Filters








57,194 Hits in 3.5 sec

Topic supervised non-negative matrix factorization [article]

Kelsey MacMillan, James D. Wilson
2017 arXiv   pre-print
In this paper, we introduce a semi-supervised method called topic supervised non-negative matrix factorization (TS-NMF) that enables the user to provide labeled example documents to promote the discovery  ...  The core of TS-NMF relies on solving a non-convex optimization problem for which we derive an iterative algorithm that is shown to be monotonic and convergent to a local optimum.  ...  Topic Supervised Non-negative Matrix Factorization Suppose that one supervises k << n documents and identifies << t topics that were contained in a subset of the documents.  ... 
arXiv:1706.05084v2 fatcat:m7xfrkogubeozkprcwvsrjiala

Guided Semi-Supervised Non-negative Matrix Factorization on Legal Documents [article]

Pengyu Li, Christine Tseng, Yaxuan Zheng, Joyce A. Chew, Longxiu Huang, Benjamin Jarman, Deanna Needell
2022 arXiv   pre-print
Non-negative Matrix Factorization (Guided NMF).  ...  In this paper, we propose a method, namely Guided Semi-Supervised Non-negative Matrix Factorization (GSSNMF), that performs both classification and topic modeling by incorporating supervision from both  ...  results. 2 Related Work Classical Non-negative Matrix Factorization Non-negative matrix factorization (NMF) is a powerful framework for performing unsupervised tasks such as topic modeling and clustering  ... 
arXiv:2201.13324v1 fatcat:3sjpru6hlra7fhqubuyjmqbw3m

Word Sense Disambiguation Based On Global Co-Occurrence Information Using Non-Negative Matrix Factorization

Minoru Sasaki
2017 Journal of Computer Science Applications and Information Technology  
In this paper, I propose a novel word sense disambiguation method based on global co-occurrence information using Non-negative Matrix Factorization (NMF).  ...  In this paper, I propose a novel WSD method based on the global co-occurrence information using Non-Negative Matrix Factorization (NMF).  ...  Non-Negative Matrix Factorization Non-Negative Matrix Factorization (NMF) is a popular decomposition method for multivariate data [4] .  ... 
doi:10.15226/2474-9257/2/3/00117 fatcat:n2l5nhyn6ffbxbbhvywv3pvwuu

Build Emotion Lexicon from the Mood of Crowd via Topic-Assisted Joint Non-negative Matrix Factorization

Kaisong Song, Wei Gao, Ling Chen, Shi Feng, Daling Wang, Chengqi Zhang
2016 Proceedings of the 39th International ACM SIGIR conference on Research and Development in Information Retrieval - SIGIR '16  
emotion lexicon from the mood of crowd via topic-assisted joint non-negative matrix factorization. (2016).  ...  We build an emotion lexicon by developing a novel joint non-negative matrix factorization model which not only incorporates crowd-annotated emotion labels of articles but also generates the lexicon using  ...  Semi-Supervised NMF (SSNMF) Non-negative Matrix Factorization (NMF) [5] is an unsupervised algorithm widely used in image or text representation.  ... 
doi:10.1145/2911451.2914759 dblp:conf/sigir/SongGCFWZ16 fatcat:fdf45jr4fvgphitmvmrat2sudy

Analysis of Legal Documents via Non-negative Matrix Factorization Methods [article]

Ryan Budahazy, Lu Cheng, Yihuan Huang, Andrew Johnson, Pengyu Li, Joshua Vendrow, Zhoutong Wu, Denali Molitor, Elizaveta Rebrova, Deanna Needell
2021 arXiv   pre-print
Processing and interpreting this large amount of information presents a significant challenge for CIP officials, which can be successfully aided by topic modeling techniques.In this paper, we apply Non-negative  ...  Matrix Factorization (NMF) method and implement various offshoots of it to the important and previously unstudied data set compiled by CIP.  ...  Discussion and Future Works In this paper, we first provide an exposition of popular variants of Non-negative Matrix Factorization.  ... 
arXiv:2104.14028v2 fatcat:mw66ghemo5g2lnj7x5j4fzmsai

Bridging Domains with Words: Opinion Analysis with Matrix Tri-factorizations [chapter]

Tao Li, Vikas Sindhwani, Chris Ding, Yi Zhang
2010 Proceedings of the 2010 SIAM International Conference on Data Mining  
We outline a novel sentiment transfer mechanism based on constrained non-negative matrix tri-factorizations of termdocument matrices in the source and target domains.  ...  A key enabler of opinion extraction and summarization is sentiment classification: the task of automatically identifying whether a given piece of text expresses positive or negative opinion towards a topic  ...  Basic Matrix Factorization Model Our proposed models are based on non-negative matrix trifactorization [7] .  ... 
doi:10.1137/1.9781611972801.26 dblp:conf/sdm/LiSDZ10 fatcat:kzumj7cv35gy7mft3f4o6nwmqy

Community-Detection via Hashtag-Graphs for Semi-Supervised NMF Topic Models [article]

Mattias Luber and Anton Thielmann and Christoph Weisser and Benjamin Säfken
2021 arXiv   pre-print
Therefore, this paper outlines a novel approach on how to integrate topic structures of hashtag graphs into the estimation of topic models by connecting graph-based community detection and semi-supervised  ...  By applying this approach on recently streamed Twitter data it will be seen that this procedure actually leads to more intuitive and humanly interpretable topics.  ...  For integrating this prior knowledge into the process of topic modelling semi-supervised non-negative matrix factorization can be used as a great interface as it also allows to control the impact of the  ... 
arXiv:2111.10401v1 fatcat:je63bxjf3vevrpzw7vzwdcd4u4

Guided Semi-Supervised Non-Negative Matrix Factorization

Pengyu Li, Christine Tseng, Yaxuan Zheng, Joyce A. Chew, Longxiu Huang, Benjamin Jarman, Deanna Needell
2022 Algorithms  
Non-negative Matrix Factorization (Guided NMF), and Topic Supervised NMF.  ...  In this paper, we propose a novel method, namely Guided Semi-Supervised Non-negative Matrix Factorization (GSSNMF), that performs both classification and topic modeling by incorporating supervision from  ...  Classical Non-Negative Matrix Factorization Non-negative matrix factorization (NMF) is a powerful framework for performing unsupervised tasks such as topic modeling and clustering [1] .  ... 
doi:10.3390/a15050136 fatcat:sl7ppahcs5hd3cqzvifuhirug4

Dimensionality Reduction for Histogram Features Based on Supervised Non-negative Matrix Factorization

Mitsuru AMBAI, Nugraha P. UTAMA, Yuichi YOSHIDA
2011 IEICE transactions on information and systems  
We propose a supervised method of reducing the dimensionality of histogram-based features by using non-negative matrix factorization (NMF).  ...  This interesting characteristic not only makes it easy to interpret the meaning of each basis but also improves the power of classification. key words: dimensionality reduction, non-negative matrix factorization  ...  For the purpose of constructing a lowdimensional feature space for non-negative data, use of non-negative matrix factorization (NMF) [7] has been focused on, instead of principal component analysis (  ... 
doi:10.1587/transinf.e94.d.1870 fatcat:77b4jab2sva3jimehrzmrg7ro4

Weak Supervision for Semi-supervised Topic Modeling via Word Embeddings [chapter]

Gerald Conheady, Derek Greene
2017 Lecture Notes in Computer Science  
It assumes interactions with a user who can provide a strictly limited level of supervision, which is subsequently employed in semi-supervised matrix factorization.  ...  This paper proposes a new process, called Niche+, for finding these kinds of niche topics.  ...  Unsupervised algorithms, such as Non-negative Matrix Factorization (NMF) [7] , have been used to uncover the underlying topical structure in unlabeled text corpora [1] .  ... 
doi:10.1007/978-3-319-59888-8_13 fatcat:5fcbonwdu5exdkp3h3jbtv2ye4

Topic Modeling of Behavioral Modes Using Sensor Data [article]

Yehezkel S. Resheff, Shay Rotics, Ran Nathan, Daphna Weinshall
2015 arXiv   pre-print
Here we present a matrix factorization based topic-model method for accelerometer bursts, derived using a linear mixture property of patch features.  ...  A common use of accelerometer data is for supervised learning of behavioral modes.  ...  Non-Negative Matrix Factorization (NNMF) has been studied extensively in the context of clustering [27, 13] and topic modeling [1] .  ... 
arXiv:1511.05082v1 fatcat:dpe67ftmzrh7bfwwkveie4rwsi

Topic Modeling: A Comprehensive Review

Pooja Kherwa, Poonam Bansal
2018 EAI Endorsed Transactions on Scalable Information Systems  
Quantitative evaluation of topic modeling techniques is also presented in detail for better understanding the concept of topic modeling.  ...  After analysing approximately 300 research articles on topic modeling, a comprehensive survey on topic modelling has been presented in this paper.  ...  S. (1999) Learning the parts of objects by non-negative matrix factorization.  ... 
doi:10.4108/eai.13-7-2018.159623 fatcat:lu6al57vp5aahbytyejhqrlzry

CRF based Feature Extraction Applied for Supervised Automatic Text Summarization

Nowshath K. Batcha, Normaziah A. Aziz, Sharil I. Shafie
2013 Procedia Technology - Elsevier  
Hence this paper proposes a Conditional Random Field (CRF) based ATS which can identify and extract the correct features which is the main issue that exists with the Non-negative Matrix Factorization (  ...  This work proposes a trainable supervised method.  ...  Non negative Matrix Factorization Recently Non-negative Matrix Factorization (NMF) has seized a finite attention in the field of information retrieval.  ... 
doi:10.1016/j.protcy.2013.12.212 fatcat:eray57kozvbctnn7bivtu7pcai

A Review on Different Opinion and Aspect Mining Techniques

Devi Venugopal, Remya R.
2016 International Journal of Computer Applications  
Opinion mining or aspect mining involves the extraction of useful information (e.g. positive or negative sentiments of a product) from a large quantity of text opinions or reviews given by Internet users  ...  Find non-negative matrix factors Wand H for a given non-negative matrix V, such that: V WH, where W features (rows), H observations/examples/feature vectors (columns).  ...  NMF NMF is Non negative Matrix Factorization(NMF) [9] which is a deterministic method for topic modeling. Topics can be identified by decomposing the data matrix into two low rank matrices.  ... 
doi:10.5120/ijca2016908127 fatcat:2jxs6ieningr3nd4kj6lak4qwq

Stability analysis of multiplicative update algorithms for non-negative matrix factorization

Roland Badeau, Nancy Bertin, Emmanuel Vincent
2011 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)  
Multiplicative update algorithms have encountered a great success to solve optimization problems with non-negativity constraints, such as the famous non-negative matrix factorization (NMF) and its many  ...  Index Terms-Optimization methods, non-negative matrix factorization, multiplicative update algorithms, stability, Lyapunov methods.  ...  INTRODUCTION Non-negative matrix factorization (NMF) is a popular technique allowing the decomposition of two-dimensional non-negative data as a linear combination of meaningful elements in a dictionary  ... 
doi:10.1109/icassp.2011.5946752 dblp:conf/icassp/BadeauBV11 fatcat:fhde6r642vbehmesnsa53wlgaq
« Previous Showing results 1 — 15 out of 57,194 results