Publikationsliste

This paper deals with aspect phrase extraction and classification in sentiment analysis. We summarize current approaches and datasets from the domain of aspect-based sentiment analysis. This domain detects sentiments expressed for individual aspects in unstructured text data. So far, mainly commercial user reviews for products or services such as restaurants were investigated. We here present our dataset consisting of German physician reviews, a sensitive and linguistically complex field. Furthermore, we describe the annotation process of a dataset for supervised learning with neural networks. Moreover, we introduce our model for extracting and classifying aspect phrases in one step, which obtains an F1-score of 80%. By applying it to a more complex domain, our approach and results outperform previous approaches.

When it comes to increased digitization in the health care domain, privacy is a relevant topic nowadays. This relates to patient data, electronic health records or physician reviews published online, for instance. There exist different approaches to the protection of individuals’ privacy, which focus on the anonymization and masking of personal information subsequent to their mining. In the medical domain in particular, measures to protect the privacy of patients are of high importance due to the amount of sensitive data that is involved (e.g. age, gender, illnesses, medication). While privacy breaches in structured data can be detected more easily, disclosure in written texts is more difficult to find automatically due to the unstructured nature of natural language. Therefore, we take a detailed look at existing research on areas related to privacy protection. Likewise, we review approaches to the automatic detection of privacy disclosure in different types of medical data. We provide a survey of several studies concerned with privacy breaches in the medical domain with a focus on Physician Review Websites (PRWs). Finally, we briefly develop implications and directions for further research.

This paper deals with online customer reviews of local multi-service providers. While many studies investigate product reviews and online labour markets with service providers delivering intangible products “over the wire”, we focus on websites where providers offer multiple distinct services that can be booked, paid and reviewed online but are performed locally offline. This type of service providers has so far been neglected in the literature. This paper analyses reviews and applies sentiment analysis. It aims to gain new insights into local multi-service providers’ performance. There is a broad literature range presented with regard to the topics addressed. The results show, among other things, that providers with good ratings continue to perform well over time. We find that many positive reviews seem to encourage sales. On average, quantitative star ratings and qualitative ratings in the form of review texts match. Further results are also achieved in this study.

The ability to openly evaluate products, locations and services is an achievement of the Web 2.0. It has never been easier to inform oneself about the quality of products or services and possible alternatives. Forming one’s own opinion based on the impressions of other people can lead to better experiences. However, this presupposes trust in one’s fellows as well as in the quality of the review platforms. In previous work on physician reviews and the corresponding websites, it was observed that there occurs faulty behavior by some reviewers and there were noteworthy differences in the technical implementation of the portals and in the efforts of site operators to maintain high quality reviews. These experiences raise new questions regarding what trust means on review platforms, how trust arises and how easily it can be destroyed.

This paper presents the various sources of uncertainty we encounter in our project. Our research focus lies on the investigation of language elaboration processes in Middle Low German. We are particularly interested in diachronic constructional changes and constructionalizations involving and affecting all linguistic dimensions. For this, it is necessary to annotate our corpus with Part-of-Speech and constructional tags. Here, we are confronted with gradualness, gradience, and ambiguity as potential sources of uncertainty that complicate the annotation process. Furthermore, due to the historicity of the investigated language, we expect cases of incomplete knowledge and comparative fallacy from the annotators. For this reason, we develop an interface that captures all annotators’ doubts.

As our world grows in complexity, companies and employees alike need, more than ever before, solutions tailored to their exact needs. Since such tools cannot always be purchased off-the-shelf and need to be designed from the ground up, developers rely on software requirements. In this paper, we present our vision of a syntactic rule-based extraction tool for software requirements specification documents. In contrast to other methods, our tool will allow stakeholders to express their needs and wishes in unfiltered natural language, which we believe is essential for non-expert users.

Natural language requirement descriptions are often unstructured, contradictory and incomplete and are therefore challenging for automatic processing. Although many of these deficits can be compensated by means of Natural Language Processing, there still remain cases where interaction with end-users is necessary for clarification. In this paper, we present our idea of using chatbot technology to establish end-user communication in order to support the automatic compensation of some deficits in natural language requirement descriptions.

Natural language software requirements descriptions enable end users to formulate their wishes and expectations for a future software product without much prior knowledge in requirements engineering. However, these descriptions are susceptible to linguistic inaccuracies such as ambiguities and incompleteness that can harm the development process. There is a number of software solutions that can detect deficits in requirements descriptions and partially solve them, but they are often hard to use and not suitable for end users. For this reason, we develop a software system that helps end-users to create unambiguous and complete requirements descriptions by combining existing expert tools and controlling them using automatic compensation strategies. In order to recognize the necessity of individual compensation methods in the descriptions, we have developed linguistic indicators, which we present in this paper. Based on these indicators, the whole text analysis pipeline is ad-hoc configured and thus adapted to the individual circumstances of a requirements description.

The main idea in On-The-Fly Computing is to automatically compose existing software services according to the wishes of end-users. However, since user requirements are often ambiguous, vague and incomplete, the selection and composition of suitable software services is a challanging task. In this paper, we present our current approach to improve requirement descriptions before they are used for software composition. This procedure is fully automated, but also has limitations, for example, if necessary information is missing. In addition, and in response to the limitations, we provide insights into our above-mentioned current work that combines the existing optimization approach with a chatbot solution.

On-The-Fly Computing is the vision of covering software needs of end users by fully-automatic compositions of existing software services. End users will receive so-called service compositions tailored to their very individual needs, based on natural language software descriptions. This everyday language may contain inaccuracies and incompleteness, which are well-known challenges in requirements engineering. In addition to existing approaches that try to automatically identify and correct these deficits, there are also new trends to involve users more in the elaboration and refinement process. In this paper, we present the relevant state of the art in the field of automated detection and compensation of multiple inaccuracies in natural language service descriptions and name open challenges needed to be tackled in NL-based software service composition.

Physician Review Websites allow users to evaluate their experiences with health services. As these evaluations are regularly contextualized with facts from users’ private lives, they often accidentally disclose personal information on the Web. This poses a serious threat to users’ privacy. In this paper, we report on early work in progress on “Text Broom”, a tool to detect privacy breaches in user-generated texts. For this purpose, we conceptualize a pipeline which combines methods of Natural Language Processing such as Named Entity Recognition, linguistic patterns and domain-specific Machine Learning approaches which have the potential to recognize privacy violations with wide coverage. A prototypical web application is openly accesible.

In this paper, we present the annotation challenges we have encountered when working on a historical language that was undergoing elaboration processes. We especially focus on syntactic ambiguity and gradience in Middle Low German, which causes uncertainty to some extent. Since current annotation tools consider construction contexts and the dynamics of the grammaticalization only partially, we plan to extend CorA – a web-based annotation tool for historical and other non-standard language data – to capture elaboration phenomena and annotator unsureness. Moreover, we seek to interactively learn morphological as well as syntactic annotations.

Bridging the gap between informal, imprecise, and vague user requirements descriptions and precise formalized specifications is the main task of requirements engineering. Techniques such as interviews or story telling are used when requirements engineers try to identify a user's needs. The requirements specification process is typically done in a dialogue between users, domain experts, and requirements engineers. In our research, we aim at automating the specification of requirements. The idea is to distinguish between untrained users and trained users, and to exploit domain knowledge learned from previous runs of our system. We let untrained users provide unstructured natural language descriptions, while we allow trained users to provide examples of behavioral descriptions. In both cases, our goal is to synthesize formal requirements models similar to statecharts. From requirements specification processes with trained users, behavioral ontologies are learned which are later used to support the requirements specification process for untrained users. Our research method is original in combining natural language processing and search-based techniques for the synthesis of requirements specifications. Our work is embedded in a larger project that aims at automating the whole software development and deployment process in envisioned future software service markets.

In this paper, we present an IoT architecture which handles stream sensor data of air pollution. Particle pollution is known as a serious threat to human health. Along with developments in the use of wireless sensors and the IoT, we propose an architecture that flexibly measures and processes stream data collected in real-time by movable and low-cost IoT sensors. Thus, it enables a wide-spread network of wireless sensors that can follow changes in human behavior. Apart from stating reasons for the need of such a development and its requirements, we provide a conceptual design as well as a technological design of such an architecture. The technological design consists of Kaa and Apache Storm which can collect air pollution information in real-time and solve various problems to process data such as missing data and synchronization. This enables us to add a simulation in which we provide issues that might come up when having our architecture in use. Together with these issues, we state r easons for choosing specific modules among candidates. Our architecture combines wireless sensors with the Kaa IoT framework, an Apache Kafka pipeline and an Apache Storm Data Stream Management System among others. We even provide open-government data sets that are freely available.

Users prefer natural language software requirements because of their usability and accessibility. Many approaches exist to elaborate these requirements and to support the users during the elicitation process. But there is a lack of adequate resources, which are needed to train and evaluate approaches for requirement refinement. We are trying to close this gap by using online available software descriptions from SourceForge and app stores. Thus, we present two real-life requirements collections based on online-available software descriptions. Our goal is to show the domain-specific characteristics of content words describing functional requirements. On the one hand, we created a semantic role-labeled requirements set, which we use for requirements classification. On the other hand, we enriched software descriptions with linguistic features and dependencies to provide evidence for the context-awareness of software functionalities.

One purpose of requirement refinement is that higher-level requirements have to be translated to something usable by developers. Since customer requirements are often written in natural language by end users, they lack precision, completeness and consistency. Although user stories are often used in the requirement elicitation process in order to describe the possibilities how to interact with the software, there is always something unspoken. Here, we present techniques how to automatically refine vague software descriptions. Thus, we can bridge the gap by first revising natural language utterances from higher-level to more detailed customer requirements, before functionality matters. We therefore focus on the resolution of semantically incomplete user-generated sentences (i.e. non-instantiated arguments of predicates) and provide ontology-based gap-filling suggestions how to complete unverbalized information in the user’s demand.

Users prefer natural language software requirements because of their usability and accessibility. When they describe their wishes for software development, they often provide off-topic information. We therefore present an automated approach for identifying and semantically annotating the on-topic parts of the given descriptions. It is designed to support requirement engineers in the requirement elicitation process on detecting and analyzing requirements in user-generated content. Since no lexical resources with domain-specific information about requirements are available, we created a corpus of requirements written in controlled language by instructed users and uncontrolled language by uninstructed users. We annotated these requirements regarding predicate-argument structures, conditions, priorities, motivations and semantic roles and used this information to train classifiers for information extraction purposes. The approach achieves an accuracy of 92% for the on- and off-topic classification task and an F1-measure of 72% for the semantic annotation.

While requirements focus on how the user interacts with the system, user stories concentrate on the purpose of software features. But in practice, functional requirements are also described in user stories. For this reason, requirements clarification is needed, especially when they are written in natural language and do not stick to any templates (e.g., "as an X, I want Y so that Z ..."). However, there is a lot of implicit knowledge that is not expressed in words. As a result, natural language requirements descriptions may suffer from incompleteness. Existing approaches try to formalize natural language or focus only on entirely missing and not on deficient requirements. In this paper, we therefore present an approach to detect knowledge gaps in user-generated software requirements for interactive requirement clarification: We provide tailored suggestions to the users in order to get more precise descriptions. For this purpose, we identify not fully instantiated predicate argument structures in requirements written in natural language and use context information to realize what was meant by the user.

Welche Informationen über Unternehmenszusammenschlüsse werden in Zeitungsnachrichten vermittelt, und wie können diese Informationen automatisch extrahiert werden? Dies soll am Beispiel des Verhaltens von Aktionären während eines Zusammenschlusses ermittelt werden. Dazu werden die wichtigsten Aussagen über das Votum der Aktionäre im Hinblick auf eine automatische Erkennung sprachlich analysiert. Im Fokus stehen dabei die Berichte über Aktionärsabstimmungen hinsichtlich der Annahme bzw. Ablehnung eines Übernahmeangebots.

Received medical services are increasingly discussed and recommended on physician rating websites (PRWs). The reviews and ratings on these platforms are valuable sources of information for patient opinion mining. In this paper, we have tackled three issues that come along with inconsistency analysis on PRWs: (1) Natural language processing of user-generated reviews, (2) the disagreement in polarity of review text and its corresponding numerical ratings (individual inconsistency) and (3) the differences in patients’ rating behavior for the same service category (e.g. ‘treatment’) expressed by varying grades on the entire data set (collective inconsistency). Thus, the basic idea is first to identify relevant opinion phrases that describe service categories and to determine their polarity. Subsequently, the particular phrase has to be assigned to its corresponding numerical rating category before checking the (dis-)agreement of polarity values. For this purpose, several local grammars for the pattern-based analysis as well as domain-specific dictionaries for the recognition of entities, aspects and polarity were applied on 593,633 physician reviews from both German PRWs jameda.de and docinsider.de. Furthermore, our research contributes to content quality improvement of PRWs because we provide a technique to detect inconsistent reviews that could be ignored for the computation of average ratings.

The individual search for information about physicians on Web 2.0 platforms can affect almost all aspects of our lives. People can directly access physician rating websites via web browsers or use any search engine to find physician reviews and ratings filtered by location resp. specialty. However, sometimes keyword search does not meet user needs because of the disagreement of users’ common terms queries for symptoms and the widespread medical terminology. In this paper, we present the prototype of a specialised search engine that overcomes this by indexing user-generated content (i.e., review texts) for physician discovery and provides automatic suggestions as well as an appropriate visualisation. On the one hand, we consider the available numeric physician ratings as sorting criterion for the ranking of query results. Furthermore, we extended existing ranking algorithms with respect to domain-specific types and physicians ratings on the other hand. We gathered more than 860,000 review texts and collected more than 213,000 physician records. A random test shows that about 19.7% of 5,100 different words in total are health- related and partly belong to consumer health vocabularies. Our evaluation results show that the query results fit user's particular health issues when seeking for physicians.

Adopting the concept of “Local Grammars” (M. Gross), which were successfully applied in practice by (Geierhos, 2010) to biographical information extraction in English our project aims to detect, encode, and finally visualize relations between persons. Our corpus consists of the digitised biographical lexicon “Neue Deutsche Biographie (NDB)”, roughly 21.000 biographies in 25 volumes in print since 1953. We developed local grammars and suitable dictionaries to describe interpersonal relations and applied them to the corpus with Unitex 3.1. The local grammars were designed to integrate existing TEI-XML structures in the corpus. Using the ability of local grammars in Unitex to act as transducers we were able to produce XML-Tags and encode semantic information. Based on grammars for personal names and places we described interpersonal relations like to study, predecessors and successors as well as friends and circles. Afterwards we identified persons (as given in the authority file or index). Finally we displayed relations on our website in an interactive and dynamic way. Utilizing the Javascript library D3.js we represented named relations between identified individuals as ego centred network graphs.

Existing approaches towards service composition demand requirements of the customers in terms of service templates, service query profiles, or partial process models. However, addressed non-expert customers may be unable to fill-in the slots of service templates as requested or to describe, for example, pre- and postconditions, or even have difficulties in formalizing their requirements. Thus, our idea is to provide non-experts with suggestions how to complete or clarify their requirement descriptions written in natural language. Two main issues have to be tackled: (1) partial or full inability (incapacity) of non-experts to specify their requirements correctly in formal and precise ways, and (2) problems in text analysis due to fuzziness in natural language. We present ideas how to face these challenges by means of requirement disambiguation and completion. Therefore, we conduct ontology-based requirement extraction and similarity retrieval based on requirement descriptions that are gathered from App marketplaces. The innovative aspect of our work is that we support users without expert knowledge in writing their requirements by simultaneously resolving ambiguity, vagueness, and underspecification in natural language.

Customized planning, engineering and build-up of factory plants are very complex tasks, where project management contains lots of risks and uncertainties. Existing simulation techniques could help massively to evaluate these uncertainties and achieve improved and at least more robust plans during project management, but are typically not applied in industry, especially at SMEs (small and medium-sized enterprises). This paper presents some results of the joint research project simject of the Universities of Paderborn and Kassel, which aims at the development of a demonstrator for a simulation-based and logistic-integrated project planning and scheduling. Based on the researched state-of-the-art, requirements and a planning process are derived and described, as well as a draft of the current technical infrastructure of the intended modular prototype. First plug-ins for project simulation and multi-project optimization are implemented and already show possible benefits for the project management process.

In this paper, we focus on the acronym representation, the concept of abbreviation of major terminology. To this end, we try to find the most efficient method to disambiguate the sense of the acronym. Comparing the various feature types, we found that using single noun (NN) overwhelmingly outperformed noun phrase (NP) base. Moreover, the result also showed that collocation information (CL) was not efficient for enhancing performance considering a huge extra data processing. We expect to apply the open knowledge base Wikipedia to scholarly service to enhance the quality of the local knowledge base and to develop value-added services.

In this paper, we present a system which makes scientific data available following the linked open data principle using standards like RDF and URI as well as the popular D2R server (D2R) and the customizable D2RQ mapping language. Our scientific data sets include acronym data and expansions, as well as researcher data such as author name, affiliation, coauthors, and abstracts. The system can easily be extended to other records. Regarding this, a domain adaptation to patent mining seems possible. For this reason, obvious similarities and differences are presented here. The data set is collected from several different providers like publishing houses and digital libraries, which follow different standards in data format and structure. Most of them are not supporting semantic web technologies, but the legacy HTML standard. The integration of these large amounts of scientific data into the Semantic Web is challenging and it needs flexible data structures to access this information and interlink them. Based on these data sets, we will be able to derive a general technology trend as well as the individual research domain for each researcher. The goal of our Linked Open Data System for scientific data is to provide access to this data set for other researchers using the Web of Linked Data. Furthermore we implemented an application for visualization, which allows usto explorethe relations between single data sets.

In this paper, we describe our system developed for the GErman SenTiment AnaLysis shared Task (GESTALT) for participation in the Maintask 2: Subjective Phrase and Aspect Extraction from Product Reviews. We present a tool, which identifies subjective and aspect phrases in German product reviews. For the recognition of subjective phrases, we pursue a lexicon-based approach. For the extraction of aspect phrases from the reviews, we consider two possible ways: Besides the subjectivity and aspect look-up, we also implemented a method to establish which subjective phrase belongs to which aspect. The system achieves better results for the recognition of aspect phrases than for the subjective identification.

This paper focuses on the first step in combining prescriptive analytics with scenario techniques in order to provide strategicdevelopment after the useof InSciTe, a data prescriptive analytics application. InSciTe supports the improvement of researchers‘ individual performance by recommending new research directions. Standardized influential factors are presented as a foundation for automated scenario modelling such as the prototypical report generation function of InSciTe. Additionally, a use-case is shown which validatesthe potential of the standardized influential factors for raw scenario development.

Our purpose is to perform data record extraction from onlineevent calendars exploiting sublanguage and domain characteristics. We therefore use so-called domain-dependent data (D³) completely based on language-specific key expressions and HTML patterns to recognize every single event given on the investigated web page. One of the most remarkable advantages of our method is that it does not require any additional classification steps based on machine learning algorithms or keyword extraction methods; it is a so-called one-step mining technique. Moreover, another important criteria is that our system is robust to DOM and layout modifications made by web designers. Thus, preliminary experimental results are provided to demonstrate proof-of-concept of such an approach tested on websites in the German opera domain. Furthermore, we could show that our proposed technique outperforms other data record mining applications run on event sites.

The conceptual condensability of technical terms permits us to use them as effective queries to search scientific databases. However, authors often employ alternative expressions to represent the meanings of specific terms, in other words, Terminological Paraphrases (TPs) in the literature for certain reasons. In this paper, we propose an effective way to retrieve “de facto relevance documents” which only contain those TPs and cannot be searched by conventional models in an environment with only controlled vocabularies by adapting Predicate Argument Tuple (PAT). The experiment confirms that PAT-based document retrieval is an effective and promising method to search those kinds of documents and to improve terminology-based scientific information access models.

Within this paper, we will describe a new approach to customer interaction management by integrating social networking channels into existing business processes. Until now, contact center agents still read these messages and forward them to the persons in charge of customer’s in the company. But with the introduction of Web 2.0 and social networking clients are more likely to communicate with the companies via Facebook and Twitter instead of filling data in contact forms or sending e-mail requests. In order to maintain an active communication with international clients via social media, the multilingual consumer contacts have to be categorized and then automatically assigned to the corresponding business processes (e.g. technicalservice, shipping, marketing, and accounting). This allows the company to follow general trends in customer opinions on the Internet, but also record two-sided communication for customer relationship management.

SCM is a simple, modular and flexible system for web monitoring and customer interaction management. In our view, its main advantages are the following: It is completely web based. It combines all technologies, data, software agents and human agents involved in the monitoring and customer interaction process. It can be used for messages written in any natural language. Although the prototype of SCM is designed for classifying and processing messages about mobile-phone related problems in social networks, SCM can easily be adapted to other text types such as discussion board posts, blogs or emails. Unlike comparable systems, SCM uses linguistic technologies to classify messages and recognize paraphrases of product names. For two reasons, product name paraphrasing plays a major role in SCM: First, product names typically have many, sometimes hundreds or thousands of intralingual paraphrases. Secondly, product names have interlingual paraphrases: The same products are often called or spelt differently in different countries and/or languages. By mapping product name variants to an international canonical form, SCM allows for answering questions like Which statements are made about this mobile phone in which languages/in which social networks/in which countries/...? The SCM product name paraphrasing engine is designed in such a way that standard variants are assigned automatically, regular variants are assigned semiautomatically and idiosyncratic variants can be added manually. With this and similar features we try to realize our philosophy of simplicity, modularity and flexibility: Whatever can be done automatically is done automatically. But manual intervention is always possible and easy and it does not conflict in any way with the automatic functions of SCM.

Within this paper, we describe the special requirements of a semantic annotation scheme used for biographical event extraction in the framework of the Europeancollaborative research project Biographe. This annotationscheme supports interlingual search for people due to its multilingual support covering four languages such as English, German, French and Dutch.

This paper presents a system that uses the domain name of a German business website to locate its information pages (e.g. company profile, contact page, imprint) and then identifies business specific information. We therefore concentrate on the extraction of characteristic vocabulary like company names, addresses, contact details, CEOs, etc. Above all, we interpret the HTML structure of documents and analyze some contextual facts to transform the unstructured web pages into structured forms. Our approach is quite robust in variability of the DOM, upgradeable and keeps data up-to-date. The evaluation experiments show high efficiency of information access to the generated data. Hence, the developed technique is adaptive to non-German websites with slight language-specific modifications, and experimental results on real-life websites confirm the feasibility of the approach.

This paper presents an approach to extract data records from websites, particularly ones with event calendars. We therefore use language-specific key expressions and HTML patterns to recognize every single event given on the investigated web page. One of the most remarkable advantages of our method is that it does not require any additional classification steps based on machine learning algorithms or keyword extraction methods; it is a so-called one-step mining technique. Our experimental results obtained on German opera websites show excellent results in precision and recall. Furthermore, we could demonstrate that our proposed technique outperforms other data record mining applications run on event sites.

Ce papier présente le contexte linguistique et la modélisation de notre système iBeCOOL (Informations Biographiques Extraites à l’aide de COntextes Observés Linguistiquement) dédié à l’extraction d’informations biographiques dans les textes de la presse financière en langue anglaise. La notion d’événement biographique (tel que la naissance, le mariage, la carrière professionnelle) est caractérisée formellement par un schéma prédicatif à plusieurs arguments dont l’un étant une instance de la classe d’objets <Personne>. Notre approche consiste à décrire ces types de relations à l’aide de grammaires locales etde lexiques terminologiques. Nos résultats montrent que cette approche semble viable et nous poussent à élargir cette étude par l’analyse de nouveaux genres textuels.

Dieser Beitrag beschäftigt sich mit der Informationsextraktion aus Stellenanzeigen im französischsprachigen Web. Ziel dieser Arbeit ist es, unstrukturierte Dokumente in Repräasentationsvektoren anhand lokaler Grammatiken zu transformieren. Auf diese Weise wird es möglich, den Stellenmarkt für Jobsuchmaschinen transparenter zu gestalten, indem nur auf dem Inhalt der Anzeige in Form von Darstellungsvektoren anstatt auf unübersichtlichem Fließtext gesucht werden muss.