{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/icelandic-parallel-abstracts-corpus","title":"Icelandic Parallel Abstracts Corpus","arxiv_id":"2108.05289","date":"2021-08-11","proceeding":null,"authors":["Haukur Barri Símonarson","Vésteinn Snæbjarnarson"],"abstract":"We present a new Icelandic-English parallel corpus, the Icelandic Parallel Abstracts Corpus (IPAC), composed of abstracts from student theses and dissertations. The texts were collected from the Skemman repository which keeps records of all theses, dissertations and final projects from students at Icelandic universities. The corpus was aligned based on sentence-level BLEU scores, in both translation directions, from NMT models using Bleualign. The result is a corpus of 64k sentence pairs from over 6 thousand parallel abstracts.","url_abs":"https://arxiv.org/abs/2108.05289v1","url_pdf":"https://arxiv.org/pdf/2108.05289v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"nmt","task_name":"NMT"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[{"slug":"ipac","name":"IPAC","full_name":"Icelandic Parallel Abstracts Corpus"}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}