Infrastructure Engineering - Research Publications
Permanent URI for this collection
Search Results
1 - 8 of 8
-
ItemSpatial and Spatiotemporal Matching Framework for Causal Inference(Schloss Dagstuhl, 2022-09-01)Matching is a procedure aimed at reducing the impact of observational data bias in causal analysis. Designing matching methods for spatial data reflecting static spatial or dynamic spatio-temporal processes is complex because of the effects of spatial dependence and spatial heterogeneity. Both may be compounded with temporal lag in the dependency effects on the study units. Current matching techniques based on similarity indexes and pairing strategies need to be extended with optimal spatial matching procedures. Here, we propose a decision framework to support analysts through the choice of existing matching methods and anticipate the development of specialized matching methods for spatial data. This framework thus enables to identify knowledge gaps.
-
ItemMultiSpanQA: A Dataset for Multi-Span Question Answering(ASSOC COMPUTATIONAL LINGUISTICS-ACL, 2022)
-
ItemTranslating Place-Related Questions to GeoSPARQL Queries(ASSOC COMPUTING MACHINERY, 2022)Many place-related questions can only be answered by complex spatial reasoning, a task poorly supported by factoid question retrieval. Such reasoning using combinations of spatial and non-spatial criteria pertinent to place-related questions is increasingly possible on linked data knowledge bases. Yet, to enable question answering based on linked knowledge bases, natural language questions must first be re-formulated as formal queries. Here, we first present an enhanced version of YAGO2geo, the geospatially-enabled variant of the YAGO2 knowledge base, by linking and adding more than one million places from OpenStreetMap data to YAGO2. We then propose a novel approach to translate the place-related questions into logical representations, theoretically grounded in the core concepts of spatial information. Next, we use a dynamic template-based approach to generate fully executable GeoSPARQL queries from the logical representations. We test our approach using the Geospatial Gold Standard dataset and report substantial improvements over existing methods.
-
ItemTarget Word Masking for Location Metonymy Resolution(International Committee on Computational Linguistics, 2020)
-
ItemIndoor LiDAR relocalization based on deep learning using a 3D model(Copernicus GmBH, 2020-08-06)Indoor localization, navigation and mapping systems highly rely on the initial sensor pose information to achieve a high accuracy. Most existing indoor mapping and navigation systems cannot initialize the sensor poses automatically and consequently these systems cannot perform relocalization and recover from a pose estimation failure. For most indoor environments, a map or a 3D model is often available, and can provide useful information for relocalization. This paper presents a novel relocalization method for LiDAR sensors in indoor environments to estimate the initial LiDAR pose using a CNN pose regression network trained using a 3D model. A set of synthetic LiDAR frames are generated from the 3D model with known poses. Each LiDAR range image is a one-channel range image, used to train the CNN pose regression network from scratch to predict the initial sensor location and orientation. The CNN regression network trained by synthetic range images is used to estimate the poses of the LiDAR using real range images captured in the indoor environment. The results show that the proposed CNN regression network can learn from synthetic LiDAR data and estimate the pose of real LiDAR data with an accuracy of 1.9 m and 8.7 degrees.
-
ItemPlace questions and human-generated answers: A data analysis approach(Springer, Cham, 2020-01-01)This paper investigates place-related questions submitted to search systems and their human-generated answers. Place-based search is motivated by the need to identify places matching some criteria, to identify them in space or relative to other places, or to characterize the qualities of such places. Human place-related questions have thus far been insufficiently studied and differ strongly from typical keyword queries. They thus challenge today’s search engines providing only rudimentary geographic information retrieval support. We undertake an analysis of the patterns in place-based questions using a large-scale dataset of questions/answers, MS MARCO V2.1. The results of this study reveal patterns that can inform the design of conversational search systems and in-situ assistance systems, such as autonomous vehicles.
-
ItemInitial Analysis of Simple Where-Questions and Human-Generated Answers(LIPIcs, 2019)Geographic questions are among the most frequently asked questions in Web search and question answering systems. While currently responses to the questions are machine-generated by document/snippet retrieval, in the future these responses will need to become more similar to answers provided by humans. Here, we have analyzed human answering behavior as response to simple where questions (i.e., where questions formulated only with one toponym) in terms of type, scale, and prominence of the places referred to. We have used the largest available machine comprehension dataset, MS-MARCO v2.1. This study uses an automatic approach for extraction, encoding and analysis of the questions and answers. Here, the distribution analysis are used to describe the relation between questions and their answers. The results of this study can inform the design of automatic question answering systems for generating useful responses to where questions.
-
ItemConsiderations for Efficient Communication of Route Directions( 2006)We can observe that people familiar with an environment give route directions of varying granularity to other locals. Such route directions are typically shorter than the turn based directions of current navigation services, and contain only references of high relevance to the wayfinder. Studying these route directions of varying granularity reveals that they are intended to be memorized, a property that requires a low cognitive workload of the wayfinder during their usage. The short-term memory span of humans imposes a limit on the amount and the structure of information communicated. We argue that route directions of varying granularity provide the means to respect these limits by efficient recoding.