Faceted summarization provides briefings of a document from different perspectives. Readers can quickly comprehend the main points of a long document with the help of a structured outline. However, little research has been conducted on this subject, partially due to the lack of large-scale faceted summarization datasets. In this study, we present FacetSum, a faceted summarization benchmark built on Emerald journal articles, covering a diverse range of domains. Different from traditional document-summary pairs, FacetSum provides multiple summaries, each targeted at specific sections of a long document, including the purpose, method, findings, and value. Analyses and empirical results on our dataset reveal the importance of bringing structure into summaries. We believe FacetSum will spur further advances in summarization research and foster the development of NLP systems that can leverage the structured information in both long texts and summaries.
Keyphrase generation aims to summarize long documents with a collection of salient phrases. Deep neural models have demonstrated a remarkable success in this task, capable of predicting keyphrases that are even absent from a document. However, such abstractiveness is acquired at the expense of a substantial amount of annotated data. In this paper, we present a novel method for keyphrase generation, AutoKeyGen, without the supervision of any human annotation. Motivated by the observation that an absent keyphrase in one document can appear in other places, in whole or in part, we first construct a phrase bank by pooling all phrases in a corpus. With this phrase bank, we then draw candidate absent keyphrases for each document through a partial matching process. To rank both types of candidates, we combine their lexical- and semantic-level similarities to the input document. Moreover, we utilize these top-ranked candidates as to train a deep generative model for more absent keyphrases. Extensive experiments demonstrate that AutoKeyGen outperforms all unsupervised baselines and can even beat strong supervised methods in certain cases.
Evaluation of intelligent assistants in large-scale and online settings remains an open challenge. User behavior-based online evaluation metrics have demonstrated great effectiveness for monitoring large-scale web search and recommender systems. Therefore, we consider predicting user engagement status as the very first and critical step to online evaluation for intelligent assistants. In this work, we first proposed a novel framework for classifying user engagement status into four categories -- fulfillment, continuation, reformulation and abandonment. We then demonstrated how to design simple but indicative metrics based on the framework to quantify user engagement levels. We also aim for automating user engagement prediction with machine learning methods. We compare various models and features for predicting engagement status using four real-world datasets. We conducted detailed analyses on features and failure cases to discuss the performance of current models as well as challenges.
Recent years have seen a flourishing of neural keyphrase generation works, including the release of several large-scale datasets and a host of new models to tackle them. Model performance on keyphrase generation tasks has increased significantly with evolving deep learning research. However, there lacks a comprehensive comparison among models, and an investigation on related factors (e.g., architectural choice, decoding strategy) that may affect a keyphrase generation system's performance. In this empirical study, we aim to fill this gap by providing extensive experimental results and analyzing the most crucial factors impacting the performance of keyphrase generation models. We hope this study can help clarify some of the uncertainties surrounding the keyphrase generation task and facilitate future research on this topic.
Multivariate time series modeling and prediction problems are abundant in many machine learning application domains. Accurate interpretation of such prediction outcomes from a machine learning model that explicitly captures temporal correlations can be a major benefit to the domain experts. In this context, temporal attention has been successfully applied to isolate the important time steps for the input time series. However, in multivariate time series problems, spatial interpretation is also critical to understand the contributions of different variables on the model outputs. We propose a novel deep learning architecture, called spatiotemporal attention mechanism (STAM) for simultaneous learning of the most important time steps and variables. STAM is a causal (i.e., only depends on past inputs and does not use future inputs) and scalable (i.e., scales well with an increase in the number of variables) approach that is comparable to the state-of-the-art models in terms of computational tractability. We demonstrate the performance of our models both on a popular public dataset as well as on a domain-specific dataset. When compared with the baseline models, the results show that STAM maintains state-of-the-art prediction accuracy while offering the benefit of accurate spatiotemporal interpretability. We validate the learned attention weights from a domain knowledge perspective for the real-world datasets.
Recently, concatenating multiple keyphrases as a target sequence has been proposed as a new learning paradigm for keyphrase generation. Existing studies concatenate target keyphrases in different orders but no study has examined the effects of ordering on models' behavior. In this paper, we propose several orderings for concatenation and inspect the important factors for training a successful keyphrase generation model. By running comprehensive comparisons, we observe one preferable ordering and summarize a number of empirical findings and challenges, which can shed light on future research on this line of work.
We propose multivariate nonstationary Gaussian processes for jointly modeling multiple clinical variables, where the key parameters, length-scales, standard deviations and the correlations between the observed output, are all time dependent. We perform posterior inference via Hamiltonian Monte Carlo (HMC). We also provide methods for obtaining computationally efficient gradient-based maximum a posteriori (MAP) estimates. We validate our model on synthetic data as well as on electronic health records (EHR) data from Kaiser Permanente (KP). We show that the proposed model provides better predictive performance over a stationary model as well as uncovers interesting latent correlation processes across vitals which are potentially predictive of patient risk.
Hidden Markov jump processes are an attractive approach for modeling clinical disease progression data because they are explainable and capable of handling both irregularly sampled and noisy data. Most applications in this context consider time-homogeneous models due to their relative computational simplicity. However, the time homogeneous assumption is too strong to accurately model the natural history of many diseases. Moreover, the population at risk is not homogeneous either, since disease exposure and susceptibility can vary considerably. In this paper, we propose a piece-wise stationary transition matrix to explain the heterogeneity in time. We propose a hierarchical structure for the heterogeneity in population, where prior information is considered to deal with unbalanced data. Moreover, an efficient, scalable EM algorithm is proposed for inference. We demonstrate the feasibility and superiority of our model on a cervical cancer screening dataset from the Cancer Registry of Norway. Experiments show that our model outperforms state-of-the-art recurrent neural network models in terms of prediction accuracy and significantly outperforms a standard hidden Markov jump process in generating Kaplan-Meier estimators.
Gaussian processes are a flexible Bayesian nonparametric modelling approach that has been widely applied to learning tasks such as facial expression recognition, image reconstruction, and human pose estimation. To address the issues of poor scaling from exact inference methods, approximation methods based on sparse Gaussian processes (SGP) and variational inference (VI) are necessary for the inference on large datasets. However, one of the problems involved in SGP, especially in latent variable models, is that the distribution of the inducing inputs may fail to capture the distribution of training inputs, which may lead to inefficient inference and poor model prediction. Hence, we propose a regularization approach for sparse Gaussian processes. We also extend this regularization approach into latent sparse Gaussian processes in a unified view, considering the balance of the distribution of inducing inputs and embedding inputs. Furthermore, we justify that performing VI on a sparse latent Gaussian process with this regularization term is equivalent to performing VI on a related empirical Bayes model with a prior on the inducing inputs. Also stochastic variational inference is available for our regularization approach. Finally, the feasibility of our proposed regularization method is demonstrated on three real-world datasets.