Share This Author
An Introduction to the Syntax and Content of Cyc
- Cynthia Matuszek, J. Cabral, M. Witbrock, J. DeOliveira
- Computer ScienceAAAI Spring Symposium: Formalizing and Compiling…
- 1 March 2006
Spring Symposium on Formalizing and Compiling Background Knowledge and Its Applications to Knowledge Representation and Question Answering, Stanford, CA, March 2006.
Dilated Recurrent Neural Networks
This paper introduces a simple yet effective RNN connection structure, the DilatedRNN, characterized by multi-resolution dilated recurrent skip connections and introduces a memory capacity measure, the mean recurrent length, which is more suitable for RNNs with long skip connections than existing measures.
Headline Generation Based on Statistical Translation
This paper presents results on experiments using this approach, in which statistical models of the term selection and term ordering are jointly applied to produce summaries in a style learned from a training corpus.
Image Super-Resolution via Dual-State Recurrent Networks
- Wei Han, Shiyu Chang, Ding Liu, Mo Yu, M. Witbrock, Thomas S. Huang
- Computer ScienceIEEE/CVF Conference on Computer Vision and…
- 7 May 2018
This paper explores new structures for SR based on this compact RNN view, leading to a dual-state design, the Dual-State Recurrent Network (DSRN), which performs favorably against state-of-the-art algorithms in terms of both memory consumption and predictive accuracy.
Word Mover’s Embedding: From Word2Vec to Document Embedding
The Word Mover’s Embedding (WME) is proposed, a novel approach to building an unsupervised document (sentence) embedding from pre-trained word embeddings that consistently matches or outperforms state-of-the-art techniques, with significantly higher accuracy on problems of short length.
Improving Natural Language Inference Using External Knowledge in the Science Questions Domain
- Xiaoyang Wang, Pavan Kapanipathi, M. Witbrock
- Computer ScienceAAAI Conference on Artificial Intelligence
- 15 September 2018
A combination of techniques that harness knowledge graphs to improve performance on the NLI problem in the science questions domain and achieves the new state-of-the-art performance over the SciTail science questions dataset.
Discrete Adversarial Attacks and Submodular Optimization with Applications to Text Classification
- Qi Lei, Lingfei Wu, Pin-Yu Chen, A. Dimakis, I. Dhillon, M. Witbrock
- Computer ScienceConference on Machine Learning and Systems
- 1 December 2018
It is proved that this set function is submodular for some popular neural network text classifiers under simplifying assumption, and guarantees a $1-1/e$ approximation factor for attacks that use the greedy algorithm.
Ultra-summarization (poster abstract): a statistical approach to generating highly condensed non-extractive summaries
This paper presents an alternative statistical model of a summarization process, which jointly applies statistical models of the term selection and term ordering process to produce brief coherent summaries in a style learned from a training corpus.
Searching for Common Sense: Populating Cyc™ from the Web
Initial work is presented on a method of using a combination of Cyc and the World Wide Web, accessed via Google, to assist in entering knowledge into Cyc.
Random Warping Series: A Random Features Method for Time-Series Embedding
- Lingfei Wu, I. E. Yen, Jinfeng Yi, Fangli Xu, Qi Lei, M. Witbrock
- Computer ScienceAISTATS
- 31 March 2018
This work studies a family of alignment-aware positive definite (p.d.) kernels, with its feature embedding given by a distribution of Random Warping Series (RWS), which reduces the computational complexity of existing DTW-based techniques from quadratic to linear in terms of both the number and the length of time-series.