In this paper, we propose a Global Navigation Satellite System (GNSS) component activation model for mobile tracking devices that automatically detects indoor/outdoor environments using the radio signals received from Long-Term Evolution (LTE) base stations. We use an Inductive System Monitoring (ISM) technique to model environmental scenarios captured by a smart tracker via extracting clusters of corresponding value ranges from LTE base stations’ signal strength. The ISM-based model is built by using the tracker’s historical data labeled with GPS coordinates. The built model is further refined by applying it to additional data without GPS location collected by the same device. This procedure allows us to identify the clusters that describe semi-outdoor scenarios. In that way, the model discriminates between two outdoor environmental categories: open outdoor and semi-outdoor. The proposed ISM-based GNSS activation approach is studied and evaluated on a real-world dataset contains radio signal measurements collected by five smart trackers and their geographical location in various environmental scenarios.

This position paper describes the aims and preliminary results of the Distributed and Adaptive Edge-based AI Models for Sensor Networks (DAISeN) 1 project.The project ambition is to address today's edge AI challenges by developing advanced AI techniques that model knowledge from the sensor network and the environment to support the deployment of sustainable AI applications.We present one of the use cases being considered in DAISeN and review the state-of-the-art in three research domains related to the use case presented and directly falling into the project scope.We additionally outline the main challenges identified in each domain.The developed Global Navigation Satellite Systems (GNSS) activation model addressing the use case challenges is also briefly introduced.The future research studies planned for the remaining period of the project are finally outlined.

Recent advances in sensor technology are expected to lead to a greater use of wireless sensor networks (WSNs) in industry, logistics, healthcare, etc. On the other hand, advances in artificial intelligence (AI), machine learning (ML), and deep learning (DL) are becoming dominant solutions for processing large amounts of data from edge-synthesized heterogeneous sensors and drawing accurate conclusions with better understanding of the situation. Integration of the two areas WSN and AI has resulted in more accurate measurements, context-aware analysis and prediction useful for smart sensing applications. In this paper, a comprehensive overview of the latest developments in context-aware intelligent systems using sensor technology is provided. In addition, it also discusses the areas in which they are used, related challenges, motivations for adopting AI solutions, focusing on edge computing, i.e., sensor and AI techniques, along with analysis of existing research gaps. Another contribution of this study is the use of a semantic-aware approach to extract survey-relevant subjects. The latter specifically identifies eleven main research topics supported by the articles included in the work. These are analyzed from various angles to answer five main research questions. Finally, potential future research directions are also discussed.

Deep neural networks for positioning can improve accuracy by adapting to inhomogeneous environments. However, they are still susceptible to noisy data, often resulting in invalid positions. A related task, map matching, can be used for reducing geographical invalid positions by aligning observations to a model of the real world. In this paper, we propose an approach for positioning, enhanced with map matching, within a single deep neural network model. We introduce a novel way of reducing the number of invalid position estimates by adding map information to the input of the model and using a map-based loss function. Evaluating on real-world Received Signal Strength Indicator data from an asset tracking application, we show that our approach gives both increased position accuracy and a decrease of one order of magnitude in the number of invalid positions.

In this paper, we investigate the annotation projection of semantic units in a practical setting. Previous approaches have focused on using parallel corpora for semantic transfer. We evaluate an alternative approach using loosely parallel corpora that does not require the corpora to be exact translations of each other. We developed a method that transfers semantic annotations from one language to another using sentences aligned by entities, and we extended it to include alignments by entity-like linguistic units. We conducted our experiments on a large scale using the English, Swedish, and French language editions of Wikipedia. Our results show that the annotationprojectionusingentitiesincombinationwithlooselyparallelcorporaprovidesaviable approach to extending previous attempts. In addition, it allows the generation of proposition banks upon which semantic parsers can be trained. (Less)

This thesis explores methods for generating proposition databases in a large-scale and multilingual setting. Our methods are centered on using semantic role labeling for extracting predicate-argument structures, and the subsequent transformation of such structures for knowledge base population and generation. By extending semantic role labeling with entity detection, we demonstrate how predicate-argument structures can be transformed to represent real world concepts and also act as a bridge connecting relational facts in multiple languages.We introduce a framework, KOSHIK, for large scale extraction of propositions from unstructured text and an annotation model for the incremental addition of annotation layers. In addition, we introduce an alignment method based on entities for aligning disparate ontologies and also for generating ontologies for new proposition databases. Using KOSHIK, we perform large-scale natural language processing of the entire English, Swedish, and French editions of Wikipedia. By transforming the structures extracted from Wikipedias, we extend existing knowledge bases in addition to generating new proposition databases. We demonstrate how generated proposition databases in Swedish and French can be used to effectively train semantic role labelers. (Less)

In this article, we describe a system that classifies relations between entities extracted from an image. We started from the idea that we could utilize lexical and semantic information from text associated with the image, such as captions or surrounding text, rather than just the geometric and visual characteristics of the entities found in the image. We collected a corpus of images from Wikipedia together with their corresponding articles. In our experimental setup, we extracted two kinds of entities from the images, human beings and horses, and we defined three relations that could exist between them: Ride, Lead, or None. We used geometric features as a baseline to identify the relations between the entities and we describe the improvements brought by the addition of bag-of-word features and predicate–argument structures that we extracted from the text. The best semantic model resulted in a relative error reduction of more than 18

The concept of culturomics was born out of the availability of massive amounts of textual data and the interest to make sense of cultural and language phenomena over time. Thus far however, culturomics has only made use of, and shown the great potential of, statistical methods. In this paper, we present a vision for a knowledge-based culturomics that complements traditional culturomics. We discuss the possibilities and challenges of combining knowledge-based methods with statistical methods and address major challenges that arise due to the nature of the data; diversity of sources, changes in language over time as well as temporal dynamics of information in general. We address all layers needed for knowledge-based culturomics, from natural language processing and relations to summaries and opinions.

Semantic role labeling has become a key module for many language processing applications such as question answering, information extraction, sentiment analysis, and machine translation.To build an unrestricted semantic role labeler, the first step is to develop a comprehensive proposition bank.However, creating such a bank is a costly enterprise, which has only been achieved for a handful of languages.In this paper, we describe a technique to build proposition banks for new languages using distant supervision.Starting from PropBank in English and loosely parallel corpora such as versions of Wikipedia in different languages, we carried out a mapping of semantic propositions we extracted from English to syntactic structures in Swedish using named entities.We trained a semantic parser on the generated Swedish propositions and we report the results we obtained.Using the CoNLL 2009 evaluation script, we could reach the scores of 52.25 for labeled propositions and 62.44 for the unlabeled ones.We believe our approach can be applied to train semantic role labelers for other resource-scarce languages.

The extraction of semantic propositions has proven instrumental in applications like IBM Watson (Ferrucci, 2012) and in Google's knowledge graph (Singhal, 2012). One of the core components of IBM Watson is the PRISMATIC knowledge base consisting of one billion propositions extracted from the English version of Wikipedia and the New York Times (Fan et al., 2010). However, extracting the propositions from the English version of Wikipedia is a time-consuming process. In practice, this task requires multiple machines and a computation distribution involving a good deal of system technicalities. In this paper, we describe REFRACTIVE, an open-source tool to extract propositions from a parsed corpus based on the Hadoop variant of MapReduce. While the complete process consists of a parsing part and an extraction part, we focus here on the extraction from the parsed corpus and we hope this tool will help computational linguists speed up the development of applications.

Semantic role labeling has become a key module of many language processing applications. To build an unrestricted semantic role labeler, the first step is to develop a comprehensive proposition bank. However, building such a bank is a costly enterprise, which has only been achieved for a handful of languages. In this paper, we describe a technique to build proposition banks for new languages using distant supervision. Starting from PropBank in English and loosely parallel corpora such as versions of Wikipedia in different languages, we carried out a mapping of semantic propositions we extracted from English to syntactic structures in Swedish using named entities. We could identify 2,333 predicate–argument frames in Swedish. (Less)

In this paper, we describe a novel system that identifies relations between the objects extracted from an image. We started from the idea that in addition to the geometric and visual properties of the image objects, we could exploit lexical and semantic information from the text accompanying the image. As experimental set up, we gathered a corpus of images from Wikipedia as well as their associated articles. We extracted two types of objects: human beings and horses and we considered three relations that could hold between them: \textit{Ride}, \textit{Lead}, or \textit{None}. We used geometric features as a baseline to identify the relations between the entities and we describe the improvements brought by the addition of bag-of-word features and predicate--argument structures we derived from the text. The best semantic model resulted in a relative error reduction of more than 18\% over the baseline.

Most question answering systems feature a step to predict an expected answer type given a question. Li and Roth \cite{li2002learning} proposed an oft-cited taxonomy to the categorize the answer types as well as an annotated data set. While offering a framework compatible with supervised learning, this method builds on a fixed and rigid model that has to be updated when the question-answering domain changes. More recently, Pinchak and Lin \cite{pinchak2006} designed a dynamic method using a syntactic model of the answers that proved more versatile. They used syntactic dependencies to model the question context and evaluated the performance on an English corpus. However, syntactic properties may vary across languages and techniques applicable to English may fail with other languages. In this paper, we present a method for constructing a probability-based answer type model for each different question. We adapted and reproduced the original experiment of Pinchak and Lin \cite{pinchak2006} on a Chinese corpus and we extended their model to semantic dependencies. Our model evaluates the probability that a candidate answer fits into the semantic context of a given question. We carried out an evaluation on a set of questions either drawn from NTCIR corpus \cite{ntcir2005} or that we created manually.

In this paper, we describe KOSHIK, an end-to-end framework to process the unstructured natural language content of multilingual documents. We used the Hadoop distributed computing infrastructure to build this framework as it enables KOSHIK to easily scale by adding inexpensive commodity hardware. We designed an annotation model that allows the processing algorithms to incrementally add layers of annotation without modifying the original document. We used the Avro binary format to serialize the documents. Avro is designed for Hadoop and allows other data warehousing tools to directly query the documents. This paper reports the implementation choices and details of the framework, the annotation model, the options for querying processed data, and the parsing results on the English and Swedish editions of Wikipedia.

While many systems such as those from Seddiqui and Aono (2009) and Cruz et al. (2009) use combinations of terminological and structural methods, the use of extensional and semantic methods in systems such as the one by Jean-Mary et al. (2009) have been largely unexplored (Pavel and Euzenat, 2012). Similarly to these approaches, we use a combination of alignment methods to create mappings between PropBank (Palmer et al., 2005) predicates and DBpedia (Auer et al., 2007) properties. In particular, we identify predicate– argument structures from Wikipedia articles to extract triples and use a combination approach of extensional and semantical methods during the matching process to align the extracted triples with an exisiting DBpedia dataset.

With the advent of massive online encyclopedic corpora such as Wikipedia, it has become possible to apply a systematic analysis to a wide range of documents covering a significant part of human knowledge. Using semantic parsers, it has become possible to extract such knowledge in the form of propositions (predicate argument structures) and build large proposition databases from these documents. This paper describes the creation of multilingual proposition databases using generic semantic dependency parsing. Using Wikipedia, we extracted, processed, clustered, and evaluated a large number of propositions. We built an architecture to provide a complete pipeline dealing with the input of text, extraction of knowledge, storage, and presentation of the resulting propositions.

From metropolitan areas to tiny villages, there is a wide variety of organizers of cultural, business, entertainment, and social events. These organizers publish such information to an equally wide variety of sources. Every source of published events uses its own document structure and provides dierent sets of information. This raises signicant customization issues. This paper explores the possibilities of extracting future events from a wide range of web sources, to determine if the document structure and content can be exploited for time-ecient hyperlocal event scraping. We report on two experimental knowledge-driven, pattern-based programs that scrape events from web pages using both their content and structure.

In this paper, we describe an end-to-end system that automatically extracts RDF triples describing entity relations and properties from unstructured text. This system is based on a pipeline of text processing modules that includes a semantic parser and a coreference solver. By using coreference chains, we group entity actions and properties described in different sentences and convert them into entity triples. We applied our system to over 114,000 Wikipedia articles and we could extract more than 1,000,000 triples. Using an ontology-mapping system that we bootstrapped using existing DBpedia triples, we mapped 189,000 extracted triples onto the DBpedia namespace. These extracted entities are availableonline in the N-Triple format. 1 1 http://semantica.cs.lth.se/ (Less)

This paper describes the structure of the LTH coreference solver used in the closed track of the CoNLL 2012 shared task (Pradhan et al., 2012). The solver core is a mention classifier that uses Soon et al. (2001)'s algorithm and features extracted from the dependency graphs of the sentences. This system builds on Björkelund and Nugues (2011)'s solver that we extended so that it can be applied to the three languages of the task: English, Chinese, and Arabic. We designed a new mention detection module that removes pleonastic pronouns, prunes constituents, and recovers mentions when they do not match exactly a noun phrase. We carefully redesigned the features so that they reflect more complex linguistic phenomena as well as discourse properties. Finally, we introduced a minimal cluster model grounded in the first mention of an entity. We optimized the feature sets for the three languages: We carried out an extensive evaluation of pairs of features and we complemented the single features with associations that improved the CoNLL score. We obtained the respective scores of 59.57, 56.62, and 48.25 on English, Chinese, and Arabic on the development set, 59.36, 56.85, and 49.43 on the test set, and the combined official score of 55.21.

Although event models and corresponding RDF vocabularies are becoming available, the collection of events still requires an initial manual encoding to produce the data. In this paper, we describe a system based on semantic parsing (SRL) to collect automatically events from text and convert them into the LODE model. Furthermore, the system automatically links extracted event properties to the external resources DBpedia and GeoNames. We applied our system to 10% of the English Wikipedia and we evaluated its performance. We managed to extract 27,500 high-confidence event instances. Although SRL is not an error-free technique, we show that it is an effective tool, as the definition of the arguments (or roles) used in our analysis and the event properties are, most of the time, nearly identical. We evaluated the results on a randomly selected sample of 100 events and we report F-measures of up to 73. The extracted events are available online from a SPARQL endpoint1.