Locally Distributed Activation Vectors for Guided Feature Attribution

no code implementations • COLING 2022 • Housam K. B. Bashier, Mi-Young Kim, Randy Goebel

Explaining the predictions of a deep neural network (DNN) is a challenging problem.

text-classification Text Classification

DISK-CSV: Distilling Interpretable Semantic Knowledge with a Class Semantic Vector

no code implementations • EACL 2021 • Housam Khalifa Bashier, Mi-Young Kim, Randy Goebel

Neural networks (NN) applied to natural language processing (NLP) are becoming deeper and more complex, making them increasingly difficult to understand and interpret.

text-classification Text Classification

RANCC: Rationalizing Neural Networks via Concept Clustering

1 code implementation • COLING 2020 • Housam Khalifa Bashier, Mi-Young Kim, Randy Goebel

We propose a new self-explainable model for Natural Language Processing (NLP) text classification tasks.

Clustering Feature Importance +2

On Generality and Knowledge Transferability in Cross-Domain Duplicate Question Detection for Heterogeneous Community Question Answering

no code implementations • 15 Nov 2018 • Mohomed Shazan Mohomed Jabbar, Luke Kumar, Hamman Samuel, Mi-Young Kim, Sankalp Prabhakar, Randy Goebel, Osmar Zaïane

Duplicate question detection is an ongoing challenge in community question answering because semantically equivalent questions can have significantly different words and structures.

Community Question Answering Domain Adaptation +3

A Lexicalized Tree Kernel for Open Information Extraction

no code implementations • IJCNLP 2015 • Ying Xu, Christoph Ringlstetter, Mi-Young Kim, Grzegorz Kondrak, R. Goebel, y, Yusuke Miyao

Entity Extraction using GAN Open Information Extraction +2

Open Information Extraction with Tree Kernels

no code implementations • HLT 2013 • Ying Xu, Mi-Young Kim, Kevin Quinn, Randy Goebel, Denilson Barbosa

Open Information Extraction Relation +2