1 Introduction
2 Project Results So Far
2.1 Comparative Argumentative Machine (CAM)
2.2 Argument Mining and Retrieval with TARGER
TARGER
[5]: a neural argument tagger, coming with a web interface5 and a RESTful API. The tool can tag arguments in free text inputs (cf. Fig. 2) and can retrieve arguments from the DepCC corpus that is also used in the CAM prototype (cf. Fig. 3). TARGER
is based on a BiLSTM-CNN-CRF neural tagger [10] pre-trained on the persuasive essays (Essays) [7], web discourse (WebD) [8], or IBM Debater (IBM) [9] datasets and is able to identify argument components in text and classify them as claims or premises. Using TARGER
’s web interface or API, researchers and practitioners can thus use state-of-the-art argument mining without any reproducibility effort (for more details on the implementation and effectiveness, see our respective paper [5]).
2.3 Re-Ranking with Argumentativeness Axioms
TARGER
to tag arguments as premises and claims and then re-rank the top-50 BM25F results with respect to several facets of argumentativeness (e.g., which document contains more argumentative units close to the query terms). We tested the axiomatic re-ranking with a focus on argumentativeness in the TREC 2018 Common Core track [4] and also in the TREC 2019 Decision track [3], where we also added credibility axioms. The results show some encouraging improvements for some of the TREC topics that we manually identified as potentially “argumentative” while the generalizability to more topics needs some further investigation (for more details on axioms and results, see our respective TREC reports [3, 4]).