1 |
Comparison of Text Mining Models for Food and Dietary Constituent Named-Entity Recognition
|
|
|
|
In: Machine Learning and Knowledge Extraction; Volume 4; Issue 1; Pages: 254-275 (2022)
|
|
BASE
|
|
Show details
|
|
2 |
SENTIMENT ANALYSIS WITH NEURAL NETWORK ; СЕНТИМЕНТ АНАЛІЗ ЗАСОБАМИ НЕЙРОННОЇ МЕРЕЖІ
|
|
|
|
In: Математичне моделювання; № 1(44) (2021); 30-37 ; 2519-8114 ; 2519-8106 (2021)
|
|
Abstract:
Natural language processing is a direction of mathematical linguistics and the field of artificial intelligence, devoted to the study of computers analyze, process and synthesize human speech. The task of input text information sentiment analysis that is the part of natural language processing is set out in the article. Sentiment analysis or opinion mining is aimed at extracting, recognizing and classifying the subjective authors attitude to a certain topic into positive, negative or neutral categories or identifying emotions: anger, fear, joy, sadness, surprise, trust, etc. The main source of sentiment analysis is data from social networks, message applications, video blogs, results of online surveys collected automatically via Internet. The subject of sentiment analysis was social network users, the object of analysis was their publications and text comments. There are a lot of methods of sentiment analysis, but the most popular is neural networks using. The algorithm for solving the problem of text information sentiment analysis is described in the article. It consists of the following steps, namely: input text information corpus forming, input data preprocessing, neural network architecture development, learning, validation and testing of the created neural network. The bidirectional long short term memory neural network (BiLSTM) was developed for sentiment analysis solving. The feasibility of using the additional neural network layer with conditionally random fields (CRF) is justified. CRF is a discriminatory probability model that takes into account the context of classified object to predict sequences. The architecture of the developed neural network is presented. Software for implementing the BiLSTM-CRF model for sentiment analysis was developed as a user application in Python using NLTK and PyTorch libraries. To conduct the neural network training the corpus of text messages from social networks was used. Results of the developed neural network training, validation and testing are presented. To evaluate the quality of sentiments recognition precision, recall and balanced F1-score were used. The best recognition rate was received for positive sentiment with values: precision=61,92%, recall=69,21%, F1=65,36%. Possible ways to improve the sentiments recognition results can be: increasing the size of training, validating and testing dataset; searching for the best neural network hyper parameters values; pre-processing optimization. ; У статті здійснено постановку завдання аналізу тональності вхідної текстової інформації, яке відноситься до розділу прикладної лінгвістики та обробки природньої мови. Розроблено двонаправлену нейронну мережу з довгою короткотривалою пам’яттю для розв’язання завдання сентимент аналізу. Обґрунтовано доцільність застосування додаткового шару для нейронної мережі з умовно випадковими полями. Для проведення навчання нейронної мережі застосовано корпус текстових повідомлень з соціальної мережі. Описано результати навчання, валідації та тестування розробленої нейронної мережі. Для оцінювання якості розпізнавання сентиментів застосовано метрики повноти (precision), точності (recall) та збалансованої міри F1. Найкращі значення розпізнавання на тестовому наборі даних були отримані для позитивного сентименту і склали precision = 61,92 %, recall = 69,21 %, F1 = 65,36 %.
|
|
Keyword:
bidirectional long short term neural network; conditional random fields; sentimental analysis; двонаправлена нейронна мережа з довгою короткотривалою пам’яттю; сентимент аналіз; умовно випадкові поля
|
|
URL: http://matmod.dstu.dp.ua/article/view/235906
|
|
BASE
|
|
Hide details
|
|
3 |
Can we Generate Emotional Pronunciations for Expressive Speech Synthesis?
|
|
|
|
In: ISSN: 1949-3045 ; IEEE Transactions on Affective Computing ; https://hal.archives-ouvertes.fr/hal-01802463 ; IEEE Transactions on Affective Computing, Institute of Electrical and Electronics Engineers, 2020, 11 (4), pp.684-695. ⟨10.1109/TAFFC.2018.2828429⟩ (2020)
|
|
BASE
|
|
Show details
|
|
4 |
Morphosyntactic disambiguation and segmentation for historical Polish with graph-based conditional random fields
|
|
|
|
In: 21st International Conference on Text, Speech and Dialogue (TSD 2018) ; https://hal.archives-ouvertes.fr/hal-01835573 ; 21st International Conference on Text, Speech and Dialogue (TSD 2018), Sep 2018, Brno, Czech Republic (2018)
|
|
BASE
|
|
Show details
|
|
5 |
Dialog Acts Annotations for Online Chats ; Annotation en Actes de Dialogue pour les Conversations d’Assistance en Ligne
|
|
|
|
In: Actes TALN-RECITAL 2018 ; 25e conférence sur le Traitement Automatique des Langues Naturelles (TALN) ; https://hal.archives-ouvertes.fr/hal-01943345 ; 25e conférence sur le Traitement Automatique des Langues Naturelles (TALN), 2018, Rennes, France (2018)
|
|
BASE
|
|
Show details
|
|
6 |
Semantic reranking of CRF label sequences for verbal multiword expression identification
|
|
|
|
In: Moreau, Erwan, Alsulaimani, Ashjan, Maldonado, Alfredo orcid:0000-0001-8426-5249 , Han, Lifeng, Vogel, Carl orcid:0000-0001-8928-8546 and Dutta Chowdhury, Koel (2018) Semantic reranking of CRF label sequences for verbal multiword expression identification. In: Markantonatou, Stella, Ramisch, Carlos orcid:0000-0001-7466-9039 , Savary, Agata and Vincze, Veronika orcid:0000-0002-9844-2194 , (eds.) Multiword expressions at length and in depth: Extended papers from the MWE 2017 workshop. Language Science Press, Berlin, pp. 177-207. ISBN 978-3-96110-124-5 (2018)
|
|
BASE
|
|
Show details
|
|
7 |
Semantic reranking of CRF label sequences for verbal multiword expression identification ; Multiword expressions at length and in depth: Extended papers from the MWE 2017 workshop
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Detecting sections and entities in court decisions using HMM and CRF graphical models
|
|
|
|
In: Conférence Extraction et Gestion des Connaissances ; https://hal.archives-ouvertes.fr/hal-02101479 ; Conférence Extraction et Gestion des Connaissances, Université Grenoble alpes (UGA), Jan 2017, Grenoble, France ; http://egc2017.imag.fr/ (2017)
|
|
BASE
|
|
Show details
|
|
9 |
Detection of Verbal Multi-Word Expressions via Conditional Random Fields with Syntactic Dependency Features and Semantic Re-Ranking
|
|
|
|
In: Proceedings of the 13th Workshop on Multiword Expressions (MWE 2017) ; https://hal.archives-ouvertes.fr/hal-01520762 ; Proceedings of the 13th Workshop on Multiword Expressions (MWE 2017), Apr 2017, Valencia, Spain. pp.114-120 ; http://multiword.sourceforge.net/ (2017)
|
|
BASE
|
|
Show details
|
|
10 |
Detection of verbal multi-word expressions via conditional random fields with syntactic dependency features and semantic re-ranking
|
|
|
|
In: Maldonado, Alfredo orcid:0000-0001-8426-5249 , Han, Lifeng orcid:0000-0002-3221-2185 , Moreau, Erwan orcid:0000-0001-7692-526X , Alsulaimani, Ashjan, Chowdhury, Koel, Vogel, Carl orcid:0000-0001-8928-8546 and Liu, Qun orcid:0000-0002-7000-1792 (2017) Detection of verbal multi-word expressions via conditional random fields with syntactic dependency features and semantic re-ranking. In: 13th Workshop on Multiword Expressions (MWE 2017), Apr 2017, Valencia, Spain. (2017)
|
|
BASE
|
|
Show details
|
|
11 |
Strategies to select examples for Active Learning with Conditional Random Fields
|
|
|
|
In: CICLing 2017 - 18th International Conference on Computational Linguistics and Intelligent Text Processing ; https://hal.archives-ouvertes.fr/hal-01621338 ; CICLing 2017 - 18th International Conference on Computational Linguistics and Intelligent Text Processing, Apr 2017, Budapest, Hungary. pp.1-14 (2017)
|
|
BASE
|
|
Show details
|
|
12 |
Statistical Pronunciation Adaptation for Spontaneous Speech Synthesis
|
|
|
|
In: Text, Speech and Dialogue (TSD) ; https://hal.inria.fr/hal-01532035 ; Text, Speech and Dialogue (TSD), Aug 2017, Prague, Czech Republic (2017)
|
|
BASE
|
|
Show details
|
|
13 |
Structuration in named entities ; La structuration dans les entités nommées
|
|
|
|
In: https://tel.archives-ouvertes.fr/tel-01772268 ; Linguistique. Université Sorbonne Paris Cité, 2017. Français. ⟨NNT : 2017USPCA100⟩ (2017)
|
|
BASE
|
|
Show details
|
|
14 |
Context identification of sentences in related work sections using a conditional random field: towards intelligent digital libraries
|
|
|
|
BASE
|
|
Show details
|
|
15 |
A 2D CRF Model for Sentence Alignment
|
|
|
|
In: 9th Workshop on Building and Using Comparable Corpora ; https://hal.archives-ouvertes.fr/hal-01388656 ; 9th Workshop on Building and Using Comparable Corpora, 2016, Portorož, Slovenia ; http://lrec2016.lrec-conf.org/en/ (2016)
|
|
BASE
|
|
Show details
|
|
16 |
A Hybrid Approach Using Maximum Entropy Model and Conditional Random Fields to Identify Tibetan Person Names
|
|
|
|
In: Jia, Yangji; Li, Yachao; Zong, Chengqing; & Yu, Hongzhi. (2016). A Hybrid Approach Using Maximum Entropy Model and Conditional Random Fields to Identify Tibetan Person Names. Himalayan Linguistics, 15(1). doi:10.5070/H915130107. Retrieved from: http://www.escholarship.org/uc/item/8k20d3x6 (2016)
|
|
BASE
|
|
Show details
|
|
17 |
Understanding Social Media Texts with Minimum Human Effort on #Twitter
|
|
|
|
In: Language and the new (instant) media (PLIN) ; https://hal.archives-ouvertes.fr/hal-01490018 ; Language and the new (instant) media (PLIN), May 2016, Louvain-la-Neuve, Belgium (2016)
|
|
BASE
|
|
Show details
|
|
18 |
Improving TTS with corpus-specific pronunciation adaptation
|
|
|
|
In: Interspeech ; https://hal.inria.fr/hal-01338111 ; Interspeech, Sep 2016, San Francisco, United States (2016)
|
|
BASE
|
|
Show details
|
|
19 |
Phonétisation statistique adaptable d'énoncés pour le français
|
|
|
|
In: Journées d'Études sur la Parole ; https://hal.inria.fr/hal-01321358 ; Journées d'Études sur la Parole, Jul 2016, Paris, France (2016)
|
|
BASE
|
|
Show details
|
|
20 |
МОРФОЛОГИЧЕСКИЙ И СИНТАКСИЧЕСКИЙ АНАЛИЗ ТЕКСТА НА ПЕРСИДСКОМ ЯЗЫКЕ С ПОМОЩЬЮ УСЛОВНЫХ СЛУЧАЙНЫХ ПОЛЕЙ ... : MORPHOLOGICAL AND SYNTACTIC ANALYSIS OF PERSIAN TEXT WITH CONDITIONAL RANDOM FIELDS ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|