Welcome to the INK Lab @ USC

The Intelligence and Knowledge Discovery (INK) Lab at USC is a group of reseachers working on next-generation machine intelligence techniques for label-efficient machine learning, knowledge-guided natural language processing and knowledge reasoning. Our research spans across machine learning, natural language processing and data mining, with a focus on weak-supervision methods for modeling natural-language text data and graph-structured data. We are excited about both developing computational models and building practical systems for real-world applications. Led by Prof. Xiang Ren, the INK lab is also part of USC Machine Learning Center, NLP Community@USC, and ISI Center on Knowledge Graphs.

KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoning, EMNLP-IJCNLP 2019
Looking Beyond Label Noise: Shifted Label Distribution Matters in Distantly Supervised Relation Extraction, EMNLP-IJCNLP 2019
Learning from Explanations with Neural Module Execution Tree, ICLR 2020
Towards Hierarchical Importance Attribution: Explaining Compositional Semantics for Neural Sequence Models, ICLR 2020
Recurrent Event Network for Reasoning over Temporal Knowledge Graphs, ICLR-RLGM 2019

News

  • Apr 2020 - INK lab has 5 papers accepted at ACL 2020.
  • Dec 2019 - INK lab has two papers (spotlight & poster) accepted at ICLR 2020.
  • Nov 2019 - Xiang was invited for a talk at CMU LTI Colloquium in Feb, 2020.
  • Sep 2019- Xiang received a data science research award from Adobe Research to work on neural symbolic learning for recommendation.
  • Aug 2019 - INK lab members have 10 papers accepted at EMNLP 2019. Congratulations!
  • June 2019 - INK lab received a gift award from Snapchat to work on modular neural networks for interpretable NLP.
  • June 2019 - INK lab received a DARPA GAILA grant to work on building AI to mimic children language learning.
  • Mar 2019 - Xiang received a Google Faculty Award for supporting INK lab's research on explainable recommendation.
  • Jan 2019 - INK lab's research on interpretable knowledge reasoning is funded by JP Morgan AI Research Award.
  • Jan 2019 - INK lab received a 2018 Amazon Research Award on neural-symbolic learning for NLP.
  • Jan 2019 - Xiang is serving as area chair (information extraction) of ACL 2019.
  • Dec 2018 - Xiang is organizer of the ICLR 2019 LLD Workshop on learning from limited labeled data.
  • Dec 2018 - Xiang is organizer of the RepL4NLP Workshop at ACL 2019 on representation Learning for NLP. We're soliciting submissions.
  • Nov 2018 - Xiang is organizing the DeepLo Workshop at EMNLP 2019 on deep learning for low-resource NLP.
  • Oct 2018 - Excited to release a new OpenIE system, ReMine. A key distinguishing feature is the ability to learn from entire corpus for measuring cohesiveness of the extraction. (Project | Github)
  • Sep 2018 - Thanks National Science Foundation for supporting INK lab's collaborative research on Modeling the Invention, Dissemination, and Translation of Scientific Concepts.
  • Aug 2018: Three papers accepted to NIPS and EMNLP.
  • Aug 2018: Xiang Ren is co-organizer of AKBC 2019. Please submit your workshop proposals.
  • Aug 2018: Congrats to Yuchen on his two papers accepted to EMNLP!
  • July 2018: Xiang's research monograph on Effort-Light (WeakSupervision) approaches for Information Extraction is published by Morgan & Claypool Publishers.
  • July 2018: Xiang won the 2018 SIGKDD Dissertation Award!
  • May 2018 - Paper on scalable deep generative model for graph accepted to ICML 2018. Github is up.
  • May 2018: A WWW paper won the Best Poster Award Runner-up.
  • Apr 2018: Two papers accepted to KDD and ACL.