This repository is the implementation of the ProTACT architecture, introduced in the paper "Prompt- and Trait Relation-aware Cross-prompt Essay Trait Scoring" (ACL Findings 2023).

This repository is for the paper UAlberta at SemEval-2023 Task 1: Context Augmentation and Translation for Multilingual Visual Word Sense Disambiguation. In Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023). Association for Computational Linguistics.

[ACL 2023] The code for our ACL'23 paper Cold-Start Data Selection for Few-shot Language Model Fine-tuning: A Prompt-Based Uncertainty Propagation Approach

WSPAlign: Word Alignment Pre-training via Large-Scale Weakly Supervised Span Prediction, to appear at ACL 2023 main conference.

ACL23 Demo SciLit: A Platform for Joint Scientific Literature Discovery, Summarization and Citation Generation

Revisiting Cross-Lingual Summarization: A Corpus-based Study and A New Benchmark with Improved Annotation

Deep Active Learning for Morphophonological Processing (Mirbostani et al., ACL 2023)

Inference library and evaluation script for WSPAlign (https://github.com/qiyuw/WSPAlign)

[ACL 2023] SPEECH: Structured Prediction with Energy-Based Event-Centric Hyperspheres

[ACL 2023] Solving Math Word Problems via Cooperative Reasoning induced Language Models

PyTorch code for paper, 'Split-NER: Named Entity Recognition via Two Question-Answering-based Classifications', ACL'23

Repo for paper "IDOL: Indicator-oriented Logic Pre-training for Logical Reasoning" accepted to the Findings of ACL 2023

Official implementation of the ACL Findings 2023 paper: Multimedia Generative Script Learning for Task Planning

[ACL2023-Findings] Shuo Wen Jie Zi is a new learning paradigm that enhances the semantics understanding ability of the Chinese PLMs with dictionary knowledge and structure of Chinese characters

Official repository for "Learn over Past, Evolve for Future: Forecasting Temporal Trends for Fake News Detection", ACL 2023

Official code repo for ACL 2023 CRFIE.

[ACL'23 Findings] This is the code repo for our ACL'23 Findings paper "ReGen: Zero-Shot Text Classification via Training Data Generation with Progressive Dense Retrieval".

RAN: Recurrent Attention Networks for Long-text Modeling | Findings of ACL23

[ACL 2023] Learning Multi-step Reasoning by Solving Arithmetic Tasks. https://arxiv.org/abs/2306.01707

[ACL 2023] Contextual Distortion Reveals Constituency: Mask Language Models are Implicit Parsers.