From Evaluating to Forecasting Performance: How to Turn Information Retrieval, Natural Language Processing and Recommender Systems into Predictive Sciences (Dagstuhl Perspectives Workshop 17442).
Nicola FerroNorbert FuhrGregory GrefenstetteJoseph A. KonstanPablo CastellsElizabeth M. DalyThierry DeclerckMichael D. EkstrandWerner GeyerJulio GonzaloTsvi KuflikKrister LindénBernardo MagniniJian-Yun NieRaffaele PeregoBracha ShapiraIan SoboroffNava TintarevKarin VerspoorMartijn C. WillemsenJustin ZobelPublished in: Dagstuhl Manifestos (2018)
Keyphrases
- natural language processing
- recommender systems
- information retrieval
- information extraction
- computational linguistics
- text mining
- text processing
- naacl hlt
- information filtering
- language processing
- question answering
- user modeling
- predictive model
- collaborative filtering
- linguistic analysis
- information retrieval systems
- machine learning
- tasks in natural language processing
- ontology learning
- user profiling
- natural language
- information overload
- matrix factorization
- short term
- user profiles
- machine translation
- word sense disambiguation
- wordnet
- named entity recognition
- user modelling
- computer science
- named entities
- bring together researchers and practitioners
- user preferences
- computational biology
- knowledge representation
- implicit feedback
- selected papers
- document collections
- search engine
- user model
- cold start problem
- recommendation quality
- trust aware
- data mining
- personalized recommendation
- long term
- web search
- computational intelligence
- information seeking
- prediction model
- learning to rank
- query expansion