• Publications
  • Influence
An Introduction to the Syntax and Content of Cyc
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
TLDR
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. Expand
Headline Generation Based on Statistical Translation
TLDR
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. Expand
Image Super-Resolution via Dual-State Recurrent Networks
TLDR
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. Expand
Searching for Common Sense: Populating Cyc™ from the Web
TLDR
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. Expand
Ultra-summarization (poster abstract): a statistical approach to generating highly condensed non-extractive summaries
TLDR
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. Expand
Word Mover’s Embedding: From Word2Vec to Document Embedding
TLDR
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. Expand
Discrete Adversarial Attacks and Submodular Optimization with Applications to Text Classification
TLDR
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. Expand
Improving Natural Language Inference Using External Knowledge in the Science Questions Domain
TLDR
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. Expand
Informedia: news-on-demand multimedia information acquisition and retrieval
TLDR
The News-on-Demand application created within the InformediaTM Digital Video Library project is described and how speech recognition is used for transcript creation from video, time alignment of closed-captioned transcripts, a speech query interface, and audio paragraph segmentation is discussed. Expand
...
1
2
3
4
5
...