Graph-Based Methods for Natural Language Processing and Understanding—A Survey and Analysis

Mills, M.T.; Bourbakis, Nikolaos G.

doi:10.1109/tsmcc.2012.2227472

Cited by 42 publications

(8 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In several machine learning research areas, input data could be naturally represented as graph structure, such as natural language processing [44,38], human pose estimation [11,66,68], visual relationship detection [32], and image classification [50,48]. In [53], Scarselli et al divided machine learning models into two classes due to different application objectives on graph data structure, named node-focused and graph-focused application.…”

Section: Graph For Machine Learningmentioning

confidence: 99%

Person Re-identification with Deep Similarity-Guided Graph Neural Network

Shen

et al. 2018

Lecture Notes in Computer Science

294

177

View full text Add to dashboard Cite

The person re-identification task requires to robustly estimate visual similarities between person images. However, existing person re-identification models mostly estimate the similarities of different image pairs of probe and gallery images independently while ignores the relationship information between different probe-gallery pairs. As a result, the similarity estimation of some hard samples might not be accurate. In this paper, we propose a novel deep learning framework, named Similarity-Guided Graph Neural Network (SGGNN) to overcome such limitations. Given a probe image and several gallery images, SGGNN creates a graph to represent the pairwise relationships between probegallery pairs (nodes) and utilizes such relationships to update the probegallery relation features in an end-to-end manner. Accurate similarity estimation can be achieved by using such updated probe-gallery relation features for prediction. The input features for nodes on the graph are the relation features of different probe-gallery image pairs. The probe-gallery relation feature updating is then performed by the messages passing in SGGNN, which takes other nodes' information into account for similarity estimation. Different from conventional GNN approaches, SGGNN learns the edge weights with rich labels of gallery instance pairs directly, which provides relation fusion more precise information. The effectiveness of our proposed method is validated on three public person re-identification datasets.

show abstract

Section: Graph For Machine Learningmentioning

confidence: 99%

Person Re-identification with Deep Similarity-Guided Graph Neural Network

Shen

et al. 2018

Lecture Notes in Computer Science

294

177

View full text Add to dashboard Cite

show abstract

“…text classification, IE, and grammar-based analysis). Mills and Bourbakis [33] surveyed graph-based techniques for NLP tasks such as classification, semantic similarity analysis, and IE. Similarly, Montoyo et al [34] surveyed sentiment analysis, and Karimi et al [35] explored the state of art of machine translation.…”

Section: Dimension 2: Prototypical Tasksmentioning

confidence: 99%

“…Two articles surveyed existing NLP-related algorithms (Mills and Bourbakis [33] surveyed graph-based methods, AlShawakfa et al [43] compared Arabic root finding algorithms). The rest 20 articles focused on real world NLP-related applications, though no prototypical tasks were explicitly represented.…”

Section: Figure 3 Prototypical Tasks Commonly Studied In Nlp Researchmentioning

confidence: 99%

A Roadmap for Natural Language Processing Research in Information Systems

Liu¹,

Li²,

Thomas³

2017

Proceedings of the Annual Hawaii International Conference on System Sciences

View full text Add to dashboard Cite

show abstract

“…For retaining the relations of words and terms, some researchers proposed to employ graph-based model in text clustering [19,20]. Mousavi et al [21] proposed a weightedgraph representation of text to extract semantic relations in terms of parse trees of sentences.…”

Section: Feature Extractionmentioning

confidence: 99%

A Novel Text Clustering Approach Using Deep-Learning Vocabulary Network

Zhang

Zhao

et al. 2017

Mathematical Problems in Engineering

View full text Add to dashboard Cite

Text clustering is an effective approach to collect and organize text documents into meaningful groups for mining valuable information on the Internet. However, there exist some issues to tackle such as feature extraction and data dimension reduction. To overcome these problems, we present a novel approach named deep-learning vocabulary network. The vocabulary network is constructed based on related-word set, which contains the “cooccurrence” relations of words or terms. We replace term frequency in feature vectors with the “importance” of words in terms of vocabulary network and PageRank, which can generate more precise feature vectors to represent the meaning of text clustering. Furthermore, sparse-group deep belief network is proposed to reduce the dimensionality of feature vectors, and we introduce coverage rate for similarity measure in Single-Pass clustering. To verify the effectiveness of our work, we compare the approach to the representative algorithms, and experimental results show that feature vectors in terms of deep-learning vocabulary network have better clustering performance.

show abstract

Graph-Based Methods for Natural Language Processing and Understanding—A Survey and Analysis

Cited by 42 publications

References 15 publications

Person Re-identification with Deep Similarity-Guided Graph Neural Network

Person Re-identification with Deep Similarity-Guided Graph Neural Network

A Roadmap for Natural Language Processing Research in Information Systems

A Novel Text Clustering Approach Using Deep-Learning Vocabulary Network

Contact Info

Product

Resources

About