Change search
Link to record
Permanent link

Direct link
BETA
Publications (10 of 50) Show all publications
Boman, M., Ben Abdesslem, F., Forsell, E., Gillblad, D., Görnerup, O., Isacsson, N., . . . Kaldo, V. (2019). Learning machines in Internet-delivered psychological treatment. Progress in Artificial Intelligence
Open this publication in new window or tab >>Learning machines in Internet-delivered psychological treatment
Show others...
2019 (English)In: Progress in Artificial Intelligence, ISSN 2192-6352Article in journal (Refereed) Epub ahead of print
Abstract [en]

A learning machine, in the form of a gating network that governs a finite number of different machine learning methods, is described at the conceptual level with examples of concrete prediction subtasks. A historical data set with data from over 5000 patients in Internet-based psychological treatment will be used to equip healthcare staff with decision support for questions pertaining to ongoing and future cases in clinical care for depression, social anxiety, and panic disorder. The organizational knowledge graph is used to inform the weight adjustment of the gating network and for routing subtasks to the different methods employed locally for prediction. The result is an operational model for assisting therapists in their clinical work, about to be subjected to validation in a clinical trial.

Place, publisher, year, edition, pages
Springer Verlag, 2019
Keywords
Ensemble learning, Gating network, Internet-based psychological treatment, Learning machine, Machine learning, Decision support systems, Learning systems, Conceptual levels, Decision supports, Learning machines, Machine learning methods, Operational model, Organizational knowledge, Psychological treatments, Patient treatment
National Category
Natural Sciences
Identifiers
urn:nbn:se:ri:diva-39062 (URN)10.1007/s13748-019-00192-0 (DOI)2-s2.0-85066625908 (Scopus ID)
Available from: 2019-06-26 Created: 2019-06-26 Last updated: 2019-07-31Bibliographically approved
Espinoza, F., Hamfors, O., Karlgren, J., Olsson, F., Persson, P., Hamberg, L. & Sahlgren, M. (2018). Analysis of Open Answers to Survey Questions through Interactive Clustering and Theme Extraction. In: : . Paper presented at Proceedings of the 2018 Conference on Human Information Interaction & Retrieval. New Brunswick, NJ, USA (pp. 317-320).
Open this publication in new window or tab >>Analysis of Open Answers to Survey Questions through Interactive Clustering and Theme Extraction
Show others...
2018 (English)Conference paper, Published paper (Other academic)
Abstract [en]

Œis paper describes design principles for and the implementationof Gavagai Explorer—a new application which builds on interactivetext clustering to extract themes from topically coherent text setssuch as open text answers to surveys or questionnaires.An automated system is quick, consistent, and has full coverageover the study material. A system allows an analyst to analyze moreanswers in a given time period; provides the same initial resultsregardless of who does the analysis, reducing the risks of interraterdiscrepancy; and does not risk miss responses due to fatige orboredom. Œese factors reduce the cost and increase the reliabilityof the service. Œe most important feature, however, is relievingthe human analyst from the frustrating aspects of the coding task,freeing the e‚ort to the central challenge of understanding themes.Gavagai Explorer is available on-line at hŠp://explorer.gavagai.se

Keywords
Information systems → Clustering; Online analytical processing;
National Category
Computer and Information Sciences
Identifiers
urn:nbn:se:ri:diva-34879 (URN)10.1145/3176349.3176892 (DOI)978-1-4503-4925-3 (ISBN)
Conference
Proceedings of the 2018 Conference on Human Information Interaction & Retrieval. New Brunswick, NJ, USA
Available from: 2018-08-21 Created: 2018-08-21 Last updated: 2019-03-06Bibliographically approved
Gyllensten, A. C. & Sahlgren, M. (2018). Distributional term set expansion. In: LREC 2018 - 11th International Conference on Language Resources and Evaluation: . Paper presented at 11th International Conference on Language Resources and Evaluation, LREC 2018, 7 May 2018 through 12 May 2018 (pp. 2554-2558).
Open this publication in new window or tab >>Distributional term set expansion
2018 (English)In: LREC 2018 - 11th International Conference on Language Resources and Evaluation, 2018, p. 2554-2558Conference paper, Published paper (Refereed)
Abstract [en]

This paper is a short empirical study of the performance of centrality and classification based iterative term set expansion methods for distributional semantic models. Iterative term set expansion is an interactive process using distributional semantics models where a user labels terms as belonging to some sought after term set, and a system uses this labeling to supply the user with new, candidate, terms to label, trying to maximize the number of positive examples found. While centrality based methods have a long history in term set expansion (Sarmento et al., 2007; Pantel et al., 2009), we compare them to classification methods based on the the Simple Margin method, an Active Learning approach to classification using Support Vector Machines (Tong and Koller, 2002). Examining the performance of various centrality and classification based methods for a variety of distributional models over five different term sets, we can show that active learning based methods consistently outperform centrality based methods.

Keywords
Active Learning, Distributional Semantics, Lexicon Acquisition, Term Set Expansion, Word Embeddings, Artificial intelligence, Semantics, Embeddings, Set expansions, Iterative methods
National Category
Natural Sciences
Identifiers
urn:nbn:se:ri:diva-37335 (URN)2-s2.0-85059894892 (Scopus ID)9791095546009 (ISBN)
Conference
11th International Conference on Language Resources and Evaluation, LREC 2018, 7 May 2018 through 12 May 2018
Available from: 2019-01-22 Created: 2019-01-22 Last updated: 2019-01-25Bibliographically approved
Gyllensten, A. C. & Sahlgren, M. (2018). Measuring Issue Ownership using Word Embeddings. In: : . Paper presented at Proceedings of the 9th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis. , Article ID W18-6221.
Open this publication in new window or tab >>Measuring Issue Ownership using Word Embeddings
2018 (English)Conference paper, Published paper (Other academic)
Abstract [en]

Sentiment and topic analysis are commonmethods used for social media monitoring.Essentially, these methods answers questionssuch as, “what is being talked about, regardingX”, and “what do people feel, regarding X”.In this paper, we investigate another venue forsocial media monitoring, namely issue ownership and agenda setting, which are conceptsfrom political science that have been used toexplain voter choice and electoral outcomes.We argue that issue alignment and agenda setting can be seen as a kind of semantic sourcesimilarity of the kind “how similar is sourceA to issue owner P, when talking about issue X”, and as such can be measured usingword/document embedding techniques. Wepresent work in progress towards measuringthat kind of conditioned similarity, and introduce a new notion of similarity for predictive embeddings. We then test this methodby measuring the similarity between politically aligned media and political pparties, conditioned on bloc-specific issues.

National Category
Natural Sciences
Identifiers
urn:nbn:se:ri:diva-37583 (URN)
Conference
Proceedings of the 9th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis
Available from: 2019-01-25 Created: 2019-01-25 Last updated: 2019-01-25Bibliographically approved
Kucher, K., Paradis, C., Sahlgren, M. & Kerren, A. (2017). Active learning and visual analytics for stance classification with ALVA. Academic Journal of Research in Business and Accounting, 7(3), Article ID 14.
Open this publication in new window or tab >>Active learning and visual analytics for stance classification with ALVA
2017 (English)In: Academic Journal of Research in Business and Accounting, ISSN 2160-6455, E-ISSN 1084-6654, Vol. 7, no 3, article id 14Article in journal (Refereed) Published
Abstract [en]

The automatic detection and classification of stance (e.g., certainty or agreement) in text data using natural language processing and machine-learning methods creates an opportunity to gain insight into the speakers' attitudes toward their own and other people's utterances. However, identifying stance in text presents many challenges related to training data collection and classifier training. To facilitate the entire process of training a stance classifier, we propose a visual analytics approach, called ALVA, for text data annotation and visualization. ALVA's interplay with the stance classifier follows an active learning strategy to select suitable candidate utterances for manual annotaion. Our approach supports annotation process management and provides the annotators with a clean user interface for labeling utterances with multiple stance categories. ALVA also contains a visualization method to help analysts of the annotation and training process gain a better understanding of the categories used by the annotators. The visualization uses a novel visual representation, called CatCombos, which groups individual annotation items by the combination of stance categories. Additionally, our system makes a visualization of a vector space model available that is itself based on utterances. ALVA is already being used by our domain experts in linguistics and computational linguistics to improve the understanding of stance phenomena and to build a st  ance classifier for applications such as social media monitoring.

Place, publisher, year, edition, pages
Association for Computing Machinery, 2017
Keywords
Artificial intelligence, Classifiers, Data visualization, Learning algorithms, Learning systems, Linguistics, Natural language processing systems, Text processing, User interfaces, Vector spaces, Visualization, Active learning strategies, Automatic Detection, Classifier training, Machine learning methods, Social media monitoring, Vector space models, Visual representations, Visualization method, Classification (of information)
National Category
Computer Systems
Identifiers
urn:nbn:se:ri:diva-38055 (URN)10.1145/3132169 (DOI)2-s2.0-85032958347 (Scopus ID)
Available from: 2019-03-18 Created: 2019-03-18 Last updated: 2019-03-19Bibliographically approved
Sandin, F., Emruli, B. & Sahlgren, M. (2017). Random indexing of multidimensional data. Knowledge and Information Systems, 52(1), 267-290
Open this publication in new window or tab >>Random indexing of multidimensional data
2017 (English)In: Knowledge and Information Systems, ISSN 0219-1377, E-ISSN 0219-3116, Vol. 52, no 1, p. 267-290Article in journal (Refereed) Published
Abstract [en]

Random indexing (RI) is a lightweight dimension reduction method, which is used, for example, to approximate vector semantic relationships in online natural language processing systems. Here we generalise RI to multidimensional arrays and therefore enable approximation of higher-order statistical relationships in data. The generalised method is a sparse implementation of random projections, which is the theoretical basis also for ordinary RI and other randomisation approaches to dimensionality reduction and data representation. We present numerical experiments which demonstrate that a multidimensional generalisation of RI is feasible, including comparisons with ordinary RI and principal component analysis. The RI method is well suited for online processing of data streams because relationship weights can be updated incrementally in a fixed-size distributed representation, and inner products can be approximated on the fly at low computational cost. An open source implementation of generalised RI is provided. © 2016, The Author(s).

Keywords
Data mining, Dimensionality reduction, Natural language processing, Random embeddings, Semantic similarity, Sparse coding, Streaming algorithm
National Category
Natural Sciences
Identifiers
urn:nbn:se:ri:diva-30273 (URN)10.1007/s10115-016-1012-2 (DOI)2-s2.0-85001755138 (Scopus ID)
Available from: 2017-08-11 Created: 2017-08-11 Last updated: 2018-08-21Bibliographically approved
Karlgren, J., Eriksson, G., Täckström, O. & Sahlgren, M. (2010). Between Bags and Trees - Constructional Patterns in Text Used for Attitude Identification (13ed.). In: : . Paper presented at ECIR 2010, 32nd European Conference on Information Retrieval, March 28-31, 2010, Milton Keynes, Great Britain.
Open this publication in new window or tab >>Between Bags and Trees - Constructional Patterns in Text Used for Attitude Identification
2010 (English)Conference paper, Published paper (Refereed)
Abstract [en]

This paper describes experiments to use non-terminological information to find attitudinal expressions in written English text. The experiments are based on an analysis of text with respect to not only the vocabulary of content terms present in it (which most other approaches use as a basis for analysis) but also with respect to presence of structural features of the text represented by constructional features (typically disregarded by most other analyses). In our analysis, following a construction grammar framework, structural features are treated as occurrences, similarly to the treatment of vocabulary features. The constructional features in play are chosen to potentially signify opinion but are not specific to negative or positive expressions. The framework is used to classify clauses, headlines, and sentences from three different shared collections of attitudinal data. We find that constructional features transfer well across different text collections and that the information couched in them integrates easily with a vocabulary based approach, yielding improvements in classification without complicating the application end of the processing framework.

Keywords
NLP for IR, Text Categorization, Clustering, Opinion mining, Sentiment Analysis, Sentiment analysis, Constructional features
National Category
Computer and Information Sciences
Identifiers
urn:nbn:se:ri:diva-23619 (URN)
Conference
ECIR 2010, 32nd European Conference on Information Retrieval, March 28-31, 2010, Milton Keynes, Great Britain
Projects
Attityd
Note

The original publication will be available at www.springerlink.com

Available from: 2016-10-31 Created: 2016-10-31 Last updated: 2018-08-21Bibliographically approved
Recchia, G., Jones, M., Sahlgren, M. & Kanerva, P. (2010). Encoding Sequential Information in Vector Space Models of Semantics: Comparing Holographic Reduced Representation and Random Permutation (11ed.). In: : . Paper presented at Proceedings of the 32nd Annual Cognitive Science Society (pp. 865-870).
Open this publication in new window or tab >>Encoding Sequential Information in Vector Space Models of Semantics: Comparing Holographic Reduced Representation and Random Permutation
2010 (English)Conference paper, Published paper (Refereed)
Abstract [en]

Encoding information about the order in which words typically appear has been shown to improve the performance of high-dimensional semantic space models. This requires an encoding operation capable of binding together vectors in an order-sensitive way, and efficient enough to scale to large text corpora. Although both circular convolution and random permutations have been enlisted for this purpose in semantic models, these operations have never been systematically compared. In Experiment 1 we compare their storage capacity and probability of correct retrieval; in Experiments 2 and 3 we compare their performance on semantic tasks when integrated into existing models. We conclude that random permutations are a scalable alternative to circular convolution with several desirable properties.

National Category
Computer and Information Sciences
Identifiers
urn:nbn:se:ri:diva-23736 (URN)
Conference
Proceedings of the 32nd Annual Cognitive Science Society
Available from: 2016-10-31 Created: 2016-10-31 Last updated: 2018-08-21Bibliographically approved
Sahlgren, M. & Knutsson, O. (2010). Workshop on Extracting and Using Constructions in Computational Linguistics (7ed.). Los Angeles, California, USA: ACL
Open this publication in new window or tab >>Workshop on Extracting and Using Constructions in Computational Linguistics
2010 (English)Book (Refereed)
Place, publisher, year, edition, pages
Los Angeles, California, USA: ACL, 2010 Edition: 7
Series
NAACL HLT 2010
National Category
Computer and Information Sciences
Identifiers
urn:nbn:se:ri:diva-23780 (URN)
Available from: 2016-10-31 Created: 2016-10-31 Last updated: 2018-08-21Bibliographically approved
Sahlgren, M. & Knutsson, O. (2009). Proceedings of the workshop on extracting and using constructions in NLP (1ed.). Kista, Sweden: Swedish Institute of Computer Science
Open this publication in new window or tab >>Proceedings of the workshop on extracting and using constructions in NLP
2009 (English)Report (Other academic)
Abstract [en]

This is a collection of papers presented at the Nodalida 2009 workshop on extracting and using constructions in NLP.

Place, publisher, year, edition, pages
Kista, Sweden: Swedish Institute of Computer Science, 2009. p. 37 Edition: 1
Series
SICS Technical Report, ISSN 1100-3154 ; 2009:10
National Category
Computer and Information Sciences
Identifiers
urn:nbn:se:ri:diva-23526 (URN)
Available from: 2016-10-31 Created: 2016-10-31 Last updated: 2018-08-21Bibliographically approved
Identifiers
ORCID iD: ORCID iD iconorcid.org/0000-0001-5100-0535

Search in DiVA

Show all publications
v. 2.35.7