Auflistung nach Schlagwort "Natural language processing"
1 - 10 von 12
Treffer pro Seite
Sortieroptionen
- ZeitschriftenartikelA Brief Tutorial on How to Extract Information from User-Generated Content (UGC)(KI - Künstliche Intelligenz: Vol. 27, No. 1, 2013) Egger, Marc; Lang, AndréIn this brief tutorial, we provide an overview of investigating text-based user-generated content for information that is relevant in the corporate context. We structure the overall process along three stages: collection, analysis, and visualization. Corresponding to the stages we outline challenges and basic techniques to extract information of different levels of granularity.
- ZeitschriftenartikelAn Interactive Narrative Format for Clinical Guidelines(KI - Künstliche Intelligenz: Vol. 29, No. 2, 2015) Cavazza, Marc; Charles, Fred; Lindsay, Alan; Siddle, Jonathan; Georg, GersendeClinical guidelines are standardised documents, which summarise best practice in complex medical situations. Their target audience comprises health professionals, or in some cases patient groups, for whom they constitute important sources of patient education. These documents are characterised by a rich knowledge content, which also relies on a complex, largely implicit background. At the heart of guidelines is a set of recommendations describing expected behaviour throughout specific, evolving contexts. Such complex documents can be challenging to assimilate, in particular their patient education versions. The need to contextualise information and visualise behaviours and their consequences suggests the use of virtual environments, as in serious gaming. However, knowledge representation in serious games are often limited and the overall implementation mainly empirical. On the other hand, interactive narratives technologies have demonstrated their ability to embed complex behavioural knowledge and support principled behaviour responding to dynamic contexts. This is why they support the exploration of complex situations, their rehearsal, and the understanding of expected behaviour through what-if interaction. The narrative perspective also provides better user guidance than a pure simulation system, allowing mixed-initiative access to information. The translation of medical protocols as interactive narratives is faced with a number of knowledge representation challenges, in particular for the representation of non-compli-ance and the consequences of incorrect behaviour. Another technical issue is the need to represent both common sense and domain knowledge, and articulate their representation with the Planning domain that forms the backbone of the interactive narrative. As part of the Open FET project MUSE (FP7-296703), we are developing a proof-of-concept prototype exploring the above aspects, and embedding the logical structure of guidelines into a real-time interactive narrative, which provides a principled simulation of the situations faced by patients, which preserves causal and deontic constraints. This paper describes the knowledge engineering process supporting the development of this prototype, from the analysis of patient guidelines to the use of planning representations supporting the interactive narrative.
- ZeitschriftenartikelChatbot – Der digitale Helfer im Unternehmen: Praxisbeispiele der Schweizerischen Post(HMD Praxis der Wirtschaftsinformatik: Vol. 55, No. 4, 2018) Stucki, Toni; D’Onofrio, Sara; Portmann, EdyChatbots gewinnen an Bedeutung. Sie ermöglichen uns Menschen, in natürlicher Sprache mit Computersystemen zu kommunizieren. Im einfachsten Fall extrahiert der Chatbot aus der Äusserung eines Benutzers dessen Intention, fragt fehlende Informationen in einer Wissensbank ab und bereitet dem Benutzer eine Antwort auf. Somit stellen Chatbots eine Schnittstelle zwischen Informationen und Nutzern dar. In einem Unternehmen können dadurch mehrere Vorteile generiert werden. Der Wissensfluss kann sowohl innerhalb des Unternehmens als auch in der Interaktion mit dem Kunden optimiert werden. Benutzer, seien es nun Mitarbeiter oder Kunden, erhalten von Chatbots schnell und in gleichbleibend hoher Qualität die gesuchten Informationen. Damit der menschliche Benutzer den sprechenden oder schreibenden Chatbot akzeptiert, sollte dieser angemessen kommunizieren. Was dies bedeutet, wie dies möglich wird und welche Potentiale Chatbots bieten, soll dieser Artikel anhand Praxisbeispielen der Schweizerischen Post diskutieren. Die kritische Reflexion der gewonnenen Erkenntnisse runden den Artikel ab. Chatbots are becoming increasingly important. They enable us humans to communicate with computer systems in natural language. In the simplest case, the chatbot extracts a user’s intention from his or her expression, asks for missing information in a knowledge base and prepares an answer for the user. Chatbots represent an interface between information and users. Several advantages can thus be generated in a company. The knowledge flow can be optimized within the company and in interaction with the customers. Users, whether they are employees or customers, quickly receive the information they are looking for from chatbots in consistently high quality. To accept the talking or writing chatbot, it should communicate appropriately. This article will discuss what this means, how this becomes possible and what potentials chatbots can offer, based on practical examples from Swiss Post. The article ends with a critical reflection on the lessons learned.
- ZeitschriftenartikelDesigning a Uniform Meaning Representation for Natural Language Processing(KI - Künstliche Intelligenz: Vol. 35, No. 0, 2021) Van Gysel, Jens E. L.; Vigus, Meagan; Chun, Jayeol; Lai, Kenneth; Moeller, Sarah; Yao, Jiarui; O’Gorman, Tim; Cowell, Andrew; Croft, William; Huang, Chu-Ren; Hajič, Jan; Martin, James H.; Oepen, Stephan; Palmer, Martha; Pustejovsky, James; Vallejos, Rosa; Xue, NianwenIn this paper we present Uniform Meaning Representation (UMR), a meaning representation designed to annotate the semantic content of a text. UMR is primarily based on Abstract Meaning Representation (AMR), an annotation framework initially designed for English, but also draws from other meaning representations. UMR extends AMR to other languages, particularly morphologically complex, low-resource languages. UMR also adds features to AMR that are critical to semantic interpretation and enhances AMR by proposing a companion document-level representation that captures linguistic phenomena such as coreference as well as temporal and modal dependencies that potentially go beyond sentence boundaries.
- ZeitschriftenartikelDissertation Abstract:Learning High Precision Lexical Inferences(KI - Künstliche Intelligenz: Vol. 35, No. 0, 2021) Shwartz, VeredThe fundamental goal of natural language processing is to build models capable of human-level understanding of natural language. One of the obstacles to building such models is lexical variability , i.e. the ability to express the same meaning in various ways. Existing text representations excel at capturing relatedness (e.g. blue / red ), but they lack the fine-grained distinction of the specific semantic relation between a pair of words. This article is a summary of a Ph.D. dissertation submitted to Bar-Ilan University in 2019, under the supervision of Professor Ido Dagan of the Computer Science Department. The dissertation explored methods for recognizing and extracting semantic relationships between concepts ( cat is a type of animal ), the constituents of noun compounds (baby oil is oil for babies), and verbal phrases (‘X died at Y’ means the same as ‘X lived until Y’ in certain contexts). The proposed models outperform highly competitive baselines and improve the state-of-the-art in several benchmarks. The dissertation concludes in discussing two challenges in the way of human-level language understanding: developing more accurate text representations and learning to read between the lines.
- ZeitschriftenartikelGrounding the Interaction: Knowledge Management for Interactive Robots(KI - Künstliche Intelligenz: Vol. 27, No. 2, 2013) Lemaignan, SéverinThe dissertation tackles the broad question of knowledge representation and manipulation for companion robots. It first builds a taxonomy of the knowledge manipulation skills required by service robots, then proposes a novel active knowledge base that integrates into large cognitive architectures, and finally explores several applications, including natural language grounding.
- ZeitschriftenartikelIntelligent User Assistance for Automated Data Mining Method Selection(Business & Information Systems Engineering: Vol. 62, No. 3, 2020) Zschech, Patrick; Horn, Richard; Höschele, Daniel; Janiesch, Christian; Heinrich, KaiIn any data science and analytics project, the task of mapping a domain-specific problem to an adequate set of data mining methods by experts of the field is a crucial step. However, these experts are not always available and data mining novices may be required to perform the task. While there are several research efforts for automated method selection as a means of support, only a few approaches consider the particularities of problems expressed in the natural and domain-specific language of the novice. The study proposes the design of an intelligent assistance system that takes problem descriptions articulated in natural language as an input and offers advice regarding the most suitable class of data mining methods. Following a design science research approach, the paper (i) outlines the problem setting with an exemplary scenario from industrial practice, (ii) derives design requirements, (iii) develops design principles and proposes design features, (iv) develops and implements the IT artifact using several methods such as embeddings, keyword extractions, topic models, and text classifiers, (v) demonstrates and evaluates the implemented prototype based on different classification pipelines, and (vi) discusses the results' practical and theoretical contributions. The best performing classification pipelines show high accuracies when applied to validation data and are capable of creating a suitable mapping that exceeds the performance of joint novice assessments and simpler means of text mining. The research provides a promising foundation for further enhancements, either as a stand-alone intelligent assistance system or as an add-on to already existing data science and analytics platforms.
- ZeitschriftenartikelInternet Corpora: A Challenge for Linguistic Processing(Datenbank-Spektrum: Vol. 15, No. 1, 2015) Horbach, Andrea; Thater, Stefan; Steffen, Diana; Fischer, Peter M.; Witt, Andreas; Pinkal, ManfredNatural language processing tools are mostly developed for and optimized on newspaper texts, and often show a substantial performance drop when applied to other types of texts such as Twitter feeds, chat data or Internet forum posts. We explore a range of easy-to-implement methods of adapting existing part-of-speech taggers to improve their performance on Internet texts. Our results show that these methods can improve tagger performance substantially.
- ZeitschriftenartikelOptimising crowdsourcing efficiency: Amplifying human computation with validation(it - Information Technology: Vol. 60, No. 1, 2018) Chamberlain, Jon; Kruschwitz, Udo; Poesio, MassimoCrowdsourcing has revolutionised the way tasks can be completed but the process is frequently inefficient, costing practitioners time and money. This research investigates whether crowdsourcing can be optimised with a validation process, as measured by four criteria: quality; cost; noise; and speed. A validation model is described, simulated and tested on real data from an online crowdsourcing game to collect data about human language. Results show that by adding an agreement validation (or a like/upvote) step fewer annotations are required, noise and collection time are reduced and quality may be improved.
- ZeitschriftenartikelSearch Challenges in Natural Language Generation with Complex Optimization Objectives(KI - Künstliche Intelligenz: Vol. 30, No. 1, 2016) Demberg, Vera; Hoffmann, Jörg; Howcroft, David M.; Klakow, Dietrich; Torralba, ÁlvaroAutomatic natural language generation (NLG) is a difficult problem already when merely trying to come up with natural-sounding utterances. Ubiquituous applications, in particular companion technologies, pose the additional challenge of flexible adaptation to a user or a situation. This requires optimizing complex objectives such as information density, in combinatorial search spaces described using declarative input languages. We believe that AI search and planning is a natural match for these problems, and could substantially contribute to solving them effectively. We illustrate this using a concrete example NLG framework, give a summary of the relevant optimization objectives, and provide an initial list of research challenges.