• Publications
  • Influence
A Discourse-Aware Attention Model for Abstractive Summarization of Long Documents
This work proposes the first model for abstractive summarization of single, longer-form documents (e.g., research papers), consisting of a new hierarchical encoder that models the discourse structure of a document, and an attentive discourse-aware decoder to generate the summary.
De-identification of patient notes with recurrent neural networks
The first de-identification system based on artificial neural networks (ANNs), which requires no handcrafted features or rules, unlike existing systems, is introduced, which outperforms the state-of-the-art systems.
Sequential Short-Text Classification with Recurrent and Convolutional Neural Networks
This work presents a model based on recurrent neural networks and convolutional neural networks that incorporates the preceding short texts that achieves state-of-the-art results on three different datasets for dialog act prediction.
NeuroNER: an easy-to-use program for named-entity recognition based on neural networks
NeuroNER is an easy-to-use named-entity recognition tool based on ANNs that can annotate entities using a graphical web-based user interface (BRAT) and be used to train an ANN, which in turn predict entities’ locations and categories in new texts.
PubMed 200k RCT: a Dataset for Sequential Sentence Classification in Medical Abstracts
We present PubMed 200k RCT, a new dataset based on PubMed for sequential sentence classification. The dataset consists of approximately 200,000 abstracts of randomized controlled trials, totaling 2.3
Scoring Sentence Singletons and Pairs for Abstractive Summarization
This proposed framework attempts to model human methodology by selecting either a single sentence or a pair of sentences, then compressing or fusing the sentence(s) to produce a summary sentence.
Transfer Learning for Named-Entity Recognition with Neural Networks
It is demonstrated that transferring an ANN model trained on a large labeled dataset to another dataset with a limited number of labels improves upon the state-of-the-art results on two different datasets for patient note de-identification.
Learning Emphasis Selection for Written Text in Visual Media from Crowd-Sourced Label Distributions
A model that employs end-to-end label distribution learning (LDL) on crowd-sourced data and predicts a selection distribution is proposed, capturing the inter-subjectivity (common-sense) in the audience as well as the ambiguity of the input.
Multilingual Twitter Corpus and Baselines for Evaluating Demographic Bias in Hate Speech Recognition
This work assemble and publish a multilingual Twitter corpus for the task of hate speech detection with inferred four author demographic factors: age, country, gender and race/ethnicity, and measures the performance of four popular document classifiers and evaluates the fairness and bias of the baseline classifiers on the author-level demographic attributes.