Automatic Speech Summarization Without Linguistic Knowledge Based on Frame Selection Through Acoustic Features

2021 ◽  
pp. 463-470
Author(s):  
Ghazaala Yasmin ◽  
Shuvodeep Debnath ◽  
Asit K. Das
Keyword(s):  
Linguistic Knowledge ◽  
Acoustic Features ◽  
Frame Selection ◽  
Knowledge Based ◽  
Speech Summarization

scholarly journals An Optimized Lesk-Based Algorithm for Word Sense Disambiguation

2016 ◽  
Vol 8 (1) ◽  
pp. 165-172
Author(s):  
Eniafe Festus Ayetiran ◽  
Kehinde Agbele
Keyword(s):  
Computational Complexity ◽  
Word Sense Disambiguation ◽  
Superior Performance ◽  
Linguistic Knowledge ◽  
Word Sense ◽  
General Domain ◽  
Domain Specific ◽  
Knowledge Based ◽  
Sense Disambiguation ◽  
Almost All

Abstract Computational complexity is a characteristic of almost all Lesk-based algorithms for word sense disambiguation (WSD). In this paper, we address this issue by developing a simple and optimized variant of the algorithm using topic composition in documents based on the theory underlying topic models. The knowledge resource adopted is the English WordNet enriched with linguistic knowledge from Wikipedia and Semcor corpus. Besides the algorithm’s eficiency, we also evaluate its efectiveness using two datasets; a general domain dataset and domain-specific dataset. The algorithm achieves a superior performance on the general domain dataset and superior performance for knowledge-based techniques on the domain-specific dataset.

scholarly journals A risk-aware fuzzy linguistic knowledge-based recommender system for hedge funds

2019 ◽  
Vol 162 ◽  
pp. 916-923
Author(s):  
Álvaro Tejeda-Lorente ◽  
Juan Bernabé-Moreno ◽  
Julio Herce-Zelaya ◽  
Carlos Porcel ◽  
Enrique Herrera-Viedma
Keyword(s):  
Recommender System ◽  
Hedge Funds ◽  
Linguistic Knowledge ◽  
Knowledge Based ◽  
Fuzzy Linguistic

Constructing Structural Equation Model Rule-Based Fuzzy System with Genetic Algorithm

Fuzzy Systems ◽  
2017 ◽  
pp. 132-152
Author(s):  
EnDer Su ◽  
Thomas W. Knowles ◽  
Yu-Gin Fen
Keyword(s):  
Genetic Algorithm ◽  
Risk Factor ◽  
Structural Equation Model ◽  
Latent Variables ◽  
Structural Equation ◽  
Equation Model ◽  
Linguistic Knowledge ◽  
United States Dollar ◽  
Knowledge Based ◽  
Economic Indices

The present study uses the structural equation model (SEM) to analyze the correlations between various economic indices pertaining to latent variables, such as the New Taiwan Dollar (NTD) value, the United States Dollar (USD) value, and USD index. In addition, a risk factor of volatility of currency returns is considered to develop a risk-controllable fuzzy inference system. The rational and linguistic knowledge-based fuzzy rules are established based on the SEM model and then optimized using the genetic algorithm. The empirical results reveal that the fuzzy logic trading system using the SEM indeed outperforms the buy-and-hold strategy. Moreover, when considering the risk factor of currency volatility, the performance appears significantly better. Remarkably, the trading strategy is apparently affected when the USD value or the volatility of currency returns shifts into either a higher or lower state.

scholarly journals Linguistic knowledge-based vocabularies for Neural Machine Translation

2020 ◽  
pp. 1-22
Author(s):  
Noe Casas ◽  
Marta R. Costa-jussà ◽  
José A. R. Fonollosa ◽  
Juan A. Alonso ◽  
Ramón Fanlo
Keyword(s):  
Neural Networks ◽  
Machine Translation ◽  
Word Formation ◽  
Linguistic Knowledge ◽  
Learning Approaches ◽  
Neural Machine Translation ◽  
Knowledge Based ◽  
Word Level ◽  
The Neural Network ◽  
Cross Lingual

Abstract Neural Networks applied to Machine Translation need a finite vocabulary to express textual information as a sequence of discrete tokens. The currently dominant subword vocabularies exploit statistically-discovered common parts of words to achieve the flexibility of character-based vocabularies without delegating the whole learning of word formation to the neural network. However, they trade this for the inability to apply word-level token associations, which limits their use in semantically-rich areas and prevents some transfer learning approaches e.g. cross-lingual pretrained embeddings, and reduces their interpretability. In this work, we propose new hybrid linguistically-grounded vocabulary definition strategies that keep both the advantages of subword vocabularies and the word-level associations, enabling neural networks to profit from the derived benefits. We test the proposed approaches in both morphologically rich and poor languages, showing that, for the former, the quality in the translation of out-of-domain texts is improved with respect to a strong subword baseline.

scholarly journals Dual-Source Transformer Model for Neural Machine Translation with Linguistic Knowledge

2020 ◽  
Author(s):  
Yirong Pan ◽  
Xiao Li ◽  
Yating Yang ◽  
Rui Dong
Keyword(s):  
Machine Translation ◽  
Linguistic Knowledge ◽  
Linguistic Features ◽  
Neural Machine Translation ◽  
Popular Method ◽  
Translation Quality ◽  
Knowledge Based ◽  
Syntactic Information ◽  
Dual Source ◽  
Transformer Model

Incorporating source-side linguistic knowledge into the neural machine translation (NMT) model has recently achieved impressive performance on machine translation tasks. One popular method is to generalize the word embedding layer of the encoder to encode each word and its linguistic features. The other method is to change the architecture of the encoder to encode syntactic information. However, the former cannot explicitly balance the contribution from the word and its linguistic features. The latter cannot flexibly utilize various types of linguistic information. Focusing on the above issues, this paper proposes a novel NMT approach that models the words in parallel to the linguistic knowledge by using two separate encoders. Compared with the single encoder based NMT model, the proposed approach additionally employs the knowledge-based encoder to specially encode linguistic features. Moreover, it shares parameters across encoders to enhance the model representation ability of the source-side language. Extensive experiments show that the approach achieves significant improvements of up to 2.4 and 1.1 BLEU points on Turkish→English and English→Turkish machine translation tasks, respectively, which indicates that it is capable of better utilizing the external linguistic knowledge and effective improving the machine translation quality.

scholarly journals Cortical encoding of acoustic and linguistic rhythms in spoken narratives

eLife ◽  
2020 ◽  
Vol 9 ◽  
Author(s):  
Cheng Luo ◽  
Nai Ding
Keyword(s):  
Cortical Activity ◽  
Linguistic Knowledge ◽  
Neural Responses ◽  
Acoustic Features ◽  
Neural Encoding ◽  
Linguistic Information ◽  
Passive Listening ◽  
Word Level ◽  
Speech Envelope ◽  
Linguistic Units

Speech contains rich acoustic and linguistic information. Using highly controlled speech materials, previous studies have demonstrated that cortical activity is synchronous to the rhythms of perceived linguistic units, for example, words and phrases, on top of basic acoustic features, for example, the speech envelope. When listening to natural speech, it remains unclear, however, how cortical activity jointly encodes acoustic and linguistic information. Here we investigate the neural encoding of words using electroencephalography and observe neural activity synchronous to multi-syllabic words when participants naturally listen to narratives. An amplitude modulation (AM) cue for word rhythm enhances the word-level response, but the effect is only observed during passive listening. Furthermore, words and the AM cue are encoded by spatially separable neural responses that are differentially modulated by attention. These results suggest that bottom-up acoustic cues and top-down linguistic knowledge separately contribute to cortical encoding of linguistic units in spoken narratives.

Sign in / Sign up

Export Citation Format

Share Document