Search Results for author: Feng Nan

Found 22 papers, 8 papers with code

SWING: Balancing Coverage and Faithfulness for Dialogue Summarization

1 code implementation25 Jan 2023 Kung-Hsiang Huang, Siffi Singh, Xiaofei Ma, Wei Xiao, Feng Nan, Nicholas Dingwall, William Yang Wang, Kathleen McKeown

Missing information is a common issue of dialogue summarization where some information in the reference summaries is not covered in the generated summaries.

Natural Language Inference

Evaluating the Tradeoff Between Abstractiveness and Factuality in Abstractive Summarization

no code implementations5 Aug 2021 Markus Dreyer, Mengwen Liu, Feng Nan, Sandeep Atluri, Sujith Ravi

Neural models for abstractive summarization tend to generate output that is fluent and well-formed but lacks semantic faithfulness, or factuality, with respect to the input documents.

Abstractive Text Summarization

Towards Clinical Encounter Summarization: Learning to Compose Discharge Summaries from Prior Notes

no code implementations27 Apr 2021 Han-Chin Shing, Chaitanya Shivade, Nima Pourdamghani, Feng Nan, Philip Resnik, Douglas Oard, Parminder Bhatia

The records of a clinical encounter can be extensive and complex, thus placing a premium on tools that can extract and summarize relevant information.

Hallucination Informativeness +2

Who did They Respond to? Conversation Structure Modeling using Masked Hierarchical Transformer

1 code implementation25 Nov 2019 Henghui Zhu, Feng Nan, Zhiguo Wang, Ramesh Nallapati, Bing Xiang

In this work, we define the problem of conversation structure modeling as identifying the parent utterance(s) to which each utterance in the conversation responds to.


no code implementations ICLR Workshop LLD 2019 Ian Gemp, Ramesh Nallapati, Ran Ding, Feng Nan, Bing Xiang

We extend NTMs to the weakly semi-supervised setting by using informative priors in the training objective.

Topic Models

Sequential Dynamic Decision Making with Deep Neural Nets on a Test-Time Budget

no code implementations31 May 2017 Henghui Zhu, Feng Nan, Ioannis Paschalidis, Venkatesh Saligrama

Deep neural network (DNN) based approaches hold significant potential for reinforcement learning (RL) and have already shown remarkable gains over state-of-art methods in a number of applications.

Decision Making Feature Engineering +2

Comments on the proof of adaptive submodular function minimization

no code implementations10 May 2017 Feng Nan, Venkatesh Saligrama

We point out an issue with Theorem 5 appearing in "Group-based active query selection for rapid diagnosis in time-critical situations".

Active Learning Stochastic Optimization

Dynamic Model Selection for Prediction Under a Budget

no code implementations25 Apr 2017 Feng Nan, Venkatesh Saligrama

Our objective is to minimize overall average cost without sacrificing accuracy.

Model Selection Test

Feature-Budgeted Random Forest

no code implementations20 Feb 2015 Feng Nan, Joseph Wang, Venkatesh Saligrama

We seek decision rules for prediction-time cost reduction, where complete data is available for training, but during prediction-time, each feature can only be acquired for an additional cost.

Max-Cost Discrete Function Evaluation Problem under a Budget

no code implementations12 Jan 2015 Feng Nan, Joseph Wang, Venkatesh Saligrama

We develop a broad class of \emph{admissible} impurity functions that admit monomials, classes of polynomials, and hinge-loss functions that allow for flexible impurity design with provably optimal approximation bounds.

General Classification

Cannot find the paper you are looking for? You can Submit a new open access paper.