Text normalization using memory augmented neural networks

Pramanik, Subhojeet; Hussain, Aman

doi:10.1016/j.specom.2019.02.003

Cited by 24 publications

(25 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For the innovation of the modeling process, a matching network based on memory and attention is proposed, which makes it possible to learn quickly. For the innovation of the training process, this work is based on a principle of traditional ML, that is training and testing are to be carried out under the same conditions [35]- [36]. It is proposed that the network should constantly look at the insufficient samples of each type during training, which will be consistent with the testing process.…”

Section: Matching Networkmentioning

confidence: 99%

Learning Models for Semantic Classification of Insufficient Plantar Pressure Images

Wu¹,

Wu²,

Dey³

et al. 2020

IJIMAI

View full text Add to dashboard Cite

Establishing a reliable and stable model to predict a target by using insufficient labeled samples is feasible and effective, particularly, for a sensor-generated data-set. This paper has been inspired with insufficient data-set learning algorithms, such as metric-based, prototype networks and meta-learning, and therefore we propose an insufficient data-set transfer model learning method. Firstly, two basic models for transfer learning are introduced. A classification system and calculation criteria are then subsequently introduced. Secondly, a dataset of plantar pressure for comfort shoe design is acquired and preprocessed through foot scan system; and by using a pre-trained convolution neural network employing AlexNet and convolution neural network (CNN)based transfer modeling, the classification accuracy of the plantar pressure images is over 93.5%. Finally, the proposed method has been compared to the current classifiers VGG, ResNet, AlexNet and pre-trained CNN. Also, our work is compared with known-scaling and shifting (SS) and unknown-plain slot (PS) partition methods on the public test databases: SUN, CUB, AWA1, AWA2, and aPY with indices of precision (tr, ts, H) and time (training and evaluation). The proposed method for the plantar pressure classification task shows high performance in most indices when comparing with other methods. The transfer learning-based method can be applied to other insufficient data-sets of sensor imaging fields.

show abstract

Section: Matching Networkmentioning

confidence: 99%

Learning Models for Semantic Classification of Insufficient Plantar Pressure Images

Wu¹,

Wu²,

Dey³

et al. 2020

IJIMAI

View full text Add to dashboard Cite

show abstract

“…Next generation of text normalisation systems used the combination of rules and language model (Sproat et al, 2001;Graliński et al, 2006;Brocki et al, 2012). Latest research focused on neural networks Jaitly, 2016, 2017;Zare and Rohatgi, 2017;Pramanik and Hussain, 2018;Zhang et al, 2019). Especially recurrent neural networks (RNN) have promising results, but also tend to fail in some unexpected and unacceptable cases, such as translating large numbers with one digit mistake or treating cm as kilometres (Zhang et al, 2019).…”

Section: Related Workmentioning

confidence: 99%

Numbers Normalisation in the Inflected Languages: a Case Study of Polish

Poświata¹,

Perełkiewicz²

2019

Proceedings of the 7th Workshop on Balto-Slavic Natural Language Processing

View full text Add to dashboard Cite

Text normalisation in Text-to-Speech systems is a process of converting written expressions to their spoken forms. This task is complicated because in many cases the normalised form depends on the context. Furthermore, when we analysed languages like Croatian, Lithuanian, Polish, Russian or Slovak there is additional difficulty related to their inflected nature. In this paper we want to show how to deal with this problem for one of these languages: Polish, without having a large dedicated data set and using solutions prepared for other NLP tasks. We limited our study to only numbers expressions, which are the most common nonstandard words to normalise. The proposed solution is a combination of morphological tagger and transducer supported by a dictionary of numbers in their spoken forms. The data set used for evaluation is based on the part of 1million word subset of the National Corpus of Polish. The accuracy of the described approach is presented with a comparison to a simple baseline and two commercial systems: Google Cloud Text-to-Speech and Amazon Polly.

show abstract

Section: Related Workmentioning

confidence: 99%

Proceedings of the 7th Workshop on Balto-Slavic Natural Language Processing

2019

View full text Add to dashboard Cite

The paper presents an unsupervised method for quickly extending a Ukrainian lexicon by generating paradigms and morphological feature structures for new proper names and neologisms, which are not covered by existing static morphological resources. This approach addresses a practical problem of modelling paradigms for entities created by the dynamic processes in the lexicon: this problem is especially serious for highly-inflected languages in domains with specialised or quickly changing lexicon. The method uses an unannotated Ukrainian corpus and a small fixed set of inflection tables, which can be found in traditional grammar textbooks. The advantage of the proposed approach is that updating the morphological lexicon does not require training or linguistic annotation, allowing fast knowledge-light extension of an existing static lexicon to improve morphological coverage on a specific corpus. The method is implemented in an open-source package on a GitHub repository. It can be applied to other low-resourced inflectional languages which have internet corpora and linguistic descriptions of their inflection system, following the example of inflection tables for Ukrainian. Evaluation results show consistent improvements in coverage for Ukrainian corpora of different corpus types.

show abstract

Text normalization using memory augmented neural networks

Cited by 24 publications

References 19 publications

Learning Models for Semantic Classification of Insufficient Plantar Pressure Images

Learning Models for Semantic Classification of Insufficient Plantar Pressure Images

Numbers Normalisation in the Inflected Languages: a Case Study of Polish

Proceedings of the 7th Workshop on Balto-Slavic Natural Language Processing

Contact Info

Product

Resources

About