INK Lab @ USC

Source code for ICLR 2021 paper : Pre-training Text-to-Text Transformers for Concept-Centric Common Sense

INK-USC

Collaborative Policy Learning for Open Knowledge Graph Reasoning (EMNLP 2019)

INK-USC

Code for paper "CrossFit :weight_lifting:: A Few-shot Learning Challenge for Cross-task Generalization in NLP" (https://arxiv.org/abs/2104.08835)

INK-USC

Temporal Attribute Prediction via Joint Modeling of Multi-Relational Structure Evolution

INK-USC

Discretized Integrated Gradients for Explaining Language Models (EMNLP 2021)

INK-USC

Source code for paper: "Learning Dual Retrieval Module for Semi-supervised Relation Extraction"

INK-USC

Good Examples Make A Faster Learner: Simple Demonstration-based Learning for Low-resource NER (ACL 2022)

INK-USC

Learning Contextualized Knowledge Structures for Commonsense Reasoning

INK-USC

Source code for "Towards Hierarchical Importance Attribution: Explaining Compositional Semantics for Neural Sequence Models", ICLR 2020.

INK-USC

Label Efficient Learning From Explanations

INK-USC