Toponym Disambiguation Using Events

نویسندگان

  • Kirk Roberts
  • Cosmin Adrian Bejan
  • Sanda M. Harabagiu
چکیده

Spatial information that grounds events geographically is often ambiguous, mainly because the same location name can be used in different states, countries, or continents. Spatial mentions, known as toponyms, must be disambiguated in order to understand many spatial relations within a document. Previous methods have utilized both “flat” and ontologybased ranking techniques to identify the correct reference. We argue that the use of location ontologies alone is not sufficient. Since toponyms are used in documents that refer to events grounded geographically, additional pragmatic knowledge can thus be used. To be able to identify the correct reference we enhanced ontology-based methods previously reported with techniques that consider the participants in events including people, organizations, and locations. Disambiguating geographical names over an ontology is cast as a probabilistic problem resolved by logistic regression. Our experimental results on the SpatialML corpus (Mani et al. 2008) indicate that event structures do indeed play an important role in understanding toponyms.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

A Hybrid Approach for Robust Multilingual Toponym Extraction and Disambiguation

Toponym extraction and disambiguation are key topics recently addressed by fields of Information Extraction and Geographical Information Retrieval. Toponym extraction and disambiguation are highly dependent processes. Not only toponym extraction effectiveness affects disambiguation, but also disambiguation results may help improving extraction accuracy. In this paper we propose a hybrid toponym...

متن کامل

Improving Toponym Extraction and Disambiguation Using Feedback Loop

This paper addresses two problems with toponym extraction and disambiguation. First, almost no existing works examine the extraction and disambiguation interdependency. Second, existing disambiguation techniques mostly take as input extracted toponyms without considering the uncertainty and imperfection of the extraction process. It is the aim of this paper to investigate both avenues and to sh...

متن کامل

Toponym Disambiguation by Arborescent Relationships

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 assign...

متن کامل

Toponym Extraction and Disambiguation Enhancement using Loops of Feedback

Toponym extraction and disambiguation have received much attention in recent years. Typical fields addressing these topics are information retrieval, natural language processing, and semantic web. This paper addresses two problems with toponym extraction and disambiguation. First, almost no existing works examine the extraction and disambiguation interdependency. Second, existing disambiguation...

متن کامل

Text-Driven Toponym Resolution using Indirect Supervision

Toponym resolvers identify the specific locations referred to by ambiguous placenames in text. Most resolvers are based on heuristics using spatial relationships between multiple toponyms in a document, or metadata such as population. This paper shows that text-driven disambiguation for toponyms is far more effective. We exploit document-level geotags to indirectly generate training instances f...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2010