Our efforts in the 2013 NLI shared task focused on the potential benefits of external corpora. We show that including training data from multiple corpora is highly effective at robust, cross-corpus NLI (i.e. open-training task 1), particularly when some form of domain adaptation is also applied. This method can also be used to boost performance even when training data from the same corpus is av...

Word-level language detection is necessary for analyzing code-switched text, where multiple languages could be mixed within a sentence. Existing models are restricted to code-switching between two specific languages and fail in real-world scenarios as text input rarely has a priori information on the languages used. We present a novel unsupervised word-level language detection technique for cod...

Although the performance of person Re-Identification (ReID) has been significantly boosted, many challenging issues in real scenarios have not been fully investigated, e.g., the complex scenes and lighting variations, viewpoint and pose changes, and the large number of identities in a camera network. To facilitate the research towards conquering those issues, this paper contributes a new datase...

Language identification is the task of identifying the language a given document is written in. This paper describes a detailed examination of what models perform best under different conditions, based on experiments across three separate datasets and a range of tokenisation strategies. We demonstrate that the task becomes increasingly difficult as we increase the number of languages, reduce th...

We present automatic language recognition results using high-order hidden Markov models (HMM) and the recently developed ORder rEDucing (ORED) and Fast Incremental Training (FIT) HMM algorithms. We demonstrate the efficiency and accuracy of pseudo-phoneme context and duration modelling mixed-order HMMs as well as fixed order HMMs over conventional approaches. For a two language problem, we show...

In this paper, deep neural networks are investigated for language identification in Indian languages. Deep neural networks (DNN) have been recently proposed for this task. However many architectural choices and training aspects that have been made while building such systems have not been studied carefully. We perform several experiments on a dataset consisting of 12 Indian languages with a tot...

Individual pitch control (IPC) is gaining increasing acceptance as a method for mitigation of periodic disturbances in wind turbines. This paper aims at formulating a repetitive control (RC) methodology capable of adapting online to changing turbine dynamics. This is achieved by performing system identification in a reduced-dimensional space using basis functions and using the identified parame...

AIM To evaluate the prevalence of alcohol consumption among university students during late adolescence and young adulthood and to identify the associated factors. MATERIAL AND METHODS Cohort study among university students in Spain (n = 1382). Heavy Episodic Drinking (HED) and Risky Consumption (RC) were measured with the Alcohol Use Disorders Identification Test (AUDIT) at ages 18, 20, 22, ...

The Albayzin 2012 Language Recognition Evaluation (LRE), carried out from June to October 2012, was the third effort made by the Spanish/Portuguese community for benchmarking language recognition technology. As in previous Albayzin 2008 and 2010 evaluations, the task consisted on deciding whether or not a target language was spoken in a test utterance. The primary condition involved 6 target la...

The acceptability of four transformer top-oil thermal models are examined vis-à-vis training with measured data. Acceptability is defined as having the qualities of adequacy, consistency, and accuracy. Metrics are used to characterize the likely deficiencies of these models. It is shown that: the classical IEEE/ANSI standard model is unacceptable for model identification purposes. The linear to...