updated 2 years ago
- [NAACL 2021] Designing a Minimal Retrieve-and-Read System for Open-Domain Question Answering☆36Updated 4 years ago
- A Framework aims to wisely initialize unseen subword embeddings in PLMs for efficient large-scale continued pretraining☆16Updated last year
- PyTorch code for "FactPEGASUS: Factuality-Aware Pre-training and Fine-tuning for Abstractive Summarization" (NAACL 2022)☆39Updated 2 years ago
- ☆10Updated 8 months ago