SubmissionNumber#=%=#195 FinalPaperTitle#=%=#GIL-IIMAS UNAM at SemEval-2024 Task 1: SAND: An In Depth Analysis of Semantic Relatedness Using Regression and Similarity Characteristics ShortPaperTitle#=%=# NumberOfPages#=%=#5 CopyrightSigned#=%=#Francisco Fernando López Ponce JobTitle#==# Organization#==#Grupo de Ingeniería Lingüística del Instituto de Ingeniería de la UNAM. Sótano de la Torre de Ingeniería, Circuito Escolar, Ingeniería S/N, C.U., Coyoacán, 04510, Ciudad de México. Abstract#==#The STR shared task aims at detecting the degree of semantic relatedness between sentence pairs in multiple languages. Semantic relatedness relies on elements such as topic similarity, point of view agreement, entailment, and even human intuition, making it a broader field than sentence similarity. The GIL-IIMAS UNAM team proposes a model based in the SAND characteristics composition (Sentence Transformers, AnglE Embeddings, N-grams, Sentence Length Difference coefficient) and classical regression algorithms. This model achieves a 0.83 Spearman Correlation score in the English test, and a 0.73 in the Spanish counterpart, finishing just above the SemEval baseline in English, and second place in Spanish. Author{1}{Firstname}#=%=#Francisco Fernando Author{1}{Lastname}#=%=#Lopez-Ponce Author{1}{Username}#=%=#franciscoflp Author{1}{Email}#=%=#francisco.lopez.ponce@ciencias.unam.mx Author{1}{Affiliation}#=%=#Universidad Nacional Autónoma de México Author{2}{Firstname}#=%=#Ángel Eduardo Author{2}{Lastname}#=%=#Cadena Author{2}{Email}#=%=#angelcaden@gmail.com Author{2}{Affiliation}#=%=#Universidad Nacional Autónoma de México Author{3}{Firstname}#=%=#Karla Denia Author{3}{Lastname}#=%=#Salas-Jimenez Author{3}{Email}#=%=#karla_dsj@ciencias.unam.mx Author{3}{Affiliation}#=%=#Universidad Nacional Autónoma de México Author{4}{Firstname}#=%=#Gemma Author{4}{Lastname}#=%=#Bel-Enguix Author{4}{Username}#=%=#gemma.bel Author{4}{Email}#=%=#gbele@iingen.unam.mx Author{4}{Affiliation}#=%=#Universidad Nacional Autónoma de México Author{5}{Firstname}#=%=#David Salvador Author{5}{Lastname}#=%=#Preciado-Márquez Author{5}{Email}#=%=#davidpreciado115@gmail.com Author{5}{Affiliation}#=%=#Universidad Nacional Autónoma de México ========== èéáğö