Research on the Uyghur morphological segmentation model with an attention mechanism

Abudouwaili, Gulinigeer; Abiderexiti, Kahaerjing; Shen, Yunfei; Wumaier, Aishan

doi:10.1080/09540091.2022.2134843

Cited by 3 publications

(3 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We introduce an attention mechanism for learning the relative importance of various words to increase the influence of crucial sentiment words on the overall sentiment expression. The use of an attention machine enhances the performance of the model by allowing for more critical information ( Abudouwaili et al, 2022 ). In this experiment, weights for emphasizing keywords are assigned using a feed-forward neural attention strategy.…”

Section: Methodsmentioning

confidence: 99%

A sentiment analysis approach for travel-related Chinese online review content

Li,

Zhao

et al. 2023

PeerJ Computer Science

View full text Add to dashboard Cite

Using technology for sentiment analysis in the travel industry can extract valuable insights from customer reviews. It can assist businesses in gaining a deeper understanding of their consumers’ emotional tendencies and enhance their services’ caliber. However, travel-related online reviews are rife with colloquialisms, sparse feature dimensions, metaphors, and sarcasm. As a result, traditional semantic representations of word vectors are inaccurate, and single neural network models do not take into account multiple associative features. To address the above issues, we introduce a dual-channel algorithm that integrates convolutional neural networks (CNN) and bi-directional long and short-term memory (BiLSTM) with an attention mechanism (DC-CBLA). First, the model utilizes the pre-trained BERT, a transformer-based model, to extract a dynamic vector representation for each word that corresponds to the current contextual representation. This process enhances the accuracy of the vector semantic representation. Then, BiLSTM is used to capture the global contextual sequence features of the travel text, while CNN is used to capture the richer local semantic information. A hybrid feature network combining CNN and BiLSTM can improve the model’s representation ability. Additionally, the BiLSTM output is feature-weighted using the attention mechanism to enhance the learning of its fundamental features and lessen the influence of noise features on the outcomes. Finally, the Softmax function is used to classify the dual-channel fused features. We conducted an experimental evaluation of two data sets: tourist attractions and tourist hotels. The accuracy of the DC-CBLA model is 95.23% and 89.46%, and that of the F1-score is 97.05% and 93.86%, respectively. The experimental results demonstrate that our proposed DC-CBLA model outperforms other baseline models.

show abstract

Section: Methodsmentioning

confidence: 99%

A sentiment analysis approach for travel-related Chinese online review content

Li,

Zhao

et al. 2023

PeerJ Computer Science

View full text Add to dashboard Cite

show abstract

“…In summary, although supervised models for Uyghur and Kazakh lexical analysis have achieved certain research progress [6,[40][41][42], these models' evaluation metrics are based on character-level metrics. The performance and differences of these models have not been explored using morpheme-level evaluation metrics.…”

Section: Related Workmentioning

confidence: 99%

“…In agglutinative languages, the first morpheme is the stem without prefixes. Furthermore, when the morphology of Uyghur and Kazakh is concatenated, phonological harmony may cause characters at the junction to occur: phenomena such as deletion, addition, and weakening [6]. Figure 1 shows three different phonological changes.…”

Section: Introductionmentioning

confidence: 99%

A Benchmark for Morphological Segmentation in Uyghur and Kazakh

Abudouwaili,

Ruzmamat,

Abiderexiti

et al. 2024

Applied Sciences

Self Cite

View full text Add to dashboard Cite

Morphological segmentation and stemming are foundational tasks in natural language processing. They have become effective ways to alleviate data sparsity in agglutinative languages because of the nature of agglutinative language word formation. Uyghur and Kazakh, as typical agglutinative languages, have made significant progress in morphological segmentation and stemming in recent years. However, the evaluation metrics used in previous work are character-level based, which may not comprehensively reflect the performance of models in morphological segmentation or stemming. Moreover, existing methods avoid manual feature extraction, but the model’s ability to learn features is inadequate in complex scenarios, and the correlation between different features has not been considered. Consequently, these models lack representation in complex contexts, affecting their effective generalization in practical scenarios. To address these issues, this paper redefines the morphological-level evaluation metrics: F1-score and accuracy (ACC) for morphological segmentation and stemming tasks. In addition, two models are proposed for morpheme segmentation and stem extraction tasks: supervised model and unsupervised model. The supervised model learns character and contextual features simultaneously, then feature embeddings are input into a Transformer encoder to study the correlation between character and context embeddings. The last layer of the model uses a CRF or softmax layer to determine morphological boundaries. In unsupervised learning, an encoder–decoder structure introduces n-gram correlation assumptions and masked attention mechanisms, enhancing the correlation between characters within n-grams and reducing the impact of characters outside n-grams on boundaries. Finally, comprehensive comparative analyses of the performance of different models are conducted from various points of view. Experimental results demonstrate that: (1) The proposed evaluation method effectively reflects the differences in morphological segmentation and stemming for Uyghur and Kazakh; (2) Learning different features and their correlation can enhance the model’s generalization ability in complex contexts. The proposed models achieve state-of-the-art performance on Uyghur and Kazakh datasets.

show abstract

Syllable‐Level Morphological Segmentation of Kannada and Tulu Words

Hegde,

Shashirekha

2024

Automatic Speech Recognition and Translation for Low Resource Languages

View full text Add to dashboard Cite

Research on the Uyghur morphological segmentation model with an attention mechanism

Cited by 3 publications

References 22 publications

A sentiment analysis approach for travel-related Chinese online review content

A sentiment analysis approach for travel-related Chinese online review content

A Benchmark for Morphological Segmentation in Uyghur and Kazakh

Syllable‐Level Morphological Segmentation of Kannada and Tulu Words

Contact Info

Product

Resources

About