ewsheng / decoding-biases
Scripts to evaluate various bias metrics for different NLG models + decoding algorithms
☆15Updated 11 months ago
Related projects ⓘ
Alternatives and complementary repositories for decoding-biases
- Perturbation CheckLists for Evaluating NLG Evaluation Metrics, EMNLP 2021☆9Updated 2 years ago
- Dataset + classifier tools to study social perception biases in natural language generation☆66Updated last year
- Data and code for APPDIA: A Discourse-aware Transformer-based Style Transfer Model for Offensive Social Media Conversations (COLING 2022)…☆12Updated 2 years ago
- DiscoScore: Evaluating Text Generation with BERT and Discourse Coherence☆35Updated last year
- Bias Benchmark for Natural Language Inference. Code repo for the Findings of NAACL 2022 paper "On Measuring Social Biases in Prompt-Based…☆15Updated 2 years ago
- LAReQA is a challenging benchmark for evaluating language agnostic answer retrieval from a multilingual candidate pool. This repository c…☆14Updated 4 years ago
- ☆28Updated 3 years ago
- Adversarial attacks against claim detection systems at FEVER☆11Updated last year
- ☆15Updated 3 years ago
- Code & data for EMNLP 2020 paper "MOCHA: A Dataset for Training and Evaluating Reading Comprehension Metrics".☆16Updated 2 years ago
- Code for our EMNLP 2019 paper titled "Sentence-Level Content Planning and Style Specification for Neural Text Generation"☆17Updated 4 years ago
- Data and code repository of " Multilingual Fairness Evaluation for Hate Speech Detection ". LREC 2020.☆20Updated last year
- Code for our EACL-2021 paper "Generating Syntactically Controlled Paraphrases without Using Annotated Parallel Pairs".☆38Updated 4 months ago
- Official code for LEWIS, from: "LEWIS: Levenshtein Editing for Unsupervised Text Style Transfer", ACL-IJCNLP 2021 Findings by Machel Rei…☆31Updated 2 years ago
- ☆31Updated last year
- Code for NAACL 2022 paper "Reframing Human-AI Collaboration for Generating Free-Text Explanations"☆31Updated last year
- ReCross: Unsupervised Cross-Task Generalization via Retrieval Augmentation☆22Updated 2 years ago
- Official codebase accompanying our ACL 2022 paper "RELiC: Retrieving Evidence for Literary Claims" (https://relic.cs.umass.edu).☆20Updated 2 years ago
- ☆38Updated last year
- ☆28Updated 2 years ago
- ☆25Updated 2 years ago
- PyTorch code for "FactPEGASUS: Factuality-Aware Pre-training and Fine-tuning for Abstractive Summarization" (NAACL 2022)☆38Updated 2 years ago
- Code and data for the EMNLP 2021 paper "Just Say No: Analyzing the Stance of Neural Dialogue Generation in Offensive Contexts". Coming so…☆16Updated last year
- ☆17Updated last year
- Repository for the CODAH dataset☆22Updated 2 years ago
- ☆13Updated last year
- A Benchmark for Robust, Multi-evidence, Multi-answer Question Answering☆16Updated last year
- Framework for controlling demographic biases in NLG (using adversarial prompts)☆19Updated last year
- EMNLP 2021 - Frustratingly Simple Pretraining Alternatives to Masked Language Modeling☆31Updated 2 years ago
- ☆33Updated last year