Aspect Term Extraction Based on MFE-CRF

Xiang, Yanmin; He, Hongyi; Zheng, Jing

doi:10.3390/info9080198

Cited by 14 publications

(24 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…< iPhoneX, sound quality, great>. In general, traditional sequential models like HMMs [72], and CRFs [74]- [77] have been employed by community for document/sentence level aspect and opinion mining. Meanwhile, many prevalent techniques (e.g.…”

Section: ) Problem Settingsmentioning

confidence: 99%

“…Traditional sequential models are suitable for sequential labeling task. Thus, several published works have explored the field by incorporating task specific strategies with HMMs and CRFs [62], [72], [74]- [77], [138]. The 1st − 6th rows in Table 8 list the corresponding models.…”

Section: ) Traditional Sequential Model Based Approachesmentioning

confidence: 99%

“…Based on the assumption, Shu [76] incorporates the lifelong learning into CRF and the proposed approach performs markedly better than the traditional CRF. To capture the semantic relatedness from multiple source embedding, Xiang [77] employs multi-feature embedding as additional position feature to train a CRF-based tagger, and the MFE-CRF also outperforms the traditional CRF.…”

Section: ) Traditional Sequential Model Based Approachesmentioning

confidence: 99%

See 2 more Smart Citations

A Survey on Opinion Mining: From Stance to Product Aspect

Wang¹,

Zhou²,

Jiang³

et al. 2019

IEEE Access

View full text Add to dashboard Cite

With the prevalence of social media and online forum, opinion mining, aiming at analyzing and discovering the latent opinion in user-generated reviews on the Internet, has become a hot research topic. This survey focuses on two important subtasks in this field, stance detection and product aspect mining, both of which can be formalized as the problem of the triple target, aspect, opinion extraction. In this paper, we first introduce the general framework of opinion mining and describe the evaluation metrics. Then, the methodologies for stance detection on different sources, such as online forum and social media are discussed. After that, approaches for product aspect mining are categorized into three main groups which are corpus level aspect extraction, corpus level aspect, and opinion mining, and document level aspect and opinion mining based on the processing units and tasks. And then we discuss the challenges and possible solutions. Finally, we summarize the evolving trend of the reviewed methodologies and conclude the survey. INDEX TERMS Opinion mining, stance detection, product aspect mining, topic model, deep neural network.

show abstract

Section: ) Problem Settingsmentioning

confidence: 99%

Section: ) Traditional Sequential Model Based Approachesmentioning

confidence: 99%

Section: ) Traditional Sequential Model Based Approachesmentioning

confidence: 99%

See 1 more Smart Citation

A Survey on Opinion Mining: From Stance to Product Aspect

Wang¹,

Zhou²,

Jiang³

et al. 2019

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The first paper "Aspect Term Extraction Based on MFE-CRF", by Yanmin Xiang, Hongye He and Jin Zheng [9] focuses on aspect term extraction in aspect-based sentiment analysis, which is one of the hot spots in natural language processing. They propose multi-feature embedding (MFE) clustering based on the conditional random field (CRF) model to improve the effect of aspect term extraction in aspect-based sentiment analysis, showing that MFE can improve both the precision and recall rates of the CRF model.…”

mentioning

confidence: 99%

Special Issue on Advanced Learning Methods for Complex Data

Atzori

Pes

2018

Information

View full text Add to dashboard Cite

The importance of data mining methods has increased dramatically in recent years, making this research area relevant and challenging to extract actionable knowledge from complex data. Indeed, new algorithms and machine learning methods are constantly being explored to deal with domains that present multiple challenges including high-dimensionality, heterogeneity of features, and complex relationships between data objects. This special issue aims at discussing emerging approaches for learning from complex data, including text data, images, and social media data.

show abstract

“…After the SemEval challenge, the generated datasets are still used for training and testing purposes by numerous researchers and constitute the standard benchmarks for ABSA (e.g. Gunes, 2016;Hasib and Rahin, 2017;Kushwaha and Chaundhary, 2017;Li and Lam., 2017;Akhtar et al, 2018;de Kok et al, 2018;Dilawar et al, 2018;Dong and de Melo, 2018;Li, Liu and Zhou, 2018;Moore and Rayson, 2018;Nguyen, 2018;Ouyang and Su, 2018;Piryani, Gupta, and Singh, 2018;Wang et al, 2018;Xiang, He and Zheng, 2018;Zhu and Qian, 2018;. In addition, the proposed datasets were recently enriched with a new annotation layer (sentiment expressions)…”

Section: Towards a Principled Unified Absa Frameworkmentioning

confidence: 99%

Fine-grained Sentiment Analysis

Pontiki¹,

Ποντίκη²

View full text Add to dashboard Cite

Η επιστημονική περιοχή της Ανάλυσης Συναισθήματος/Άποψης αποτελεί ένα βασικό εργαλείο ανάλυσης δεδομένων σε πολλoύς κλάδους, καθώς βοηθάει στον αυτόματο εντοπισμό και την ανάλυση απόψεων, συναισθημάτων, συμπεριφορών και αναγκών που εκφράζονται από χρήστες του διαδικτύου σε τεράστιες ποσότητες μη δομημένων δεδομένων χρησιμοποιώντας μεθόδους Επεξεργασίας Φυσικής Γλώσσας και Εξόρυξης Κειμένου. Η ερευνητική δραστηριότητα αυτής της διδακτορικής διατριβής επικεντρώθηκε σε δύο τύπους περιεχομένου που παράγεται από χρήστες του διαδικτύου: αξιολογήσεις πελατών σχετικά με προϊόντα, υπηρεσίες και τα επιμέρους χαρακτηριστικά τους σε συγκεκριμένους τομείς επιχειρηματικής δραστηριότητας (κριτικές εστιατορίων και φορητών υπολογιστών), και λεκτικές επιθέσεις εναντίον προκαθορισμένων ομάδων στόχων (π.χ. πρόσφυγες, μετανάστες) στον χώρο των ανθρωπιστικών, και συγκεκριμένα, των Υπολογιστικών Κοινωνικών Επιστημών. Στο πλαίσιο αυτό, η παρούσα διατριβή παρουσιάζει: α) ένα ενιαίο πλαίσιο αναπαράστασης γνώσης και τρία σύνολα επισημειωμένων δεδομένων στην Αγγλική γλώσσα για την ανάλυση συναισθήματος/άποψης βασισμένης σε χαρακτηριστικά οντοτήτων, και β) ένα γλωσσικά εμπνευσμένο και καθοδηγούμενο από δεδομένα πλαίσιο για την εξέταση της λεκτικής επιθετικότητας ως δείκτη ξενοφοβικών συμπεριφορών στα ελληνικά μέσα κοινωνικής δικτύωσης.

show abstract

Aspect Term Extraction Based on MFE-CRF

Cited by 14 publications

References 25 publications

A Survey on Opinion Mining: From Stance to Product Aspect

A Survey on Opinion Mining: From Stance to Product Aspect

Special Issue on Advanced Learning Methods for Complex Data

Fine-grained Sentiment Analysis

Contact Info

Product

Resources

About