No abstract

The success of a text simplification system heavily depends on the quality and quantity of complex-simple sentence pairs in the training corpus, which are extracted by aligning sentences between parallel articles. To evaluate and improve sentence alignment quality, we create two manually annotated sentence-aligned datasets from two commonly used text simplification corpora, Newsela and Wikipedia. We propose a novel neural CRF alignment model which not only leverages the sequential nature of sentences in parallel documents but also utilizes a neural sentence pair model to capture semantic similarity. Experiments demonstrate that our proposed approach outperforms all the previous work on monolingual sentence alignment task by more than 5 points in F1. We apply our CRF aligner to construct two new text simplification datasets, NEWSELA-AUTO and WIKI-AUTO, which are much larger and of better quality compared to the existing datasets. A Transformer-based seq2seq model trained on our datasets establishes a new state-of-the-art for text simplification in both automatic and human evaluation. 1

We design a novel speaker diarization system for the first DI-HARD challenge by integrating several important modules of speech denoising, speech activity detection (SAD), i-vector design, and scoring strategy. One main contribution is the proposed long short-term memory (LSTM) based speech denoising model. By fully utilizing the diversified simulated training data and advanced network architecture using progressive multitask learning with dense structure, the denoising model demonstrates the strong generalization capability to realistic noisy environments. The enhanced speech can boost the performance for the subsequent SAD, segmentation and clustering. To the best of our knowledge, this is the first time we show significant improvements of deep learning based single-channel speech enhancement over state-of-the-art diarization systems in highly mismatch conditions. For the design of i-vector extraction, we adopt a residual convolutional neural network trained on large dataset including more than 30,000 people. Finally, by score fusion of different i-vectors based on all these techniques, our systems yield diarization error rates (DERs) of 24.56% and 36.05% on the evaluation sets of Track1 and Track2, which are both in the second place among 14 and 11 participating teams, respectively.

In order to enhance the communication between sensor networks in the Internet of things (IoT), it is indispensable to establish the semantic connections between sensor ontologies in this field. For this purpose, this paper proposes an up-and-coming sensor ontology integrating technique, which uses debate mechanism (DM) to extract the sensor ontology alignment from various alignments determined by different matchers. In particular, we use the correctness factor of each matcher to determine a correspondence’s global factor, and utilize the support strength and disprove strength in the debating process to calculate its local factor. Through comprehensively considering these two factors, the judgment factor of an entity mapping can be obtained, which is further applied in extracting the final sensor ontology alignment. This work makes use of the bibliographic track provided by the Ontology Alignment Evaluation Initiative (OAEI) and five real sensor ontologies in the experiment to assess the performance of our method. The comparing results with the most advanced ontology matching techniques show the robustness and effectiveness of our approach.

BackgroundIn biomedical research, data sharing and information exchange are very important for improving quality of care, accelerating discovery, and promoting the meaningful secondary use of clinical data. A big concern in biomedical data sharing is the protection of patient privacy because inappropriate information leakage can put patient privacy at risk.MethodsIn this study, we deployed a grid logistic regression framework based on Secure Multi-party Computation (SMAC-GLORE). Unlike our previous work in GLORE, SMAC-GLORE protects not only patient-level data, but also all the intermediary information exchanged during the model-learning phase.ResultsThe experimental results demonstrate the feasibility of secure distributed logistic regression across multiple institutions without sharing patient-level data.ConclusionsIn this study, we developed a circuit-based SMAC-GLORE framework. The proposed framework provides a practical solution for secure distributed logistic regression model learning.