INK Lab @ USC

USC-DS-RelationExtraction

Distantly Supervised Relation Extraction

KagNet

Knowledge-Aware Graph Networks for Commonsense Reasoning (EMNLP-IJCNLP 19)

MHGRN

Scalable Multi-Hop Relational Reasoning for Knowledge-Aware Question Answering (EMNLP 2020)

temporal-gcn-lstm

Code for Characterizing and Forecasting User Engagement with In-App Action Graphs: A Case Study of Snapchat

AFET

AFET: Automatic Fine-Grained Entity Typing (EMNLP'16)

CPL

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

NERO

Source Code for paper "NERO: A Neural Rule Grounding Framework for Label-Efficient Relation Extraction", WWW 2020

shifted-label-distribution

Source code for paper "Looking Beyond Label Noise: Shifted Label Distribution Matters in Distantly Supervised Relation Extraction" (EMNLP 2019)

DualRE

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

hierarchical-explanation-neural-sequence-models

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

CALM

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

LEAN-LIFE

Label Efficient Learning From Explanations

XCSR

Code Repo for the ACL21 paper "Common Sense Beyond English: Evaluating and Improving Multilingual LMs for Commonsense Reasoning"

DArtNet

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

NExT

Source Code for paper "Learning from Explanations with Neural Execution Tree", ICLR 2020

expl-refinement

Code for the paper "Refining Language Model with Compositional Explanation" (NeurIPS 2021)

hypter

Zero-shot Learning by Generating Task-specific Adapters

ConNet

IsoBN

IsoBN: Fine-Tuning BERT with Isotropic Batch Normalization

RiddleSense

RiddleSense: Reasoning about Riddle Questions Featuring Linguistic Creativity and Commonsense Knowledge

mrc-explanation

Source Code for "Teaching Machine Comprehension with Compositional Explanations" (Findings of EMNLP 2020)

rockner

CLIF

Code for Findings at EMNLP 2021 paper: "Learn Continually, Generalize Rapidly: Lifelong Knowledge Accumulation for Few-shot Learning"

procedural-extraction

Code for paper Eliciting Knowledge from Experts: Automatic Transcript Parsing for Cognitive Task Analysis, in proceedings of ACL 2019

Upstream-Bias-Mitigation

Code and data for NAACL 2021 paper "On Transferability of Bias Mitigation Effects in Language Model Fine-Tuning"

deceive-KG-models

An implementation of the experiments on KG robustness

bias-mitigation-via-transfer-learning

Source code for Arxiv paper: Efficiently Mitigating Classification Bias via Transfer Learning

get-started-on-dl-experiments

MACROSCORE

MACROSCORE - Scoring Scientific Research

AutoTriggER