[NAACL'21 & ACL'21] SapBERT: Self-alignment pretraining for BERT & XL-BEL: Cross-Lingual Biomedical Entity Linking.

source code and pre-trained/fine-tuned checkpoint for NAACL 2021 paper LightningDOT

Repository containing code for the NAACL 2021 paper (Incorporating External Knowledge to Enhance Tabular Reasoning)

Code for "Highly Efficient Knowledge Graph Embedding Learning with Closed-Form Orthogonal Procrustes Analysis" (NAACL 2021)

Code for "Cross-Lingual Word Embedding Refinement by ℓ1 Norm Optimisation" (NAACL 2021)

[NAACL 2021] Reading and Acting while Blindfolded: The Need for Semantics in Text Game Agents

Official resource of the paper "Knowledge Enhanced Masked Language Model for Stance Detection", NAACL 2021

Discourse Probing of Pretrained Language Models. In Proceedings of NAACL 2021.

Codebase, data and models for the Headline Grouping paper at NAACL2021

An implementation of SSI

Evaluation Dataset for "Bootstrapping Large-Scale Fine-Grained Contextual Advertising Classifier from Wikipedia" (TextGraphs-15 Workshop@NAACL 2021)

Development repository for implementations of Models/Experiments in "Hierarchical Transformer for Task Oriented Dialog Systems" - NAACL 2021 (Long Paper)

The PyTorch codebase for the NAACL 2021 paper - "tWT–WT: A Dataset to Assert the Role of Target Entities for Detecting Stance of Tweets"

Official Repo for Implementations of Models/Experiments in "Hierarchical Transformer for Task Oriented Dialog Systems" - NAACL 2021 (Long Paper)

Code for the runners up entry on the English subtask on the Shared-Task-On-Fighting the COVID-19 Infodemic, NLP4IF workshop, NAACL'21.

OptimSeed - Seed Word Selection for Weakly-Supervised Text Classification [NAACL SRW 2021]