Filters








162,853 Hits in 7.0 sec

Prior matters: simple and general methods for evaluating and improving topic quality in topic modeling [article]

Angela Fan, Finale Doshi-Velez, Luke Miratrix
2017 arXiv   pre-print
This approach, a collection of informative priors easily introduced into most LDA-style inference methods, automatically promotes terms with domain relevance and demotes domain-specific stop words.  ...  Latent Dirichlet Allocation (LDA) models trained without stopword removal often produce topics with high posterior probabilities on uninformative words, obscuring the underlying corpus content.  ...  Thanks also to Chirag Lakhani and Tim Miller (and others) for scoring topics and topic words.  ... 
arXiv:1701.03227v3 fatcat:xaozv3k7pzcrfcfxvjm56zhj7q

Lifelong Machine Learning for Topic Modeling and Beyond

Zhiyuan Chen
2015 Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop  
In this thesis proposal, I first present a survey of lifelong machine learning (LML). I then narrow down to one specific NLP task, i.e., topic modeling.  ...  I propose several approaches to apply lifelong learning idea in topic modeling. Such capability is essential to make an NLP system versatile and holistic.  ...  Acknowledgments This work was supported in part by grants from National Science Foundation (NSF) under grant no. IIS-1111092 and IIS-1407927.  ... 
doi:10.3115/v1/n15-2018 dblp:conf/naacl/Chen15 fatcat:ml4cs6bklvgnhajrrmkf527mje

Mining topics in documents

Zhiyuan Chen, Bing Liu
2014 Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining - KDD '14  
In recently years, knowledge-based topic models have been proposed, which ask human users to provide some prior domain knowledge to guide the model to produce better topics.  ...  When faced with a new task, we first mine some reliable (prior) knowledge from the past learning/modeling results and then use it to guide the model inference to generate more coherent topics.  ...  Asking users to provide prior domain knowledge: An obvious form of external information is the prior knowledge of the domain from the user.  ... 
doi:10.1145/2623330.2623622 dblp:conf/kdd/Chen014 fatcat:6g52s45esfagjhrleo2woglcoy

Mining Aspect-Specific Opinion using a Holistic Lifelong Topic Model

Shuai Wang, Zhiyuan Chen, Bing Liu
2016 Proceedings of the 25th International Conference on World Wide Web - WWW '16  
In this paper, we first propose a holistic fine-grained topic model, called the JAST (Joint Aspectbased Sentiment Topic) model, that can simultaneously model all of above problems under a unified framework  ...  LAST automatically mines the prior knowledge of aspect, opinion, and their correspondence from other products or domains.  ...  This work was supported in part by a grant from National Science Foundation (NSF) under grant no. IIS-1407927, a NCI grant under grant no. R01CA192240, and a gift from Bosch.  ... 
doi:10.1145/2872427.2883086 dblp:conf/www/WangC016 fatcat:v6d24dyntjbtbiz2mv4gzg32ny

A Query-Driven Topic Model [article]

Zheng Fang, Yulan He, Rob Procter
2021 arXiv   pre-print
A possible solution is to incorporate domain-specific knowledge into topic modeling, but this requires a specification from domain experts.  ...  Experimental results demonstrate the effectiveness of our model in comparison with both classical topic models and neural topic models.  ...  All these approaches require experts to provide domain-specific, prior knowledge, which is problematic for two reasons: different corpora in the same domain may contain different information; and it may  ... 
arXiv:2106.07346v2 fatcat:mvoi324y3reu5pgxnwnfqkqe5q

Termite

Jason Chuang, Christopher D. Manning, Jeffrey Heer
2012 Proceedings of the International Working Conference on Advanced Visual Interfaces - AVI '12  
In this paper we present Termite, a visual analysis tool for assessing topic model quality. Termite uses a tabular layout to promote comparison of terms both within and across latent topics.  ...  Topic models aid analysis of text corpora by identifying latent topics based on co-occurring words.  ...  In contrast to existing tools for summarizing LDA model output [11] , Termite aims to support the domain-specific task of building and refining topic models.  ... 
doi:10.1145/2254556.2254572 dblp:conf/avi/ChuangMH12 fatcat:rjujvpqxsrgntct3rhvcpy3ute

Promoting ranking diversity for genomics search with relevance-novelty combined model

Xiaoshi Yin, Zhoujun Li, Jimmy Huang, Xiaohua Hu
2011 BMC Bioinformatics  
In the biomedical domain, the desired information of a question (query) asked by biologists usually is a list of a certain type of entities covering different aspects that are related to the question,  ...  It consists of two component models, namely the aspect-term relevance model and the aspect-term novelty model. They model the relevance of a document and the novelty of a document respectively.  ...  Acknowledgements This research is supported in part by the National Natural Science Foundation of China (under  ... 
doi:10.1186/1471-2105-12-s5-s8 pmid:21989180 pmcid:PMC3226257 fatcat:wxx2rexkybdjnotjfoht622qgi

A proposal for chemical information retrieval evaluation

Jianhan Zhu, John Tait
2008 Proceeding of the 1st ACM workshop on Patent information retrieval - PaIR '08  
Based on the important progresses made in information retrieval (IR) in terms of theoretical models and evaluations, more and more attention has recently been paid to the research in domain specific IR  ...  We think that now is the right time to carry out large scale evaluations on chemistry datasets in order to promote the research in chemical IR in general and chemical patent IR in particular.  ...  Domain specific IR deserves special attention since specific domains have special characteristics and user information needs distinct from general purpose IR.  ... 
doi:10.1145/1458572.1458577 dblp:conf/cikm/ZhuT08 fatcat:2kddhweeovcrpl7e2y5l7kp47m

Promoting Domain-Specific Participation via Off-topic Forum Participation in Electronic Networks of Practice

Thomas Mattson, Elizabeth Davidson
2018 Communications of the Association for Information Systems  
In this paper, we investigate how members' participation in off-topic social forums in electronic networks of practice (eNoPs) influences their propensity to participate in their domain-specific forums  ...  Our paper highlights new theoretical insights on the network effects in an eNoP whereby network structures in one section (off-topic forums) have ramifications for behaviors in a different section (domain-specific  ...  terms of promoting domain-specific participation.  ... 
doi:10.17705/1cais.04335 fatcat:3eo7mbtrx5hkrec37zeybejlsm

Improving Learner's Cognitive Learning Skills in Course based Learning Environment

Kalla Madhusudhana
2017 Indian Journal of Science and Technology  
In order to overcome the deficiency of existing metadata standards, this research work proposed the content model for course based e-learning environment.  ...  Objectives: The existing metadata standards in e-learning domain have been subject to much criticism for its lack of explicit category of metadata to allow cognitive-based description of learning resources  ...  In educational domain, the pool of course concepts is connected to form hierarchy. 8 The domain ontology contains information about the domain knowledge of learning content and describes the content  ... 
doi:10.17485/ijst/2017/v10i14/109982 fatcat:bn5dnrxyava4xbcra5qn2cy5j4

Weakly-supervised Domain Adaption for Aspect Extraction via Multi-level Interaction Transfer [article]

Tao Liang, Wenya Wang, Fengmao Lv
2020 arXiv   pre-print
Specifically, the aspect category information is used to construct pivot knowledge for transfer with assumption that the interactions between sentence-level aspect category and token-level aspect terms  ...  Fine-grained aspect extraction is an essential sub-task in aspect based opinion analysis. It aims to identify the aspect terms (a.k.a. opinion targets) of a product or service in each sentence.  ...  Then the specific aspect terms can be informed in the target domain given the sentence-level aspect category labels.  ... 
arXiv:2006.09235v1 fatcat:t6diemitzfe2fneaq5lmixbci4

Mechanisms of Epistemic Change—Under Which Circumstances Does Diverging Information Support Epistemic Development?

Martin Kerwer, Tom Rosman
2018 Frontiers in Psychology  
change and (3) how topic-specific diverging information affects topic-and domain-specific epistemic beliefs.  ...  Moreover, our findings indicate that effects of topic-specific interventions are more pronounced on topic-specific measures.  ...  Furthermore, we would like to thank Lisa Friedrich, Magdalena Hornung, Tabea Kloos, Giulia Wilhelmi and Hanna Drucks for their support in recruiting, data collection, data entry, and data preparation.  ... 
doi:10.3389/fpsyg.2018.02278 pmid:30524345 pmcid:PMC6262050 fatcat:6febs3gvpzfdfmyt6pyofnbpki

Mind wandering and reading comprehension: Examining the roles of working memory capacity, interest, motivation, and topic experience

Nash Unsworth, Brittany D. McMillan
2013 Journal of Experimental Psychology. Learning, Memory and Cognition  
These results suggest that both domain-general and domain-specific factors contribute to mind wandering while reading and to reading comprehension.  ...  In particular, individual differences in mind wandering, working memory capacity, interest in the current topic, motivation to do well on the task, and topic experience and their relations with reading  ...  In terms of individual differences in reading comprehension, the current results are consistent with the prior literature suggesting that topic experience (prior knowledge), interest, motivation, WMC,  ... 
doi:10.1037/a0029669 pmid:22905931 fatcat:3elyeyoetvfpzasvrhoywpalni

Exploring the Development of Research, Technology and Business of Machine Tool Domain in New-Generation Information Technology Environment Based on Machine Learning

Jihong Chen, Kai Zhang, Yuan Zhou, Yufei Liu, Lingfeng Li, Zheng Chen, Li Yin
2019 Sustainability  
To solve this challenge, we propose an integrating framework combining topic models, bibliometric, trend analysis and patent analysis to mine multi-source literature within the machine tool domain, including  ...  Although much attention has been paid to development studies of a specific domain in recent years, it is challenging to conduct a multidimensional study related to the development status of the machine  ...  plays a critical role in promoting the integration of the machine tool technology with the emerging information technologies.  ... 
doi:10.3390/su11123316 fatcat:i2sb6xsybbecxdau2qbima2bxq

Measuring Process-oriented Teaching

Fabio Alivernini, Sara Manganelli, Fabio Lucidi
2013 Procedia - Social and Behavioral Sciences  
The reliability of the scales in terms of internal consistency ranged from .81 to .87.  ...  Process-oriented teaching is generally recognized as a way to promote lifelong learning, which in turn is tied to a demand of modern society.  ...  a specific topic.  ... 
doi:10.1016/j.sbspro.2013.06.754 fatcat:kfvxq4jkq5hbrhejm7aguewu3m
« Previous Showing results 1 — 15 out of 162,853 results