论文信息 - Webis at TREC 2019: Decision Track

Webis at TREC 2019: Decision Track

is paper gives an overview of the Webis group’s participation in the TREC 2019 Decision Track. Our idea is to axiomatically re-rank the top-k results of BM25F for those topics that seem to be argumentative. For the re-ranking, we use ve axioms that capture signals of argumentativeness and information credibility.

[1] Nick Craswell,et al. Learning to Match using Local and Distributed Representations of Text for Web Search , 2016, WWW.

[2] Jakob Grue Simonsen,et al. Evaluation Measures for Relevance and Credibility in Ranked Lists , 2017, ICTIR.

[3] Matthias Hagen,et al. Axiomatic Result Re-Ranking , 2016, CIKM.

[4] 京都大学防災研究所技術部. 防災研究所技術部通信 = Technical communication , 1992 .

[5] Paolo Torroni,et al. MARGOT: A web server for argumentation mining , 2016, Expert Syst. Appl..

[6] Guo-Qiang Zhang,et al. Enhancing relevance scoring with chronological term rank , 2007, SIGIR.

[7] ChengXiang Zhai,et al. Axiomatic Thinking for Information Retrieval: And Related Tasks , 2017, SIGIR.

[8] J. Powell,et al. Empirical studies assessing the quality of health information for consumers on the world wide web: a systematic review. , 2002, JAMA.

[9] Matthias Hagen,et al. Webis at TREC 2018: Common Core Track , 2018, TREC.

[10] Matthias Hagen,et al. Elastic ChatNoir: Search Engine for the ClueWeb and the Common Crawl , 2018, ECIR.

[11] Matthias Hagen,et al. TARGER: Neural Argument Mining at Your Fingertips , 2019, ACL.