In this paper, we describe the DeepNNNER entry to The 2nd Workshop on Noisy User-generated Text (WNUT) Shared Task #2: Named Entity Recognition in Twitter. Our shared task submission adopts the bidirectional LSTM-CNN model of Chiu and Nichols (2016), as it has been shown to perform well on both newswire and Web texts. It uses word embeddings trained on large-scale Web text collections together ...

The nature of predictive relations between early language and later cognitive function is a fundamental question in research on human cognition. In a longitudinal study assessing speed of language processing in infancy, Fernald, Perfors and Marchman (2006) found that reaction time at 25 months was strongly related to lexical and grammatical development over the second year. In this follow-up st...

The Maximum a posteriori hypothesis is treated as the decoded truth in speech recognition. However, since the word recognition accuracy is not 100%, it is desirable to have an independent con dence measure on how good the maximum a posteriori hypothesis is relative to the spoken truth for some applications. E orts are in progress [1, 2, 3] to develop such con dence measures with the intent of a...

An approach to online handwriting word recognition using segmentation-based techniques is presented in this paper. This approach is referred to as lexicon-driven approach because an optimal segmentation is generated for each string in the lexicon. Word recognition problem is transformed into matching optimization problems between the dictionary entry and the handwritten word image. The segmenta...

One of the most useful applications of Confidence Measures (CMs) in Automatic Speech Recognition systems is early detection of incorrect recognition hypotheses. A purely acoustic basis for such a CM is particularly important when tracking errors resulting from Out of Vocabulary speech, background noise or keyword substitution. A commonly taken approach is to compute scores on subword units of t...

A parallel distributed processing model of visual word recognition and pronunciation is described. The model consists of sets of orthographic and phonological units and an interlevel of hidden units. Weights on connections between units were modified during a training phase using the back-propagation learning algorithm. The model simulates many aspects of human performance, including (a) differ...

The work presented in this paper deals with the construction of a large-vocabulary semantic network to assist computerised speech or text recognition. The semantic network is systematically constructed with semantic information about nouns and verbs from the Longman Dictionary of Contemporary English by the application of pattern matching rules. It is represented in the form of a directed graph...

This paper demonstrates end-to-end neural network architectures for Vietnamese named entity recognition. Our best model is the combination of bidirectional Long ShortTerm Memory (Bi-LSTM), Convolutional Neural Network (CNN), Conditional Random Field (CRF), using pre-trained word embeddings as input, which achieves an F1 score of 88.59% on a standard test set. Our system is able to achieve a com...

We have investigated if subjects are aware of what natural tongue movements look like, by showing them animations based on either measurements or rule-based synthesis. The issue is of interest since a previous audiovisual speech perception study recently showed that the word recognition rate in sentences with degraded audio was significantly better with real tongue movements than with synthesiz...

in this paper we address the issue of recognizing farsi handwritten words. two types of gradient features are extracted from a sliding vertical stripe which sweeps across a word image. these are directional and intensity gradient features. the feature vector extracted from each stripe is then coded using the self organizing map (som). in this method each word is modeled using the discrete hidde...