• Publications
  • Influence
Multi-Task Identification of Entities, Relations, and Coreference for Scientific Knowledge Graph Construction
The multi-task setup reduces cascading errors between tasks and leverages cross-sentence relations through coreference links and supports construction of a scientific knowledge graph, which is used to analyze information in scientific literature. Expand
From HMM's to segment models: a unified view of stochastic modeling for speech recognition
A general stochastic model is described that encompasses most of the models proposed in the literature for speech recognition, pointing out similarities in terms of correlation and parameter tying assumptions, and drawing analogies between segment models and HMMs. Expand
Automatic labeling of prosodic patterns
A general algorithm for labeling prosodic patterns in speech is described, which provides a mechanism for mapping sequences of observations to prosodic labels using decision trees and a Markov sequence model. Expand
Reading Level Assessment Using Support Vector Machines and Statistical Language Models
This paper uses support vector machines to combine features from traditional reading level measures, statistical language models, and other language processing tools to produce a better method of assessing reading level. Expand
A general framework for information extraction using dynamic span graphs
This framework significantly outperforms state-of-the-art on multiple information extraction tasks across multiple datasets reflecting different domains and is good at detecting nested span entities, with significant F1 score improvement on the ACE dataset. Expand
Enriching speech recognition with automatic detection of sentence boundaries and disfluencies
A metadata detection system that combines information from different types of textual knowledge sources with information from a prosodic classifier is described, and it is found that discriminative models generally outperform generative models. Expand
Aligning Sentences from Standard Wikipedia to Simple Wikipedia
This work improves monolingual sentence alignment for text simplification, specifically for text in standard and simple Wikipedia by using a greedy search over the document and a word-level semantic similarity score based on Wiktionary that also accounts for structural similarity through syntactic dependencies. Expand
Normalization of non-standard words
A taxonomy of NSWs was developed on the basis of four rather distinct text types, and several general techniques including n-gram language models, decision trees and weighted finite-state transducers were investigated, demonstrating that a systematic treatment can lead to better results than have been obtained by the ad hoc treatments that have typically been used in the past. Expand
Deep Reinforcement Learning with a Natural Language Action Space
This paper introduces a novel architecture for reinforcement learning with deep neural networks designed to handle state and action spaces characterized by natural language, as found in text-basedExpand