Quality-Aware Ranking of Arguments

Dumani, Lorik; Schenkel, Ralf

doi:10.1145/3340531.3411960

Cited by 5 publications

(5 citation statements)

References 31 publications

(77 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Dumani and Schenkel [24] applied clustering with NLP by creating a quality-aware ranking framework for arguments extracted from texts and represented in graphs. To achieve that, they used a (claim, premise) dataset based on debates taken on online portals in which they used SBERT instead of BERT, previously used on [25], to obtain the embeddings of the claims and premises.…”

Section: Related Workmentioning

confidence: 99%

Supporting Argumentation Dialogues in Group Decision Support Systems: An Approach Based on Dynamic Clustering

et al. 2022

View full text Add to dashboard Cite

Group decision support systems (GDSSs) have been widely studied over the recent decades. The Web-based group decision support systems appeared to support the group decision-making process by creating the conditions for it to be effective, allowing the management and participation in the process to be carried out from any place and at any time. In GDSS, argumentation is ideal, since it makes it easier to use justifications and explanations in interactions between decision-makers so they can sustain their opinions. Aspect-based sentiment analysis (ABSA) intends to classify opinions at the aspect level and identify the elements of an opinion. Intelligent reports for GDSS provide decision makers with accurate information about each decision-making round. Applying ABSA techniques to group decision making context results in the automatic identification of alternatives and criteria, for instance. This automatic identification is essential to reduce the time decision makers take to step themselves up on group decision support systems and to offer them various insights and knowledge on the discussion they are participating in. In this work, we propose and implement a methodology that uses an unsupervised technique and clustering to group arguments on topics around a specific alternative, for example, or a discussion comparing two alternatives. We experimented with several combinations of word embedding, dimensionality reduction techniques, and different clustering algorithms to achieve the best approach. The best method consisted of applying the KMeans++ clustering technique, using SBERT as a word embedder with UMAP dimensionality reduction. These experiments achieved a silhouette score of 0.63 with eight clusters on the baseball dataset, which wielded good cluster results based on their manual review and word clouds. We obtained a silhouette score of 0.59 with 16 clusters on the car brand dataset, which we used as an approach validation dataset. With the results of this work, intelligent reports for GDSS become even more helpful, since they can dynamically organize the conversations taking place by grouping them on the arguments used.

show abstract

Section: Related Workmentioning

confidence: 99%

Supporting Argumentation Dialogues in Group Decision Support Systems: An Approach Based on Dynamic Clustering

et al. 2022

View full text Add to dashboard Cite

show abstract

“…For ranking, they utilize ElasticSearch together with the scoring model Okapi BM25 [11]. 7 In our work, we also use the corpus from Ajjour et al [2] as it is the official dataset of Touché. In contrast to the previous mentioned models, ours works more strictly with a two-step retrieval and does not take into account textual similarity between query and premise because convincing premises do not need to have much textual overlap to the query.…”

Section: Related Workmentioning

confidence: 99%

“…In this section, we examine the process of finding arguments that runs in the background when a query comes in. For this GUI we implemented the probabilistic framework described in detail in our groundworks [6,7] and presented in the CLEF lab Touché. Below, we revise, due to space limitations, only the most important points.…”

Section: Backendmentioning

confidence: 99%

“…Still, it naturally needs some modifications to integrate other systems there. We demonstrate the functionality and visualization of the tool by incorporating a system [6,7] we presented in the CLEF lab Touché [3][4][5]. 1 2 This demo addresses people interested in argument retrieval and argument search.…”

Section: Introductionmentioning

confidence: 99%

“…Next, Section 2 introduces to related work. Then, Section 3 explains the backend and the retrieval process that works in the background of our system [6,7]. After that, we describe the frontend and the default user interactivity in Section 4.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations