Wikipedia Ad Hoc Passage Retrieval and Wikipedia Document Linking

Author(s):  
Dylan Jenkinson ◽  
Andrew Trotman
Keyword(s):  
Ad Hoc ◽  
2019 ◽  
Vol 28 (07) ◽  
pp. 1950021
Author(s):  
Rim Faiz ◽  
Nouha Othman

Question Answering is most likely one of the toughest tasks in the field of Natural Language Processing. It aims at directly returning accurate and short answers to questions asked by users in human language over a huge collection of documents or database. Recently, the continuously exponential rise of digital information has imposed the need for more direct access to relevant answers. Thus, question answering has been the subject of a widespread attention and has been extensively explored over the last few years. Retrieving passages remains a crucial but also a challenging task in question answering. Although there has been an abundance of work on this task, this latter still implies non-trivial endeavor. In this paper, we propose an ad-hoc passage retrieval approach for Question Answering using n-grams. This approach relies on a new measure of similarity between a passage and a question for the extraction and ranking of the different passages based on n-gram overlapping. More concretely, our measure is based on the dependency degree of n-gram words of the question in the passage. We validate our approach by the development of the “SysPex” system that automatically returns the most relevant passages to a given question.


2021 ◽  
Vol 39 (4) ◽  
pp. 1-29
Author(s):  
Sheng-Chieh Lin ◽  
Jheng-Hong Yang ◽  
Rodrigo Nogueira ◽  
Ming-Feng Tsai ◽  
Chuan-Ju Wang ◽  
...  

Conversational search plays a vital role in conversational information seeking. As queries in information seeking dialogues are ambiguous for traditional ad hoc information retrieval (IR) systems due to the coreference and omission resolution problems inherent in natural language dialogue, resolving these ambiguities is crucial. In this article, we tackle conversational passage retrieval, an important component of conversational search, by addressing query ambiguities with query reformulation integrated into a multi-stage ad hoc IR system. Specifically, we propose two conversational query reformulation (CQR) methods: (1) term importance estimation and (2) neural query rewriting. For the former, we expand conversational queries using important terms extracted from the conversational context with frequency-based signals. For the latter, we reformulate conversational queries into natural, stand-alone, human-understandable queries with a pretrained sequence-to-sequence model. Detailed analyses of the two CQR methods are provided quantitatively and qualitatively, explaining their advantages, disadvantages, and distinct behaviors. Moreover, to leverage the strengths of both CQR methods, we propose combining their output with reciprocal rank fusion, yielding state-of-the-art retrieval effectiveness, 30% improvement in terms of NDCG@3 compared to the best submission of Text REtrieval Conference (TREC) Conversational Assistant Track (CAsT) 2019.


Pflege ◽  
2020 ◽  
Vol 33 (5) ◽  
pp. 289-298
Author(s):  
Katharina Silies ◽  
Angelika Schley ◽  
Janna Sill ◽  
Steffen Fleischer ◽  
Martin Müller ◽  
...  

Zusammenfassung. Hintergrund: Die COVID-19-Pandemie ist eine Ausnahmesituation ohne Präzedenz und erforderte zahlreiche Ad-hoc-Anpassungen in den Strukturen und Prozessen der akutstationären Versorgung. Ziel: Ziel war es zu untersuchen, wie aus Sicht von Führungspersonen und Hygienefachkräften in der Pflege die stationäre Akutversorgung durch die Pandemiesituation beeinflusst wurde und welche Implikationen sich daraus für die Zukunft ergeben. Methoden: Qualitative Studie bestehend aus semistrukturierten Interviews mit fünf Verantwortlichen des leitenden Pflegemanagements und drei Hygienefachkräften in vier Krankenhäusern in Deutschland. Die Interviews wurden mittels qualitativer Inhaltsanalyse ausgewertet. Ergebnisse: Die Befragten beschrieben den auf die prioritäre Versorgung von COVID-19-Fällen hin umstrukturierten Klinikalltag. Herausforderungen waren Unsicherheit und Angst bei den Mitarbeiter_innen, relative Ressourcenknappheit von Material und Personal und die schnelle Umsetzung neuer Anforderungen an die Versorgungleistung. Dem wurde durch gezielte Kommunikation und Information, massive Anstrengungen zur Sicherung der Ressourcen und koordinierte Steuerung aller Prozesse durch bereichsübergreifende, interprofessionelle Task Forces begegnet. Schlussfolgerungen: Die in der COVID-19-Pandemie vorgenommenen Anpassungen zeigen Entwicklungspotenziale für die zukünftige Routineversorgung auf, z. B. könnten neue Arbeits- und Skill Mix-Modelle aufgegriffen werden. Für die Konkretisierung praktischer Implikationen sind vertiefende Analysen der Daten mit zeitlichem Abstand erforderlich.


2006 ◽  
Vol 5 (2) ◽  
pp. 68-71 ◽  
Author(s):  
Simone Kauffeld
Keyword(s):  
Ad Hoc ◽  

Zusammenfassung. Der FEO, der in Kooperation mit betrieblichen Praktikern entwickelt wurde, dient der Erfassung des Organisationsklimas. Er umfasst 82 Items und bildet 12 Skalen ab. Eine Stärke des FEO im Gegensatz zu ad hoc entwickelten Befragungsinstrumenten sind die Vergleichsdaten, die für Profit- und Non-Profit-Organisationen bereit gestellt werden. Kritisch diskutiert wird die theoretische Verortung, die Anwenderfreundlichkeit sowie der Nutzen der individuellen Auswertung. Die konsensuale, konvergente, diskriminante und kriterienbezogene Validierung steht aus.


1999 ◽  
Vol 15 (2) ◽  
pp. 151-157 ◽  
Author(s):  
José Muñiz ◽  
Gerardo Prieto ◽  
Leandro Almeida ◽  
Dave Bartram

Summary: The two main sources of errors in educational and psychological evaluation are the lack of adequate technical and psychometric characteristics of the tests, and especially the failure to properly implement the testing process. The main goal of the present research is to study the situation of test construction and test use in the Spanish-speaking (Spain and Latin American countries) and Portuguese-speaking (Portugal and Brazil) countries. The data were collected using a questionnaire constructed by the European Federation of Professional Psychologists Association (EFPPA) Task Force on Tests and Testing, under the direction of D. Bartram . In addition to the questionnaire, other ad hoc data were also gathered. Four main areas of psychological testing were investigated: Educational, Clinical, Forensic and Work. Key persons were identified in each country in order to provide reliable information. The main results are presented, and some measures that could be taken in order to improve the current testing practices in the countries surveyed are discussed. As most of the tests used in these countries were originally developed in other cultures, a problem that appears to be especially relevant is the translation and adaptation of tests.


Sign in / Sign up

Export Citation Format

Share Document