A Comprehensive Survey of Deep Learning Techniques Natural Language Processing

Bharadiya, Jasmin Praful

doi:10.47672/ejt.1473

Cited by 29 publications

(8 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years, representative natural language processing techniques [16,17], such as ChatGPT [18], have developed rapidly due to their demonstrated superior ability to process massive amounts of data and learn complex semantic relationships. Advances in such models have led to significant achievements [19] in sentence comprehension and generation.…”

Section: Motivation and Significancementioning

confidence: 99%

See 1 more Smart Citation

Advancements in Word Sense Disambiguation: A Poly-Encoder Bert Model Perspective

Xia,

Cai,

Huang

et al. 2024

Preprint

View full text Add to dashboard Cite

In the application domain, accurate word sense identification is crucial for improving the performance of machine translation, information retrieval and end-to-end communication tasks. However, word polysemy is a major obstacle to accurate semantic identification. Therefore, word semantic disambiguation has always been one of the key challenges in natural language processing and has attracted the attention of a large number of researchers. This research proposes an innovative disambiguation algorithm based on the large-scale Bert model and the Polly encoder framework, and introduces WordNet as a benchmark for word semantic. By exploiting the ability of the pre-trained model to extract and learn semantic information, and using a specially designed forward propagation algorithm and loss function to fine-tune the large-scale Bert model, the model has high Accuracy and robustness. In this research, several experiments were conducted on the Semcor 3.0 semantic dataset. The experimental results show that the model proposed in this research shows excellent performance on the Semcor test set, with an Accuracy of 86.1% and an F1 score of 0.847, which is a significant improvement over the traditional model.

show abstract

Section: Motivation and Significancementioning

confidence: 99%

“…For ease of later computation, we construct a new dimension in Gloss new , resulting in a new matrix dimension as Equation (17).…”

Section: Attention Dot Productmentioning

confidence: 99%

Advancements in Word Sense Disambiguation: A Poly-Encoder Bert Model Perspective

Xia,

Cai,

Huang

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…The agent explores the environment, takes actions, and receives feedback, allowing it to learn and improve its decision-making processes over time. Reinforcement learning is often used in scenarios where an agent must make sequential decisions, such as in game playing or autonomous systems [13] .…”

Section: Reinforcement Learning: Reinforcement Learningmentioning

confidence: 99%

“…ML algorithms can identify patterns and relationships in data, enabling organizations to forecast demand, anticipate market trends, predict customer behavior, and make datadriven decisions based on these insights. [13,14] .…”

Section: Predictive Analytics: ML Enables Predictive Analyticsmentioning

confidence: 99%

The role of machine learning in transforming business intelligence

Bharadiya¹

2023

Int. J. Comput. Artif. Intell.

View full text Add to dashboard Cite

Machine Learning (ML) has emerged as a transformative force in the field of Business Intelligence (BI), revolutionizing the way organizations extract insights from vast amounts of data. This abstract explores the role of ML in transforming BI and its impact on decision-making processes. ML enables efficient data collection and preparation through integration, cleaning, and feature engineering. Predictive analytics powered by ML facilitates forecasting, customer segmentation, demand prediction, and churn analysis. ML's anomaly detection capabilities identify outliers, fraud, and operational anomalies. Natural Language Processing (NLP) empowers sentiment analysis, text mining, and chatbots for enhanced customer support. Recommendation systems provide personalized suggestions using ML techniques like collaborative and content-based filtering. Once the data is prepared, it is subjected to analysis using various techniques and algorithms. ML-driven data visualization and reporting enable interactive dashboards and real-time monitoring. The benefits of ML in BI include improved accuracy, faster decision-making, enhanced customer experience, cost reduction, and competitive advantage. However, challenges such as data quality, ethics, interpretability, and skill gaps need to be addressed. Future trends include advanced ML techniques, augmented analytics, edge computing, and ethical AI practices. ML's role in transforming BI is pivotal, urging businesses to embrace ML to unlock its full potential and gain a competitive edge.

show abstract

“…Essentially, it completes the unequal-length sequence mapping based on text and transfer to corresponding speech (Donahue et al, 2006 ). It acts like a bridge during human-computer interaction, enabling machines to communicate like real humans with understandable languages (Bharadiya, 2023 ). TTS technology has gone through a long history, which evolved from a rule-based synthesis (Oliviera et al, 1992 ) to a concatenative generation model (Lee and Cox, 2002 ), and then upgraded to a statistical parametric structure (Zen, 2015 ).…”

Section: Introductionmentioning

confidence: 99%

SR-TTS: a rhyme-based end-to-end speech synthesis system

Yao,

Liang,

Feng

et al. 2024

Front. Neurorobot.

View full text Add to dashboard Cite

Deep learning has significantly advanced text-to-speech (TTS) systems. These neural network-based systems have enhanced speech synthesis quality and are increasingly vital in applications like human-computer interaction. However, conventional TTS models still face challenges, as the synthesized speeches often lack naturalness and expressiveness. Additionally, the slow inference speed, reflecting low efficiency, contributes to the reduced voice quality. This paper introduces SynthRhythm-TTS (SR-TTS), an optimized Transformer-based structure designed to enhance synthesized speech. SR-TTS not only improves phonological quality and naturalness but also accelerates the speech generation process, thereby increasing inference efficiency. SR-TTS contains an encoder, a rhythm coordinator, and a decoder. In particular, a pre-duration predictor within the cadence coordinator and a self-attention-based feature predictor work together to enhance the naturalness and articulatory accuracy of speech. In addition, the introduction of causal convolution enhances the consistency of the time series. The cross-linguistic capability of SR-TTS is validated by training it on both English and Chinese corpora. Human evaluation shows that SR-TTS outperforms existing techniques in terms of speech quality and naturalness of expression. This technology is particularly suitable for applications that require high-quality natural speech, such as intelligent assistants, speech synthesized podcasts, and human-computer interaction.

show abstract

A Comprehensive Survey of Deep Learning Techniques Natural Language Processing

Cited by 29 publications

References 0 publications

Advancements in Word Sense Disambiguation: A Poly-Encoder Bert Model Perspective

Advancements in Word Sense Disambiguation: A Poly-Encoder Bert Model Perspective

The role of machine learning in transforming business intelligence

SR-TTS: a rhyme-based end-to-end speech synthesis system

Contact Info

Product

Resources

About