Summary Generation for Toponym-referenced Images using Object Type Language Models
نویسندگان
چکیده
This paper presents a novel approach to automatic captioning of toponym-referenced images. The automatic captioning procedure works by summarizing multiple web-documents that contain information related to an image’s location. Our summarizer can generate both query-based and language model-biased multidocument summaries. The models are created from large numbers of existing articles pertaining to places of the same “object type”. Evaluation relative to human written captions shows that when language models are used to bias the summarizer the summaries score more highly than the non-biased ones.
منابع مشابه
Gazetteer-Independent Toponym Resolution Using Geographic Word Profiles
Toponym resolution, or grounding names of places to their actual locations, is an important problem in analysis of both historical corpora and present-day news and web content. Recent approaches have shifted from rule-based spatial minimization methods to machine learned classifiers that use features of the text surrounding a toponym. Such methods have been shown to be highly effective, but the...
متن کاملModeling and Evaluation of Stochastic Discrete-Event Systems with RayLang Formalism
In recent years, formal methods have been used as an important tool for performance evaluation and verification of a wide range of systems. In the view points of engineers and practitioners, however, there are still some major difficulties in using formal methods. In this paper, we introduce a new formal modeling language to fill the gaps between object-oriented programming languages (OOPLs) us...
متن کاملModeling and Evaluation of Stochastic Discrete-Event Systems with RayLang Formalism
In recent years, formal methods have been used as an important tool for performance evaluation and verification of a wide range of systems. In the view points of engineers and practitioners, however, there are still some major difficulties in using formal methods. In this paper, we introduce a new formal modeling language to fill the gaps between object-oriented programming languages (OOPLs) us...
متن کاملConnecting Language and Geography with Region-Topic Models
We describe an approach for connecting language and geography that anchors natural language expressions to specific regions of the Earth, implemented in our TextGrounder system. The core of the system is a region-topic model, which we use to learn word distributions for each region discussed in a given corpus. This model performs toponym resolution as a by-product, and additionally enables us t...
متن کاملEntity type modeling for multi-document summarization : generating descriptive summaries of geo-located entities
In this work we investigate the application of entity type models in extractive multi-document summarization using the automatic caption generation for images of geo-located entities (e.g. Westminster Abbey, Loch Ness, Eiffel Tower) as an application scenario. Entity type models contain sets of patterns aiming to capture the ways the geo-located entities are described in natural language. They ...
متن کامل