Learn More
Knowledge graph completion aims to perform link prediction between entities. In this paper, we consider the approach of knowledge graph embeddings. Recently, models such as TransE and TransH build entity and relation embeddings by regarding a relation as translation from head entity to tail entity. We note that these models simply put both entities and(More)
Little is known about the biochemical environment in phagosomes harboring an infectious agent. To assess the state of this organelle we captured the transcriptional responses of Mycobacterium tuberculosis (MTB) in macrophages from wild-type and nitric oxide (NO) synthase 2-deficient mice before and after immunologic activation. The intraphagosomal(More)
Attention mechanism advanced state-of-the-art neural machine translation (NMT) by jointly learning to align and translate. However, attention-based NMT ignores past alignment information, which often leads to over-translation and under-translation. In response to this problem, we maintain a coverage vector to keep track of the attention history. The(More)
OBJECTIVE Brain-computer interface (BCI) provides a mean of communication for the patients that are severely disabled by neuromuscular diseases. The performance of the classical P300 speller, however, declines noticeably in the gaze fixation condition. The speller paradigm presented in this paper aims to release the gaze dependency at the cost of an extra(More)
We propose minimum risk training for end-to-end neural machine translation. Unlike conventional maximum likelihood estimation, minimum risk training is capable of optimizing model parameters directly with respect to evaluation metrics. Experiments on Chinese-English and English-French translation show that our approach achieves significant improvements over(More)
Anterior approach was extensively used in surgical treatment of multilevel cervical spondylotic myelopathy. Following anterior decompression, many different reconstructive techniques (multilevel ACDF, hybrid construct and long corpectomy) all had satisfied outcomes. However, there are few studies focusing on the comparison of these three reconstructed(More)
Most word embedding models typically represent each word using a single vector, which makes these models indiscriminative for ubiquitous homonymy and poly-semy. In order to enhance discriminativeness, we employ latent topic models to assign topics for each word in the text corpus, and learn topical word embeddings (TWE) based on both words and their topics.(More)
Without discourse connectives, classifying implicit discourse relations is a challenging task and a bottleneck for building a practical discourse parser. Previous research usually makes use of one kind of discourse framework such as PDTB or RST to improve the classification performance on discourse relations. Actually, under different discourse annotation(More)
Mitogen-activated protein kinase (MAPK) cascades are signalling modules that transduce extracellular signalling to a range of cellular responses. Plant MAPK cascades have been implicated in development and stress response. In this study, we isolated a novel group C MAPKK gene, ZmMKK4, from maize. Northern blotting analysis revealed that the ZmMKK4(More)