Geographical information recognition and visualization in texts written in various languages

Pouliquen, Bruno; Steinberger, Ralf; Ignat, Camelia; Groeve, Tom De

doi:10.1145/967900.968115

Cited by 25 publications

(19 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For instance, assigning to the ambiguous toponym the referent with the largest population (Amitay et al, 2004;Pouliquen et al, 2004;Rauch et al, 2003) or choosing the most frequent referent, for example if the toponym to be resolved is Gaza, applying this heuristic, the referent "Gaza>Palestine" will be chosen instead of "Gaza>USA" because the former is the most known (Stokes et al, 2008).…”

Section: Introductionmentioning

confidence: 99%

“…There is also a similar method which seeks in the text the eventual mention of the root place (i.e., the referent's direct holonym). For example, searching Lebanon or Libya if the ambiguous toponym is Tripoli, this heuristic is used by Pouliquen et al (2004) and Li et al (2006). Smith and Crane (2001) proposed a heuristic that consists in calculating the geographical centroid of toponyms' candidate referents and then remove all referents located more than two standard deviations away from the center.…”

Section: Introductionmentioning

confidence: 99%

“…In the methods presented above, (Leidner et al, 2003;Smith and Crane, 2001) and (Rauch et al, 2003) suppose a distance proximity between the toponyms referents and (Clough, 2005;Pouliquen et al, 2004;Li et al, 2006) and (Buscaldi and Rosso, 2008a) assume a proximity in the hierarchical tree of world places, that we call arborescent proximity.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Toponym Disambiguation by Arborescent Relationships

Bensalem¹,

Kholladi²

2010

Journal of Computer Science

View full text Add to dashboard Cite

Problem statement:The way of referring to a place in the geographical space can be formal, based on the spatial coordinates, or informal, which we use in natural language by using toponyms (place names). A toponym can represent several geographical places. This ambiguity made problematic its conversion towards a unique formal representation. Toponym disambiguation in text is the task of assigning a unique location to an ambiguous place name in a given textual context. Approach: Several toponym disambiguation heuristics assumed a geographical proximity between the toponyms of the same context. This proximity can be in terms of spatial distance or in terms of arborsecent relationships, i.e., proximity in the hierarchical tree of the world places. This study presented a new toponym disambiguation heuristic in text based on the quantification of the arborescent proximity between toponyms. This quantification was done by a new measure of geographical correlation that we call the Geographical Density. Results: Our method was compared to the state of the art methods using GeoSemCor corpus and it has outperformed them in term of recall (87.4%) and coverage (99.0%). The results showed that the toponyms of the same context are much closer in terms of arborescent relationships than in terms of spatial relationships. Conclusion: We believe that the quantification of arborescent relationships between toponyms of the same textual context is a good way to improve the recall of TD task. However, all the arborescent relationships' types must be considered and not only the meronymy, which is the relation the most exploited in the existing TD methods.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Toponym Disambiguation by Arborescent Relationships

Bensalem¹,

Kholladi²

2010

Journal of Computer Science

View full text Add to dashboard Cite

show abstract

“…Using a gazetteer as a dictionary to look up road names, landmarks, and populated places should improve the performance [4]. However, in many cases the construction zone is bound by harder to define landmarks.…”

Section: Discussionmentioning

confidence: 99%

“…By grounding named entities to spatial locations, a system can answer spatial queries [3]. A geo-parser combines data from multilingual gazetteer with natural language text and a geographic information system to produce a map highlighting the locations mentioned in the text [4].…”

Section: Introductionmentioning

confidence: 99%

Road Segment Identification in Natural Language Text

Tawfik

Barsanti

IFIP International Federation for Information Processing

View full text Add to dashboard Cite

Abstract. This paper describes a technique to extract geographic location information from a natural language description of a location. The technique relies on a set of domain specific tags and a set of keywords. The tags are used to identify roads, intersections, and landmarks. Tag combinations are used to discover road segments. The technique is applied to understanding highway construction reports for the Canadian Province of Ontario.

show abstract

Technologies for Business Information Systems

Abramowicz¹,

Mayr²

2007

View full text Add to dashboard Cite

Geographical information recognition and visualization in texts written in various languages

Cited by 25 publications

References 7 publications

Toponym Disambiguation by Arborescent Relationships

Toponym Disambiguation by Arborescent Relationships

Road Segment Identification in Natural Language Text

Technologies for Business Information Systems

Contact Info

Product

Resources

About