Peter J. Liu

Learning to Write Notes in Electronic Health Records

2018 · arXiv (Cornell University)

Clinicians spend a significant amount of time inputting free-form textual notes into Electronic Health Records (EHR) systems. Much of this documentation work is seen as a burden, reducing time spent with patients and contributing to …

Online and Linear-Time Attention by Enforcing Monotonic Alignments

2017 · arXiv (Cornell University)

Recurrent neural network models with an attention mechanism have proven to be extremely effective on a wide variety of sequence-to-sequence problems. However, the fact that soft attention mechanisms perform a pass over the entire input …

Get To The Point: Summarization with Pointer-Generator Networks

2017 · arXiv (Cornell University)

Neural sequence-to-sequence models have provided a viable new approach for abstractive text summarization (meaning they are not restricted to simply selecting and rearranging passages from the original text). However, these models have two shortcomings: they …

Beyond Word Importance: Contextual Decomposition to Extract Interactions from LSTMs

2018 · arXiv (Cornell University)

The driving force behind the recent success of LSTMs has been their ability to learn complex and non-linear relationships. Consequently, our inability to describe these relationships has led to LSTMs being characterized as black boxes. …

Assessing The Factual Accuracy of Generated Text

2019

We propose a model-based metric to estimate the factual accuracy of generated text that is complementary to typical scoring schemes like ROUGE (Recall-Oriented Understudy for Gisting Evaluation) and BLEU (Bilingual Evaluation Understudy). We introduce and …

MeanSum: A Neural Model for Unsupervised Multi-Document Abstractive Summarization

2019

Abstractive summarization has been studied using neural sequence transduction methods with datasets of large, paired document-summary examples. However, such datasets are rare and the models trained from them do not generalize to other domains. Recently, …

Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer

2019 · arXiv (Cornell University)

Transfer learning, where a model is first pre-trained on a data-rich task before being fine-tuned on a downstream task, has emerged as a powerful technique in natural language processing (NLP). The effectiveness of transfer learning …

PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization

2019 · arXiv (Cornell University)

Recent work pre-training Transformers with self-supervised objectives on large text corpora has shown great success when fine-tuned on downstream NLP tasks including text summarization. However, pre-training objectives tailored for abstractive text summarization have not been …