[EMNLP 2022] An Open Toolkit for Knowledge Graph Extraction and Construction

A Unified Semi-Supervised Learning Codebase (NeurIPS'22)

CrossNER: Evaluating Cross-Domain Named Entity Recognition (AAAI-2021)

Convert your PDFs and EPUBs into audiobooks effortlessly. Features intelligent text extraction, customizable text-to-speech settings, and efficient processing for low-resource systems.

Coach: A Coarse-to-Fine Approach for Cross-domain Slot Filling (ACL-2020)

TriggerNER: Learning with Entity Triggers as Explanations for Named Entity Recognition (ACL 2020)

Code and datasets for the ACL 2021 paper "OntoED: Low-resource Event Detection with Ontology Embedding"

Attention-Informed Mixed-Language Training for Zero-shot Cross-lingual Task-oriented Dialogue Systems (AAAI-2020)

Zero-shot Cross-lingual Task-Oriented Dialogue Systems (EMNLP 2019)

Code + data for the EMNLP'20 publication "Transfer Learning and Distant Supervision for Multilingual Transformer Models: A Study on African Languages"

Code of ICKG2020 best student paper: A Robust and Domain-Adaptive Approach for Low-Resource Named Entity Recognition

Original PyTorch implementation for AAAI 2021 Paper "Meta-Transfer Learning for Low-Resrouce Abstractive Summarization."

In search of effective and efficient Pipeline for Distillating Knowledge in Convolutional Neural Networks

Exploring Self-Supervised Learning for Low-Resource Medical Image Analysis, ICIP 2023

[SIGIR 2023] Schema-aware Reference as Prompt Improves Data-Efficient Knowledge Graph Construction

Official code for "Too Brittle To Touch: Comparing the Stability of Quantization and Distillation Towards Developing Lightweight Low-Resource MT Models" to appear in WMT 2022.

Exploring ways to reduce Neural Machine Translation Memory and Computation through binarized networks

[EMNLP 2022 Findings] Towards Realistic Low-resource Relation Extraction: A Benchmark with Empirical Baseline Study

EMNLP-2020: Cross-lingual Spoken Language Understanding with Regularized Representation Alignment

This repository is an open-source colleciton of various low-resource machine translation experiments.