Learn More
Cloze-style queries are representative problems in reading comprehension. Over the past few months, we have seen much progress that utilizing neural network approach to solve Cloze-style questions. In this paper, we present a novel model called attention-over-attention reader for the Cloze-style reading comprehension task. Our model aims to place another(More)
Reasoning and inference are central to human and artificial intelligence. Modeling inference in human language is notoriously challenging but is fundamental to natural language understanding and many applications. With the availability of large annotated data, neural network models have recently advanced the field significantly. In this paper, we present a(More)
This paper presents two new ideas for text dependent mispronunciation detection. Firstly, mispronunciation detection is formulated as a classification problem to integrate various predictive features. A Support Vector Machine (SVM) is used as the classifier and the loglikelihood ratios between all the acoustic models and the model corresponding to the given(More)
(1) Handcrafted features [BAPM15] 78.2 (2) LSTM [BGR+16] 80.6 (3) GRU [VKFU15] 81.4 (4) Tree CNN [MML+16] 82.1 (5) SPINN-PI [BGR+16] 83.2 (6) BiLSTM intra-Att [LSLW16] 84.2 (7) NSE [MY16a] 84.6 (8) Att-LSTM [RGH+15] 83.5 (9) mLSTM [WJ16] 86.1 (10) LSTMN [CDL16] 86.3 (11) Decomposable Att [PTDU16] 86.3 (12) Intra-sent Att+(11) [PTDU16] 86.8 (13)(More)
Distributed representation learned with neural networks has recently shown to be effective in modeling natural languages at fine granularities such as words, phrases, and even sentences. Whether and how such an approach can be extended to help model larger spans of text, e.g., documents, is intriguing, and further investigation would still be desirable.(More)
In this paper, we propose a general framework to incorporate semantic knowledge into the popular data-driven learning process of word embeddings to improve the quality of them. Under this framework, we represent semantic knowledge as many ordinal ranking inequalities and formulate the learning of semantic word embeddings (SWE) as a constrained optimization(More)
A key problem in spoken language identification (LID) is to design effective representations which are specific to language information. For example, in recent years, representations based on both phonotactic and acoustic features have proven their effectiveness for LID. Although advances in machine learning have led to significant improvements, LID(More)
Perfluorinated acids (PFAs) such as perfluorooctanesulfonate (PFOS) and perfluorooctanoate (PFOA) are global environmental contaminants. The physicochemical properties of PFAs are unique in that they have high water solubilities despite the low reactivity of carbon-fluorine bond, which also imparts high stability in the environment. Because of the high(More)
Perfluorinated compounds (PFCs) have been widely used in industrial and consumer products and frequently detected in many environmental media. Potential reproductive effects of perfluorooctanesulfonate (PFOS), perfluorooctanoic acid (PFOA) and perfluorononanoic acid (PFNA) have been reported in mice, rats and water birds. PFOS and PFOA were also confirmed(More)
Thirteen samples of seawater were collected from Yellow Sea and East China Sea near Qingdao, Lianyungang, and Xiamen, China. They were analyzed for halogenated organophosphorus flame retardants (OPFRs). The compounds selected for detection were Tris(2-chloroethyl) phosphate (TCEP), Tris(2-chloroisopropyl) phosphate (TCPP), Tris (1,3-dichloro-2-propyl)(More)