Semantic Textual Similarity Measures for Case-Based Retrieval of Argument Graphs

Lenz, Mirko; Ollinger, Stefan; Sahitaj, Premtim; Bergmann, Ralph

doi:10.1007/978-3-030-29249-2_15

Cited by 16 publications

(9 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This confirms the assumption that partly motivated this paper. The effect might be amplified by domains that are even more complex than CB-II, such as argumentation [25] or flexible manufacturing [4]. Additionally, it is shown that sGEM and sGMN, although integrating rich semantic information, are not able to consistently outperform FBM in MAC/FAC retrieval tasks.…”

Section: Discussionmentioning

confidence: 98%

“…This optimization ranges from aspects of parameterization to adjustments of the data encoding scheme and the usage of different neural network structures. The neural network structures could be optimized to better process other graph domains, e.g., argument graphs [25], or even other types of complex similarity measures [56]. A structural change could be, for instance, using a differentiable ranking loss function that optimizes according to the ground-truth ordering of the retrieval results (e.g., [57]).…”

Section: Discussionmentioning

confidence: 99%

“…In this case, a spoon and a knife are needed to execute the task (Auxiliaries) and the estimated time that the task takes is two minutes (Duration). The definition of NEST graphs [7] does not strictly specify the contents of the semantic descriptions in S. To frame the scope of this work regarding semantic descriptions, we refer to the definitions of the POCBR framework ProCAKE [24] since it is widely used in the POCBR literature (e.g., [5,19,21,22,25]). Entries of semantic descriptions in ProCAKE have a certain data type and a content (or value).…”

Section: Semantic Graph Representationmentioning

confidence: 99%

See 2 more Smart Citations

Using Graph Embedding Techniques in Process-Oriented Case-Based Reasoning

Hoffmann

Bergmann

2022

Algorithms

Self Cite

View full text Add to dashboard Cite

Similarity-based retrieval of semantic graphs is a core task of Process-Oriented Case-Based Reasoning (POCBR) with applications in real-world scenarios, e.g., in smart manufacturing. The involved similarity computation is usually complex and time-consuming, as it requires some kind of inexact graph matching. To tackle these problems, we present an approach to modeling similarity measures based on embedding semantic graphs via Graph Neural Network (GNNs). Therefore, we first examine how arbitrary semantic graphs, including node and edge types and their knowledge-rich semantic annotations, can be encoded in a numeric format that is usable by GNNs. Given this, the architecture of two generic graph embedding models from the literature is adapted to enable their usage as a similarity measure for similarity-based retrieval. Thereby, one of the two models is more optimized towards fast similarity prediction, while the other model is optimized towards knowledge-intensive, more expressive predictions. The evaluation examines the quality and performance of these models in preselecting retrieval candidates and in approximating the ground-truth similarities of a graph-matching-based similarity measure for two semantic graph domains. The results show the great potential of the approach for use in a retrieval scenario, either as a preselection model or as an approximation of a graph similarity measure.

show abstract

Section: Discussionmentioning

confidence: 98%

Section: Discussionmentioning

confidence: 99%

Section: Semantic Graph Representationmentioning

confidence: 99%

See 1 more Smart Citation

Using Graph Embedding Techniques in Process-Oriented Case-Based Reasoning

Hoffmann

Bergmann

2022

Algorithms

Self Cite

View full text Add to dashboard Cite

show abstract

“…Brychcín [33] introduced a new transformation technique to project monolingual semantic spaces using a bilingual dictionary. Lenz et al [34] proposed new supervised and unsupervised measures in the context of a graph-based similarity for argument graphs. BERT encoder is applied in a fully unsupervised crosslingual semantic similarity measures for identifying parallel data [35].…”

Section: Related Workmentioning

confidence: 99%

Leveraging Grammatical Roles for Measuring Semantic Similarity Between Texts

et al. 2021

View full text Add to dashboard Cite

Semantic similarity between texts can be defined based on their meaning. Assessing the textual similarity is a prerequisite in almost all applications in the field of language processing and information retrieval. However, the diversity in the sentence structure makes it formidable to estimate the similarity. Some sentences pairs are lexicographically similar but semantically dissimilar. That is why the trivial lexical overlapping is not enough for measuring the similarity. To attain the semanticity of sentences, the context of the words and the structure of the sentence should be considered. In this paper, we propose a new method for capturing the semantic similarity between sentences based on their grammatical roles through word semantics. First, the sentences are divided grammatically into different parts where each part is considered as a grammatical role. Then multiple new measures are introduced to estimate the role-based similarity exploiting word semantics considering the sentence structure. The proposed similarity measures focus on inter-role and intra-role similarity between the sentence-pair. The word-level semantic information is extracted from a pre-trained word-embedding model. The performance of the proposed method was verified by conducting a wide range of experiments on the SemEval STS dataset. The experimental results indicated the effectiveness of the proposed method in terms of different standard evaluation metrics and outperformed some known related works.

show abstract

“…Argument similarity and search Assessing argument similarity is a key task in argument mining (Reimers et al, 2019;Lenz et al, 2019) and can enhance argument search (Maturana, 1988;Rissland et al, 1993;Wachsmuth et al, 2017;Ajjour et al, 2019;Chesnevar and Maguitman, 2004). Yet, while delivering solid performance on benchmarks, current methods fail to provide any deeper rationale for their predictions.…”

Section: Related Workmentioning

confidence: 99%

Explainable Unsupervised Argument Similarity Rating with Abstract Meaning Representation and Conclusion Generation

Opitz¹,

Heinisch²,

Wiesenbach³

et al. 2021

Proceedings of the 8th Workshop on Argument Mining

View full text Add to dashboard Cite

When assessing the similarity of arguments, researchers typically use approaches that do not provide interpretable evidence or justifications for their ratings. Hence, the features that determine argument similarity remain elusive. We address this issue by introducing novel argument similarity metrics that aim at high performance and explainability. We show that Abstract Meaning Representation (AMR) graphs can be useful for representing arguments, and that novel AMR graph metrics can offer explanations for argument similarity ratings. We start from the hypothesis that similar premises often lead to similar conclusionsand extend an approach for AMR-based argument similarity rating by estimating, in addition, the similarity of conclusions that we automatically infer from the arguments used as premises. We show that AMR similarity metrics make argument similarity judgements more interpretable and may even support argument quality judgements. Our approach provides significant performance improvements over strong baselines in a fully unsupervised setting. Finally, we make first steps to address the problem of reference-less evaluation of argumentative conclusion generations.

show abstract

Semantic Textual Similarity Measures for Case-Based Retrieval of Argument Graphs

Cited by 16 publications

References 21 publications

Using Graph Embedding Techniques in Process-Oriented Case-Based Reasoning

Using Graph Embedding Techniques in Process-Oriented Case-Based Reasoning

Leveraging Grammatical Roles for Measuring Semantic Similarity Between Texts

Explainable Unsupervised Argument Similarity Rating with Abstract Meaning Representation and Conclusion Generation

Contact Info

Product

Resources

About