Change search
Link to record
Permanent link

Direct link
BETA
Publications (10 of 14) Show all publications
Strömbergsson, S., Edlund, J., Götze, J. & Björkenstam, K. N. (2017). Approximating phonotactic input in children's linguistic environments from orthographic transcripts. In: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH 2017: . Paper presented at 18th Annual Conference of the International Speech Communication Association, INTERSPEECH 2017, 20 August 2017 through 24 August 2017 (pp. 2213-2217). International Speech Communication Association, 2017
Open this publication in new window or tab >>Approximating phonotactic input in children's linguistic environments from orthographic transcripts
2017 (English)In: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH 2017, International Speech Communication Association , 2017, Vol. 2017, p. 2213-2217Conference paper, Published paper (Refereed)
Abstract [en]

Child-directed spoken data is the ideal source of support for claims about children's linguistic environments. However, phonological transcriptions of child-directed speech are scarce, compared to sources like adult-directed speech or text data. Acquiring reliable descriptions of children's phonological environments from more readily accessible sources would mean considerable savings of time and money. The first step towards this goal is to quantify the reliability of descriptions derived from such secondary sources. We investigate how phonological distributions vary across different modalities (spoken vs. written), and across the age of the intended audience (children vs. adults). Using a previously unseen collection of Swedish adult-and child-directed spoken and written data, we combine lexicon look-up and graphemeto-phoneme conversion to approximate phonological characteristics. The analysis shows distributional differences across datasets both for single phonemes and for longer phoneme sequences. Some of these are predictably attributed to lexical and contextual characteristics of text vs. speech. The generated phonological transcriptions are remarkably reliable. The differences in phonological distributions between child-directed speech and secondary sources highlight a need for compensatory measures when relying on written data or on adult-directed spoken data, and/or for continued collection of actual child-directed speech in research on children's language environments.

Place, publisher, year, edition, pages
International Speech Communication Association, 2017
Keywords
Grapheme-To-Phoneme Conversion, language Acquisition, Phonology
National Category
Language Technology (Computational Linguistics)
Identifiers
urn:nbn:se:kth:diva-222093 (URN)10.21437/Interspeech.2017-1634 (DOI)000457505000462 ()2-s2.0-85039166025 (Scopus ID)
Conference
18th Annual Conference of the International Speech Communication Association, INTERSPEECH 2017, 20 August 2017 through 24 August 2017
Note

QC 20180131

Available from: 2018-01-31 Created: 2018-01-31 Last updated: 2019-09-24Bibliographically approved
Götze, J. & Johan, B. (2017). Reference resolution for pedestrian wayfinding systems. In: 20th AGILE International Conference on Geographic Information Science, 2017: . Paper presented at 9 May 2017 through 12 May 2017 (pp. 59-75). Kluwer Academic Publishers
Open this publication in new window or tab >>Reference resolution for pedestrian wayfinding systems
2017 (English)In: 20th AGILE International Conference on Geographic Information Science, 2017, Kluwer Academic Publishers , 2017, p. 59-75Conference paper, Published paper (Refereed)
Abstract [en]

References to objects in our physical environment are common especially in language about wayfinding. Advanced wayfinding systems that interact with the pedestrian bymeans of (spoken) natural language therefore need to be able to resolve references given by pedestrians (i.e. understand what entity the pedestrian is referring to). The contribution of this paper is a probabilistic approach to reference resolution in a large-scale, real city environment, where the context changes constantly as the pedestrians are moving. The geographic situation, including information about objects’ location and type, is represented using OpenStreetMap data.

Place, publisher, year, edition, pages
Kluwer Academic Publishers, 2017
Keywords
Data-driven methods, Natural language processing, Openstreetmap, Pedestrian navigation, Probabilistic approach, Reference resolution, Wayfinding, Air navigation, Geographic information systems, Mobile devices, Natural language processing systems, Telecommunication services, Probabilistic approaches, Way-finding, Location based services
National Category
Computer Systems
Identifiers
urn:nbn:se:kth:diva-207439 (URN)10.1007/978-3-319-56759-4_4 (DOI)2-s2.0-85017505207 (Scopus ID)9783319472881 (ISBN)9783319567587 (ISBN)
Conference
9 May 2017 through 12 May 2017
Note

QC 20170523

Available from: 2017-05-23 Created: 2017-05-23 Last updated: 2019-10-17Bibliographically approved
Götze, J. & Boye, J. (2016). Learning Landmark Salience Models from Users' Route Instructions. Journal of Location Based Services, 10(1), 47-63
Open this publication in new window or tab >>Learning Landmark Salience Models from Users' Route Instructions
2016 (English)In: Journal of Location Based Services, ISSN 1748-9725, Vol. 10, no 1, p. 47-63Article in journal (Refereed) Published
Abstract [en]

Route instructions for pedestrians are usually better understood if they include references to landmarks, and moreover, these landmarks should be as salient as possible. In this paper, we present an approach for automatically deriving a mathematical model of salience directly from route instructions given by humans. Each possible landmark that a person can refer to in a given situation is modelled as a feature vector, and the salience associated with each landmark can be computed as a weighted sum of these features. We use a ranking SVM method to derive the weights from route instructions given by humans as they are walking the route. The weight vector, representing the person’s personal salience model, determines which landmark(s) are most appropriate to refer to in new situations.

Place, publisher, year, edition, pages
Taylor & Francis, 2016
Keywords
Pedestrian navigation, landmark salience, ranking algorithm, spoken route descriptions
National Category
Information Systems
Identifiers
urn:nbn:se:kth:diva-186356 (URN)10.1080/17489725.2016.1172739 (DOI)000378235800005 ()2-s2.0-84964422547 (Scopus ID)
Funder
Swedish Research Council, 2013-4854
Note

QC 20160510

Available from: 2016-05-10 Created: 2016-05-10 Last updated: 2018-01-10Bibliographically approved
Götze, J. (2016). Talk the walk: Empirical studies and data-driven methods for geographical natural language applications. (Doctoral dissertation). KTH Royal Institute of Technology
Open this publication in new window or tab >>Talk the walk: Empirical studies and data-driven methods for geographical natural language applications
2016 (English)Doctoral thesis, monograph (Other academic)
Abstract [en]

Finding the way in known and unknown city environments is a task that all pedestrians carry out regularly. Current technology allows the use of smart devices as aids that can give automatic verbal route directions on the basis of the pedestrian's current position. Many such systems only give route directions, but are unable to interact with the user to answer clarifications or understand other verbal input. Furthermore, they rely mainly on conveying the quantitative information that can be derived directly from geographic map representations: 'In 300 meters, turn into High Street'. However, humans are reasoning about space predominantly in a qualitative manner, and it is less cognitively demanding for them to understand route directions that express such qualitative information, such as 'At the church, turn left' or 'You will see a café'. This thesis addresses three challenges that an interactive wayfinding system faces in the context of natural language generation and understanding: in a given situation, it must decide on whether it is appropriate to give an instruction based on a relative direction, it must be able to select salient landmarks, and it must be able to resolve the user's references to objects. In order to address these challenges, this thesis takes a data-driven approach: data was collected in a large-scale city environment to derive decision-making models from pedestrians' behavior. As a representation for the geographical environment, all studies use the crowd-sourced Openstreetmap database. The thesis presents methodologies on how the geographical and language data can be utilized to derive models that can be incorporated into an automatic route direction system.

Place, publisher, year, edition, pages
KTH Royal Institute of Technology, 2016. p. 183
Series
TRITA-CSC-A, ISSN 1653-5723 ; 2016:13
Keywords
pedestrian wayfinding, salience, route instructions, reference resolution
National Category
Computer Sciences Information Systems Language Technology (Computational Linguistics)
Research subject
Computer Science
Identifiers
urn:nbn:se:kth:diva-186358 (URN)978-91-7595-978-8 (ISBN)
Public defence
2016-06-10, D3, Lindstedtsvägen 5, Stockholm, 14:00 (English)
Opponent
Supervisors
Funder
EU, FP7, Seventh Framework Programme, 270019Swedish Research Council, 2013-4854
Note

QC 20160516

Available from: 2016-05-16 Created: 2016-05-10 Last updated: 2018-01-10Bibliographically approved
Götze, J. & Boye, J. (2015). Resolving spatial references using crowdsourced geographical data. In: Proceedings of the 20th Nordic Conference of Computational Linguistics, NODALIDA 2015: . Paper presented at 20th Nordic Conference on Computational Linguistics, Wilna, Lithuania, 2015 (pp. 61-68). Linköping University Electronic Press
Open this publication in new window or tab >>Resolving spatial references using crowdsourced geographical data
2015 (English)In: Proceedings of the 20th Nordic Conference of Computational Linguistics, NODALIDA 2015, Linköping University Electronic Press, 2015, p. 61-68Conference paper, Published paper (Refereed)
Abstract [en]

We present a study in which we seek to interpret spatial references that are part of in-situ route descriptions. Our aim is to resolve these references to actual entities and places in the city using a crowdsourced geographic database (OpenStreetMap). We discuss the problems related to this task, and present a possible automatic reference resolution method that can find the correct referent in 68% of the cases using features that are easily computable from the map.

Place, publisher, year, edition, pages
Linköping University Electronic Press, 2015
National Category
Language Technology (Computational Linguistics)
Identifiers
urn:nbn:se:kth:diva-165612 (URN)
Conference
20th Nordic Conference on Computational Linguistics, Wilna, Lithuania, 2015
Funder
Swedish Research Council, 2013-4854
Note

QC 20150508

Available from: 2015-04-29 Created: 2015-04-29 Last updated: 2018-01-11Bibliographically approved
Götze, J. & Boye, J. (2015). "Turn left" vs. "Walk towards the cafe": When relative directions work better than landmarks. In: Bacao, F., M.Y. Santos, M. Painho (Ed.), AGILE 2015: Geographic Information Science as an Enabler of Smarter Cities and Communities. Part III. Paper presented at 18th AGILE Conference on Geographic Information Science, Lisboa, Portugal,June 9th – 12th 2015 (pp. 253-267). Paper presented at 18th AGILE Conference on Geographic Information Science, Lisboa, Portugal,June 9th – 12th 2015. Springer Publishing Company
Open this publication in new window or tab >>"Turn left" vs. "Walk towards the cafe": When relative directions work better than landmarks
2015 (English)In: AGILE 2015: Geographic Information Science as an Enabler of Smarter Cities and Communities. Part III / [ed] Bacao, F., M.Y. Santos, M. Painho, Springer Publishing Company, 2015, p. 253-267Chapter in book (Refereed)
Abstract [en]

An automatic mechanism that gives verbal navigation instructions to pedestrians in situ needs to take into account a number of factors. Besides giving the instruction at the righttime and place, the information needs to be as unambiguous as possible for the user to both choose the correct path and be confident in doing so. Humans make extensive use of landmarks when describ-ing the way to others and are more successful following instructions that in-clude landmarks. We present a study comparing landmark-based instructions with relative direction instructions on pedestrians in a real city environment, measuring both objective and subjective success. We find that atsome deci-sion points, relative direction instructions work better. We present a method that uses openly available geographic data to predict which kindof instruction is preferable ata given decision point.

Place, publisher, year, edition, pages
Springer Publishing Company, 2015
Series
Lecture Notes in Geoinformation and Cartography, ISSN 1863-2246
National Category
Language Technology (Computational Linguistics)
Identifiers
urn:nbn:se:kth:diva-165593 (URN)10.1007/978-3-319-16787-9_15 (DOI)000380561000015 ()2-s2.0-84945958077 (Scopus ID)978-3-319-16787-9 (ISBN)
External cooperation:
Conference
18th AGILE Conference on Geographic Information Science, Lisboa, Portugal,June 9th – 12th 2015
Projects
VR 2013-4854 “Personalized spatially- aware dialogue systems”
Funder
Swedish Research Council, 2013-4854
Note

QC 20150518

Available from: 2015-04-29 Created: 2015-04-29 Last updated: 2018-01-11Bibliographically approved
Fredriksson, M., Königsmann, J., Bartie, P., Boye, J., Dalmas, T., Götze, J., . . . Minock, M. (2014). D5.2.2: Final city search SpaceBook prototype. Paper presented at Geographic Human-Computer Interaction (GeoHCI) workshop at CHI.
Open this publication in new window or tab >>D5.2.2: Final city search SpaceBook prototype
Show others...
2014 (English)Report (Other academic)
Publisher
p. 9
National Category
Computer and Information Sciences
Research subject
Computer Science
Identifiers
urn:nbn:se:kth:diva-134887 (URN)
Conference
Geographic Human-Computer Interaction (GeoHCI) workshop at CHI
Projects
spacebook-project.eu
Funder
EU, FP7, Seventh Framework Programme
Note

QC 20150429

Available from: 2015-04-29 Created: 2013-12-01 Last updated: 2018-01-11Bibliographically approved
Boye, J., Fredriksson, M., Götze, J., Gustafson, J. & Königsmann, J. (2014). Walk this way: Spatial grounding for city exploration. In: Natural interaction with robots, knowbots and smartphones: (pp. 59-67). Springer-Verlag
Open this publication in new window or tab >>Walk this way: Spatial grounding for city exploration
Show others...
2014 (English)In: Natural interaction with robots, knowbots and smartphones, Springer-Verlag , 2014, p. 59-67Chapter in book (Refereed)
Abstract [en]

Recently there has been an interest in spatially aware systems for pedestrian routing and city exploration, due to the proliferation of smartphones with GPS receivers among the general public. Since GPS readings are noisy, giving good and well-timed route instructions to pedestrians is a challenging problem. This paper describes a spoken-dialogue prototype for pedestrian navigation in Stockholm that addresses this problem by using various grounding strategies.

Place, publisher, year, edition, pages
Springer-Verlag, 2014
National Category
Computer Sciences Language Technology (Computational Linguistics)
Identifiers
urn:nbn:se:kth:diva-158175 (URN)10.1007/978-1-4614-8280-2_6 (DOI)978-1-4614-8279-6 (ISBN)
Note

tmh_import_14_12_30, tmh_id_3954. QC 20150217

Available from: 2014-12-30 Created: 2014-12-30 Last updated: 2018-01-11Bibliographically approved
Götze, J. & Boye, J. (2013). Deriving Salience Models from Human Route Directions. In: Workshop on Computational Models of Spatial Language Interpretation and Generation 2013: (CoSLI-3). Paper presented at CoSLI-3: Workshop on Computational Models of Spatial Language Interpretation and Generation, Co-located with the 10th International Conference on Computational Semantics; Potsdam, Germany, March 19, 2013.
Open this publication in new window or tab >>Deriving Salience Models from Human Route Directions
2013 (English)In: Workshop on Computational Models of Spatial Language Interpretation and Generation 2013: (CoSLI-3), 2013Conference paper, Published paper (Refereed)
Abstract [en]

We present an approach to derive individual preferences in the use of landmarks for route instructions in a city environment. Each possible landmark that a person can refer to in a given situation is modelled as a feature vector, and the preference (or salience) associated with the landmark can be computed as a weighted sum of these features. The weight vector, representing the person's personal salience model, is automatically derived from the person's own route descriptions. Experiments show that the derived salience models can correctly predict the user's choice of landmark in 69% of the cases.

National Category
Language Technology (Computational Linguistics)
Identifiers
urn:nbn:se:kth:diva-136933 (URN)978-1-62748-401-5 (ISBN)
Conference
CoSLI-3: Workshop on Computational Models of Spatial Language Interpretation and Generation, Co-located with the 10th International Conference on Computational Semantics; Potsdam, Germany, March 19, 2013
Note

QC 20140124

Available from: 2013-12-09 Created: 2013-12-09 Last updated: 2018-01-11Bibliographically approved
Oertel, C., Salvi, G., Götze, J., Edlund, J., Gustafson, J. & Heldner, M. (2013). The KTH Games Corpora: How to Catch a Werewolf. In: IVA 2013 Workshop Multimodal Corpora: Beyond Audio and Video: MMC 2013. Paper presented at IVA 2013 Workshop Multimodal Corpora: Beyond Audio and Video - MMC 2013; Edinburgh, UK, 1 September 2013.
Open this publication in new window or tab >>The KTH Games Corpora: How to Catch a Werewolf
Show others...
2013 (English)In: IVA 2013 Workshop Multimodal Corpora: Beyond Audio and Video: MMC 2013, 2013Conference paper, Published paper (Refereed)
National Category
Computer Sciences Language Technology (Computational Linguistics)
Identifiers
urn:nbn:se:kth:diva-137399 (URN)
Conference
IVA 2013 Workshop Multimodal Corpora: Beyond Audio and Video - MMC 2013; Edinburgh, UK, 1 September 2013
Note

QC 20140623

tmh_import_13_12_13, tmh_id_3871

Available from: 2013-12-13 Created: 2013-12-13 Last updated: 2018-01-11Bibliographically approved
Organisations
Identifiers
ORCID iD: ORCID iD iconorcid.org/0000-0002-7829-5561

Search in DiVA

Show all publications