INK-USC / CALM
Source code for ICLR 2021 paper : Pre-training Text-to-Text Transformers for Concept-Centric Common Sense
☆27Updated 3 years ago
Related projects ⓘ
Alternatives and complementary repositories for CALM
- Source code for paper on commonsense reasoning for 2020 Annual Conference of the Association for Computational Linguistics (ACL) 2020.☆28Updated 3 months ago
- Code Repo for the ACL21 paper "Common Sense Beyond English: Evaluating and Improving Multilingual LMs for Commonsense Reasoning"☆22Updated 3 years ago
- EMNLP'2020: Look at the First Sentence: Position Bias in Question Answering☆29Updated 4 years ago
- Code for our NAACL-2021 paper "Disentangling Semantics and Syntax in Sentence Embeddings with Pre-trained Language Models".☆24Updated 3 years ago
- ☆21Updated 3 years ago
- TGLS: Unsupervised Text Generation by Learning from Search☆25Updated 3 years ago
- The implementation of the paper "Harvesting and Refining Question-Answer Pairs for Unsupervised QA"☆33Updated 3 years ago
- [EMNLP 2020] Discern: Discourse-Aware Entailment Reasoning Network for Conversational Machine Reading☆36Updated last year
- ☆21Updated 3 years ago
- A unified approach to explain conditional text generation models. Pytorch. The code of paper "Local Explanation of Dialogue Response Gene…☆18Updated 2 years ago
- Code and Data for our EMNLP 2020 paper titled 'Learning to Explain: Datasets and Models for Identifying Valid Reasoning Chains in Multiho…☆27Updated 2 years ago
- Codes for NAACL 2021 paper 'Noisy Self-Knowledge Distillation for Text Summarization'☆23Updated 3 years ago
- Code for paper "Extract, Denoise and Enforce: Evaluating and Improving Concept Preservation for Text-to-Text Generation" EMNLP 2021 and "…☆18Updated 2 years ago
- ☆24Updated last year
- Learning Contextualized Knowledge Structures for Commonsense Reasoning☆17Updated last year
- Pytorch Implementation of "Contrastive Representation Learning for Exemplar-Guided Paraphrase Generation"☆25Updated last year
- ReConsider is a re-ranking model that re-ranks the top-K (passage, answer-span) predictions of an Open-Domain QA Model like DPR (Karpukhi…☆49Updated 3 years ago
- [ACL'21 Findings] Why Machine Reading Comprehension Models Learn Shortcuts?☆16Updated last year
- Implementation for paper " Unsupervised Domain Adaptation on Reading Comprehension "☆30Updated 4 years ago
- Common Sense or World Knowledge? Investigating Adapter-Based Knowledge Injection into Pretrained Transformers☆20Updated 3 years ago
- Posterior Control of Blackbox Generation☆23Updated 4 years ago
- Code and data for "Retrieval Enhanced Model for Commonsense Generation" (ACL-IJCNLP 2021).☆28Updated 2 years ago
- Code for NAACL 2021 full paper "Efficient Attentions for Long Document Summarization"☆64Updated 3 years ago
- [NAACL'22-Findings] Dataset for "Retrieval-Augmented Multilingual Keyphrase Generation with Retriever-Generator Iterative Training"☆18Updated 2 years ago
- Code Repo for "Differentiable Open-Ended Commonsense Reasoning" (NAACL 2021)☆31Updated last year
- Code for "Understanding Neural Abstractive Summarization Models via Uncertainty" (EMNLP20)☆30Updated 4 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
- Code base for paper "Zero-Shot Cross-Lingual Transfer with Meta Learning"☆33Updated this week
- ☆23Updated last year
- Source code of the paper "Do Syntax Trees Help Pre-trained Transformers Extract Information?" (EACL 2021)☆72Updated 2 years ago