{"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/a-multilingual-parallel-corpora-collection-1","title":"A Multilingual Parallel Corpora Collection Effort for Indian Languages","arxiv_id":"2007.07691","date":"2020-07-15","proceeding":"LREC 2020 5","authors":["Shashank Siripragada","Jerin Philip","Vinay P. Namboodiri","C. V. Jawahar"],"abstract":"We present sentence aligned parallel corpora across 10 Indian Languages - Hindi, Telugu, Tamil, Malayalam, Gujarati, Urdu, Bengali, Oriya, Marathi, Punjabi, and English - many of which are categorized as low resource. The corpora are compiled from online sources which have content shared across languages. The corpora presented significantly extends present resources that are either not large enough or are restricted to a specific domain (such as health). We also provide a separate test corpus compiled from an independent online source that can be independently used for validating the performance in 10 Indian languages. Alongside, we report on the methods of constructing such corpora using tools enabled by recent advances in machine translation and cross-lingual retrieval using deep neural network based methods.","url_abs":"https://arxiv.org/abs/2007.07691v1","url_pdf":"https://arxiv.org/pdf/2007.07691v1.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":[{"paper_slug":"a-multilingual-parallel-corpora-collection-1","repo_url":"https://github.com/jerinphilip/fairseq-ilmt","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"a-multilingual-parallel-corpora-collection-1","repo_url":"https://github.com/shashanksiripragada/pib-crawl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2007.07691","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.07691"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jerinphilip/fairseq-ilmt","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/shashanksiripragada/pib-crawl","reach":{"status":"ok"}}],"summary":{"ran":3,"unverified":7},"by_repo_kind":{"listed":{"samples":10,"ran":3,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":10,"samples":[{"code_sha256_prefix":"90b79fe15491de83","entry":"is_master","repo":"jerinphilip/fairseq-ilmt","repo_kind":"listed","path":"fairseq/distributed_utils.py","file_url":"https://github.com/jerinphilip/fairseq-ilmt/blob/HEAD/fairseq/distributed_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"90b79fe15491de83"}},{"code_sha256_prefix":"82bdf940665aeeb4","entry":"safe_readline","repo":"jerinphilip/fairseq-ilmt","repo_kind":"listed","path":"fairseq/binarizer.py","file_url":"https://github.com/jerinphilip/fairseq-ilmt/blob/HEAD/fairseq/binarizer.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"82bdf940665aeeb4"}},{"code_sha256_prefix":"9418b43048e4e4ec","entry":"url_to_filename","repo":"jerinphilip/fairseq-ilmt","repo_kind":"listed","path":"fairseq/file_utils.py","file_url":"https://github.com/jerinphilip/fairseq-ilmt/blob/HEAD/fairseq/file_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"9418b43048e4e4ec"}},{"code_sha256_prefix":"59755e76d7c3f48b","entry":"all_reduce","repo":"jerinphilip/fairseq-ilmt","repo_kind":"listed","path":"fairseq/distributed_utils.py","file_url":"https://github.com/jerinphilip/fairseq-ilmt/blob/HEAD/fairseq/distributed_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"59755e76d7c3f48b"}},{"code_sha256_prefix":"27cb9a85ba28e204","entry":"distributed_init","repo":"jerinphilip/fairseq-ilmt","repo_kind":"listed","path":"fairseq/distributed_utils.py","file_url":"https://github.com/jerinphilip/fairseq-ilmt/blob/HEAD/fairseq/distributed_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"27cb9a85ba28e204"}},{"code_sha256_prefix":"b1a033619f614e17","entry":"filename_to_url","repo":"jerinphilip/fairseq-ilmt","repo_kind":"listed","path":"fairseq/file_utils.py","file_url":"https://github.com/jerinphilip/fairseq-ilmt/blob/HEAD/fairseq/file_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"b1a033619f614e17"}},{"code_sha256_prefix":"689c715a241a8919","entry":"load_archive_file","repo":"jerinphilip/fairseq-ilmt","repo_kind":"listed","path":"fairseq/file_utils.py","file_url":"https://github.com/jerinphilip/fairseq-ilmt/blob/HEAD/fairseq/file_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"689c715a241a8919"}},{"code_sha256_prefix":"c5ea9d48b6fc2167","entry":"load_checkpoint","repo":"jerinphilip/fairseq-ilmt","repo_kind":"listed","path":"fairseq/checkpoint_utils.py","file_url":"https://github.com/jerinphilip/fairseq-ilmt/blob/HEAD/fairseq/checkpoint_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"c5ea9d48b6fc2167"}},{"code_sha256_prefix":"df40d96cc20e7f57","entry":"load_checkpoint_to_cpu","repo":"jerinphilip/fairseq-ilmt","repo_kind":"listed","path":"fairseq/checkpoint_utils.py","file_url":"https://github.com/jerinphilip/fairseq-ilmt/blob/HEAD/fairseq/checkpoint_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"df40d96cc20e7f57"}},{"code_sha256_prefix":"b3616a62387703cb","entry":"save_checkpoint","repo":"jerinphilip/fairseq-ilmt","repo_kind":"listed","path":"fairseq/checkpoint_utils.py","file_url":"https://github.com/jerinphilip/fairseq-ilmt/blob/HEAD/fairseq/checkpoint_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"b3616a62387703cb"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}