Beyond Similarity - Dimensions of Semantics and How to Detect them

Aus SDQ-Institutsseminar
Version vom 2. Januar 2023, 11:12 Uhr von Sophie Corallo (Diskussion | Beiträge)
(Unterschied) ← Nächstältere Version | Aktuelle Version (Unterschied) | Nächstjüngere Version → (Unterschied)
Vortragende(r) Felix Pieper
Vortragstyp Masterarbeit
Betreuer(in) Sophie Corallo
Termin Fr 13. Januar 2023
Vortragsmodus in Präsenz
Kurzfassung Semantic similarity estimation is a widely used and well-researched area. Current state-of-the-art approaches estimate text similarity with large language models. However, semantic similarity estimation often ignores fine-grain differences between semantic similar sentences. This thesis proposes the concept of semantic dimensions to represent fine-grain differences between two sentences. A workshop with domain experts identified ten semantic dimensions. From the workshop insights, a model for semantic dimensions was created. Afterward, 60 participants decided via a survey which semantic dimensions are useful to users. Detectors for the five most useful semantic dimensions were implemented in an extendable framework. To evaluate the semantic dimensions detectors, a dataset of 200 sentence pairs was created. The detectors reached an average F1 score of 0.815.