Publications

@inproceedings{	20.500.12708_137002,

title = {PARM: A Paragraph Aggregation Retrieval Model for Dense Document-to-Document Retrieval},

author = {Sophia Althammer and Sebastian Hofstätter and Mete Sertkan and Suzan Verberne and Allan Hanbury},

doi = {10.1007/978-3-030-99736-6_2},

year  = {2022},

date = {2022-01-01},

pages = {19–34},

publisher = {Springer},

abstract = {Dense passage retrieval (DPR) models show great effectiveness gains in first stage retrieval for the web domain. However in the web domain we are in a setting with large amounts of training data and a query-to-passage or a query-to-document retrieval task. We investigate in this paper dense document-to-document retrieval with limited labelled target data for training, in particular legal case retrieval. In order to use DPR models for document-to-document retrieval, we propose a Paragraph Aggregation Retrieval Model (PARM) which liberates DPR models from their limited input length. PARM retrieves documents on the paragraph-level: for each query paragraph, relevant documents are retrieved based on their paragraphs. Then the relevant results per query paragraph are aggregated into one ranked list for the whole query document. For the aggregation we propose vector-based aggregation with reciprocal rank fusion (VRRF) weighting, which combines the advantages of rank-based aggregation and topical aggregation based on the dense embeddings. Experimental results show that VRRF outperforms rank-based aggregation strategies for dense document-to-document retrieval with PARM. We compare PARM to document-level retrieval and demonstrate higher retrieval effectiveness of PARM for lexical and dense first-stage retrieval on two different legal case retrieval collections. We investigate how to train the dense retrieval model for PARM on limited target data with labels on the paragraph or the document-level. In addition, we analyze the differences of the retrieved results of lexical and dense retrieval with PARM.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{	20.500.12708_58556,

title = {Workshop on Recommenders in Tourism (RecTour)},

author = {Julia Neidhardt and Wolfgang Wörndl and Tsvi Kuflik and Markus Zanker},

doi = {10.1145/3460231.3470930},

year  = {2021},

date = {2021-01-01},

booktitle = {Fifteenth ACM Conference on Recommender Systems},

publisher = {ACM},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{	20.500.12708_58574,

title = {WebTour 2021 Workshop on Web Tourism},

author = {Tsvi Kuflik and Catalin Mihai Barbu and Amra Delic and Dmitri Goldenberg and Julia Neidhardt and Ludovik Coba and Markus Zanker},

doi = {10.1145/3437963.3441836},

year  = {2021},

date = {2021-01-01},

booktitle = {Proceedings of the 14th ACM International Conference on Web Search and Data Mining},

publisher = {ACM},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{	20.500.12708_58724,

title = {Semantische Netzwerke als Hilfsmittel für die Untersuchung des Begriffskomplexes Arbeit-Lohn-Vermögen im öffentlichen Diskurs Österreichs},

author = {Klaus Hofmann and Andreas Baumann and Anna Marakasova and Julia Neidhardt and Tanja Wissik},

year  = {2021},

date = {2021-01-01},

booktitle = {Momentum 2021 Kongress},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{	20.500.12708_55667,

title = {Exploring Causal Relationships Among Emotional and Topical Trajectories in Political Text Data},

author = {Andreas Baumann and Klaus Hofmann and Bettina Kern and Anna Marakasova and Julia Neidhardt and Tanja Wissik},

doi = {10.4230/OASIcs.LDK.2021.38},

isbn = {978-3-95977-199-3},

year  = {2021},

date = {2021-01-01},

booktitle = {3rd Conference on Language, Data and Knowledge (LDK 2021)},

pages = {1–8},

publisher = {OASICS},

address = {93},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{	20.500.12708_55666,

title = {A review and cluster analysis of German polarity resources for sentiment analysis},

author = {Bettina Kern and Andreas Baumann and Thomas Kolb and Katharina Sekanina and Klaus Hofmann and Tanja Wissik and Julia Neidhardt},

doi = {10.4230/OASIcs.LDK.2021.37},

isbn = {978-3-95977-199-3},

year  = {2021},

date = {2021-01-01},

booktitle = {3rd Conference on Language, Data and Knowledge (LDK 2021)},

pages = {1–17},

publisher = {OASICS},

address = {93},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{	20.500.12708_58755,

title = {Modeling Users and Items for Recommenders:There Is More than Semantics},

author = {Mete Sertkan},

doi = {10.1145/3460231.3473898},

year  = {2021},

date = {2021-01-01},

booktitle = {Fifteenth ACM Conference on Recommender Systems},

publisher = {ACM},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{zia2021step,

title = {A step towards improving knowledge tracing},

author = {Aayesha Zia and Jalal Nouri and Muhammad Afzaal and Yongchao Wu and Xiu Li and Rebecka Weegar},

year  = {2021},

date = {2021-01-01},

booktitle = {2021 International Conference on Advanced Learning Technologies (ICALT)},

pages = {38–39},

organization = {IEEE},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}