Intelligent Search in the Social Web
The continuously growing amount of data on the Internet leads to a considerable information overflow, which makes it more difficult for users to access relevant content. Intelligent search technologies are thus needed to optimally find and retrieve relevant information. In addition to the classic search query, automatic question answering technologies have become more and more popular over the past years. Systems that already allow answering simple factual questions have reached the daily lives of many people through digital assistants such as Apple Siri. However, there exist many other types of complicated questions that cannot be answered with existing approaches. This is, for example, the case for questions that require detailed descriptions, opinions, or experiences as answers (“What are the pros and cons of X?”, or “I have problem Y, how can I solve it?”).
In the project “Intelligent Search for Information in the Social Web” we will close this gap by researching intelligent search technologies in the social web. In particular, for new user questions we will search for relevant content in question-answer platforms, where many complicated questions have already been answered. Retrieving this information reliably will enable us to automatically answer complex questions.
Software Campus program (BMBF)
- DATEV eG, Nürnberg Germany
- Prof. Dr. Iryna Gurevych, Mentor
- Andreas Rückle, Doctoral Researcher
Eichler, Max ; Şahin, Gözde Gül ; Gurevych, Iryna (2019):
LINSPECTOR WEB: A Multilingual Probing Suite for Word Representations.
In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing (EMNLP 2019), In: The 2019 Conference on Empirical Methods in Natural Language Processing (EMNLP 2019), Hong Kong, China, 03.11.2019-07.11.2019, [Online-Edition: https://public.ukp.informatik.tu-darmstadt.de/UKP_Webpage/pu...],
Rücklé, Andreas ; Swarnkar, Krishnkant ; Gurevych, Iryna (2019):
Improved Cross-Lingual Question Retrieval for Community Question Answering.
In: Proceedings of The Web Conference (WWW-19), San Francisco, USA, San Francisco, USA, [Online-Edition: https://dl.acm.org/citation.cfm?id=3313502],
Rücklé, Andreas ; Moosavi, Nafise Sadat ; Gurevych, Iryna (2019):
COALA: A Neural Coverage-Based Approach for Long Answer Selection with Small Data.
In: Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence (AAAI-19), Honolulu, Hawaii, USA, In: Thirty-Third AAAI Conference on Artificial Intelligence (AAAI-19), Honolulu, Hawaii, USA, DOI: 10.1609/aaai.v33i01.33016932,