To Extend or not to Extend? Complementary Documents

An agent in pursuit of a task may work with a corpus of documents with linked subjective content descriptions. Performing the task of document retrieval for a user or aiming to extend its own corpus, an agent so far relies on similarity measures to identify related documents. However, similarity may...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2022 IEEE 16th International Conference on Semantic Computing (ICSC) s. 17 - 24
Hlavní autoři: Bender, Magnus, Kuhr, Felix, Braun, Tanya
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.01.2022
Témata:
Complementarity
Conferences
Corpus extension
Document classification
Semantics
Subjective context description
Task analysis
Taxonomy
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:An agent in pursuit of a task may work with a corpus of documents with linked subjective content descriptions. Performing the task of document retrieval for a user or aiming to extend its own corpus, an agent so far relies on similarity measures to identify related documents. However, similarity may not be appropriate if looking for new information or different aspects of the same content. Therefore, this paper focuses on complementarity, specifically, contributing (i) a formal definition of complementarity using the available subjective content de-scriptions in the form of relational tuples as well as a taxonomy interrelating the concepts referenced in the tuples, (ii) a problem definition and solution approach for classifying complementary documents, and (iii) a case study assessing classification performance for complementary documents.
DOI:10.1109/ICSC52841.2022.00011