Search

Background Infection with the novel severe acute respiratory syndrome coronavirus 2 has been associated with a hypercoagulable state. Emerging data from China and Europe have consistently shown an increased incidence of venous thromboembolism (VTE). We aimed to identify the VTE incidence and early predictors of VTE at our high-volume tertiary care center. Methods We performed a retrospective cohort study of 147 patients who had been admitted to Temple University Hospital with coronavirus disease 2019 (COVID-19) from April 1, 2020 to April 27, 2020. We first identified the VTE (pulmonary embolism [PE] and deep vein thrombosis [DVT]) incidence in our cohort. The VTE and no-VTE groups were compared by univariable analysis for demographics, comorbidities, laboratory data, and treatment outcomes. Subsequently, multivariable logistic regression analysis was performed to identify the early predictors of VTE. Results The 147 patients (20.9% of all admissions) admitted to a designated COVID-19 unit at Temple University Hospital with a high clinical suspicion of acute VTE had undergone testing for VTE using computed tomography pulmonary angiography and/or extremity venous duplex ultrasonography. The overall incidence of VTE was 17% (25 of 147). Of the 25 patients, 16 had had acute PE, 14 had had acute DVT, and 5 had had both PE and DVT. The need for invasive mechanical ventilation (adjusted odds ratio, 3.19; 95% confidence interval, 1.07-9.55) and the admission D-dimer level ≥1500 ng/mL (adjusted odds ratio, 3.55; 95% confidence interval, 1.29-9.78) were independent markers associated with VTE. The all-cause mortality in the VTE group was greater than that in the non-VTE group (48% vs 22%; P = .007). Conclusions Our study represents one of the earliest reported from the United States on the incidence rate of VTE in patients with COVID-19. Patients with a high clinical suspicion and the identified risk factors (invasive mechanical ventilation, admission D-dimer level ≥1500 ng/mL) should be considered for early VTE testing. We did not screen all patients admitted for VTE; therefore, the true incidence of VTE could have been underestimated. Our findings require confirmation in future prospective studies.

Virtual assistants such as Google Assistant, Amazon Alexa, and Apple Siri enable users to interact with a large number of services and APIs on the web using natural language. In this work, we investigate two methods for Natural Language Generation (NLG) using a single domain-independent model across a large number of APIs. First, we propose a schema-guided approach which conditions the generation on a schema describing the API in natural language. Our second method investigates the use of a small number of templates, growing linearly in number of slots, to convey the semantics of the API. To generate utterances for an arbitrary slot combination, a few simple templates are first concatenated to give a semantically correct, but possibly incoherent and ungrammatical utterance. A pre-trained language model is subsequently employed to rewrite it into coherent, natural sounding text. Through automatic metrics and human evaluation, we show that our method improves over strong baselines, is robust to out-of-domain inputs and shows improved sample efficiency.

Understanding and conversing about dynamic scenes is one of the key capabilities of AI agents that navigate the environment and convey useful information to humans. Video question answering is a specific scenario of such AI-human interaction where an agent generates a natural language response to a question regarding the video of a dynamic scene. Incorporating features from multiple modalities, which often provide supplementary information, is one of the challenging aspects of video question answering. Furthermore, a question often concerns only a small segment of the video, hence encoding the entire video sequence using a recurrent neural network is not computationally efficient. Our proposed question-guided video representation module efficiently generates the token-level video summary guided by each word in the question. The learned representations are then fused with the question to generate the answer. Through empirical evaluation on the Audio Visual Scene-aware Dialog (AVSD) dataset, our proposed models in single-turn and multi-turn question answering achieve state-of-the-art performance on several automatic natural language generation evaluation metrics., Accepted at SIGDIAL 2019

This paper presents a novel approach for multi-task learning of language understanding (LU) and dialogue state tracking (DST) in task-oriented dialogue systems. Multi-task training enables the sharing of the neural network layers responsible for encoding the user utterance for both LU and DST and improves performance while reducing the number of network parameters. In our proposed framework, DST operates on a set of candidate values for each slot that has been mentioned so far. These candidate sets are generated using LU slot annotations for the current user utterance, dialogue acts corresponding to the preceding system utterance and the dialogue state estimated for the previous turn, enabling DST to handle slots with a large or unbounded set of possible values and deal with slot values not seen during training. Furthermore, to bridge the gap between training and inference, we investigate the use of scheduled sampling on LU output for the current user utterance as well as the DST output for the preceding turn., Published at SIGdial 2018; 9 pages

In task-oriented dialogue systems, spoken language understanding, or SLU, refers to the task of parsing natural language user utterances into semantic frames. Making use of context from prior dialogue history holds the key to more effective SLU. State of the art approaches to SLU use memory networks to encode context by processing multiple utterances from the dialogue at each turn, resulting in significant trade-offs between accuracy and computational efficiency. On the other hand, downstream components like the dialogue state tracker (DST) already keep track of the dialogue state, which can serve as a summary of the dialogue history. In this work, we propose an efficient approach to encoding context from prior utterances for SLU. More specifically, our architecture includes a separate recurrent neural network (RNN) based encoding module that accumulates dialogue context to guide the frame parsing sub-tasks and can be shared between SLU and DST. In our experiments, we demonstrate the effectiveness of our approach on dialogues from two domains., Submitted to INTERSPEECH 2018

Dialogue state tracking (DST) is a key component of task-oriented dialogue systems. DST estimates the user's goal at each user turn given the interaction until then. State of the art approaches for state tracking rely on deep learning methods, and represent dialogue state as a distribution over all possible slot values for each slot present in the ontology. Such a representation is not scalable when the set of possible values are unbounded (e.g., date, time or location) or dynamic (e.g., movies or usernames). Furthermore, training of such models requires labeled data, where each user turn is annotated with the dialogue state, which makes building models for new domains challenging. In this paper, we present a scalable multi-domain deep learning based approach for DST. We introduce a novel framework for state tracking which is independent of the slot value set, and represent the dialogue state as a distribution over a set of values of interest (candidate set) derived from the dialogue history or knowledge. Restricting these candidate sets to be bounded in size addresses the problem of slot-scalability. Furthermore, by leveraging the slot-independent architecture and transfer learning, we show that our proposed approach facilitates quick adaptation to new domains., Published at ASRU-17. New version has updated results in Tables 1, 2 and 3 corresponding to the datasets released on github.com/google-research-datasets/simulated-dialogue