• Publications
  • Influence
Ranking Sentences for Extractive Summarization with Reinforcement Learning
TLDR
This paper conceptualize extractive summarization as a sentence ranking task and proposes a novel training algorithm which globally optimizes the ROUGE evaluation metric through a reinforcement learning objective. Expand
Creating Training Corpora for NLG Micro-Planners
TLDR
This paper presents a novel framework for semi-automatically creating linguistically challenging NLG corpora from existing Knowledge Bases, applying it to DBpedia data and shows that while (Wen et al., 2016)'s dataset is more than twice larger than the authors', it is less diverse both in terms of input and in Terms of text. Expand
Leveraging Pre-trained Checkpoints for Sequence Generation Tasks
TLDR
A Transformer-based sequence-to-sequence model that is compatible with publicly available pre-trained BERT, GPT-2, and RoBERTa checkpoints is developed and an extensive empirical study on the utility of initializing the model, both encoder and decoder, with these checkpoints is conducted. Expand
Split and Rephrase
TLDR
A new sentence simplification task (Split-and-Rephrase) where the aim is to split a complex sentence into a meaning preserving sequence of shorter sentences, which could be used as a preprocessing step which facilitates and improves the performance of parsers, semantic role labellers and machine translation systems. Expand
Hybrid Simplification using Deep Semantics and Machine Translation
TLDR
A hybrid approach to sentence simplification which combines deep semantics and monolingual machine translation to derive simple sentences from complex ones that yields significantly simpler output that is both grammatical and meaning preserving. Expand
Variation in external beam treatment plan quality: An inter-institutional study of planners and planning systems.
TLDR
Wide variation in radiation treatment plan quality could be attributed to a general "planner skill" category that would lend itself to processes of continual improvement where best practices could be derived and disseminated to improve the mean quality and minimize the variation in any population of treatment planners. Expand
Document Modeling with External Attention for Sentence Extraction
TLDR
A framework composed of a hierarchical document encoder and an attention-based extractor with attention over external information is developed to use external information to improve document modeling for problems that can be framed as sentence extraction. Expand
Leukocytosis as a harbinger and surrogate marker of Clostridium difficile infection in hospitalized patients with diarrhea
TLDR
Infection with C. difficile should be considered in the differential diagnosis of sudden onset of leukocytosis in hospitalized patients previously or concurrently treated with antibiotics, and may obviate the need for expensive and time-consuming tests for other etiologies. Expand
Privacy-preserving Neural Representations of Text
TLDR
This article measures the privacy of a hidden representation by the ability of an attacker to predict accurately specific private information from it and characterize the tradeoff between the privacy and the utility of neural representations. Expand
Sticking to the Facts: Confident Decoding for Faithful Data-to-Text Generation
TLDR
This work proposes a novel confidence oriented decoder that assigns a confidence score to each target position in training using a variational Bayes objective, and can be leveraged at inference time using a calibration technique to promote more faithful generation. Expand
...
1
2
3
4
5
...