{"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/inltk-natural-language-toolkit-for-indic","title":"iNLTK: Natural Language Toolkit for Indic Languages","arxiv_id":"2009.12534","date":"2020-09-26","proceeding":"EMNLP (NLPOSS) 2020 11","authors":["Gaurav Arora"],"abstract":"We present iNLTK, an open-source NLP library consisting of pre-trained language models and out-of-the-box support for Data Augmentation, Textual Similarity, Sentence Embeddings, Word Embeddings, Tokenization and Text Generation in 13 Indic Languages. By using pre-trained models from iNLTK for text classification on publicly available datasets, we significantly outperform previously reported results. On these datasets, we also show that by using pre-trained models and data augmentation from iNLTK, we can achieve more than 95% of the previous best performance by using less than 10% of the training data. iNLTK is already being widely used by the community and has 40,000+ downloads, 600+ stars and 100+ forks on GitHub. The library is available at https://github.com/goru001/inltk.","url_abs":"https://arxiv.org/abs/2009.12534v2","url_pdf":"https://arxiv.org/pdf/2009.12534v2.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":"inltk-natural-language-toolkit-for-indic","repo_url":"https://github.com/goru001/inltk","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"paraphrase-generation","task_name":"Paraphrase Generation"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"sentence-embeddings","task_name":"Sentence Embeddings"},{"task_slug":"text-classification","task_name":"Text Classification"},{"task_slug":"text-generation","task_name":"Text Generation"},{"task_slug":"word-embeddings","task_name":"Word Embeddings"},{"task_slug":"text-classification-1","task_name":"text-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2009.12534","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.12534"}},"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/goru001/inltk","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":6},"by_repo_kind":{"official":{"samples":6,"ran":0,"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":0,"samples":[{"code_sha256_prefix":"e332284c5d26af5e","entry":"cos_sim","repo":"goru001/inltk","repo_kind":"official","path":"inltk/utils.py","file_url":"https://github.com/goru001/inltk/blob/HEAD/inltk/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e332284c5d26af5e"}},{"code_sha256_prefix":"1d17b0f13465166d","entry":"download_file","repo":"goru001/inltk","repo_kind":"official","path":"inltk/download_assets.py","file_url":"https://github.com/goru001/inltk/blob/HEAD/inltk/download_assets.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1d17b0f13465166d"}},{"code_sha256_prefix":"6894ddb79710d564","entry":"handle_all_caps","repo":"goru001/inltk","repo_kind":"official","path":"inltk/utils.py","file_url":"https://github.com/goru001/inltk/blob/HEAD/inltk/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6894ddb79710d564"}},{"code_sha256_prefix":"c6bd5918dc29cec3","entry":"is_english","repo":"goru001/inltk","repo_kind":"official","path":"inltk/utils.py","file_url":"https://github.com/goru001/inltk/blob/HEAD/inltk/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c6bd5918dc29cec3"}},{"code_sha256_prefix":"f8ef889fc3dcf131","entry":"setup_language","repo":"goru001/inltk","repo_kind":"official","path":"inltk/download_assets.py","file_url":"https://github.com/goru001/inltk/blob/HEAD/inltk/download_assets.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f8ef889fc3dcf131"}},{"code_sha256_prefix":"931db6cd051e7147","entry":"verify_language","repo":"goru001/inltk","repo_kind":"official","path":"inltk/download_assets.py","file_url":"https://github.com/goru001/inltk/blob/HEAD/inltk/download_assets.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"931db6cd051e7147"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}