{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/transliteration","name":"Transliteration","slug":"transliteration","description_markdown":"**Transliteration** is a mechanism for converting a word in a source (foreign) language to a target language, and often adopts approaches from machine translation. In machine translation, the objective is to preserve the semantic meaning of the utterance as much as possible while following the syntactic structure in the target language. In Transliteration, the objective is to preserve the original pronunciation of the source word as much as possible while following the phonological structures of the target language.\n\nFor example, the city’s name “Manchester” has become well known by people of languages other than English. These new words are often named entities that are important in cross-lingual information retrieval, information extraction, machine translation, and often present out-of-vocabulary challenges to spoken language technologies such as automatic speech recognition, spoken keyword search, and text-to-speech.\n\n\n<span class=\"description-source\">Source: [Phonology-Augmented Statistical Framework for Machine Transliteration using Limited Linguistic Resources ](https://arxiv.org/abs/1810.03184)</span>","categories":[{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":435,"papers_with_code":54,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":5,"subtasks":0,"parent_tasks":1},"benchmarks":[],"datasets":[{"url":"/dataset/dakshina","name":"Dakshina","full_name":"Dakshina","num_papers_in_archive":14},{"url":"/dataset/tsac","name":"TSAC","full_name":"Tunisian Sentiment Analysis Corpus","num_papers_in_archive":9},{"url":"/dataset/arzen","name":"ArzEn","full_name":"Corpus of Egyptian Arabic-English Code-switching","num_papers_in_archive":3},{"url":"/dataset/anetac","name":"ANETAC","full_name":"Arabic Named Entity Transliteration and Classification","num_papers_in_archive":2},{"url":"/dataset/bianet","name":"Bianet","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/machine-translation","name":"Machine Translation"}],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":5,"rows_per_page":100,"shown":100,"of":435,"of_with_code":54,"tagged_in_all":435,"counts":{"archive_papers_tagged":435,"with_a_code_link":54,"where_syntology_ran_a_sample":6,"not_listed_spam_title":0,"listed":435,"listed_where_code_ran":6,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":4,"every_run_a_failure_of_syntologys_instrument":2,"listed_with_a_run_with_no_instrument_failure":4,"listed_every_run_a_failure_of_syntologys_instrument":2,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/applying-the-transformer-to-character-level","slug":"applying-the-transformer-to-character-level","title":"Applying the Transformer to Character-level Transduction","date":"2020-05-20","arxiv_id":"2005.10213","repositories_listed":3,"syntology":{"n":5,"n_ran":4,"n_constructed":2,"n_ran_checked":2,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"4 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/applying-the-transformer-to-character-level#ran","syntology_url":"https://syntology.ai/paper/2005.10213","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.10213"}},"official":{"repos":["shijie-wu/neural-transducer"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"url":"/paper/aksharantar-towards-building-open","slug":"aksharantar-towards-building-open","title":"Aksharantar: Open Indic-language Transliteration datasets and models for the Next Billion Users","date":"2022-05-06","arxiv_id":"2205.03018","repositories_listed":2,"syntology":null},{"url":"/paper/shuowen-jiezi-linguistically-informed","slug":"shuowen-jiezi-linguistically-informed","title":"Sub-Character Tokenization for Chinese Pretrained Language Models","date":"2021-06-01","arxiv_id":"2106.00400","repositories_listed":2,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/shuowen-jiezi-linguistically-informed#ran","syntology_url":"https://syntology.ai/paper/2106.00400","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.00400"}},"official":{"repos":["thunlp/subchartokenization"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/processing-south-asian-languages-written-in-1","slug":"processing-south-asian-languages-written-in-1","title":"Processing South Asian Languages Written in the Latin Script: the Dakshina Dataset","date":"2020-07-02","arxiv_id":"2007.01176","repositories_listed":2,"syntology":null},{"url":"/paper/universal-dependency-parsing-for-hindi","slug":"universal-dependency-parsing-for-hindi","title":"Universal Dependency Parsing for Hindi-English Code-switching","date":"2018-04-16","arxiv_id":"1804.05868","repositories_listed":2,"syntology":null},{"url":"/paper/parsipy-nlp-toolkit-for-historical-persian","slug":"parsipy-nlp-toolkit-for-historical-persian","title":"ParsiPy: NLP Toolkit for Historical Persian Texts in Python","date":"2025-03-22","arxiv_id":"2503.17810","repositories_listed":1,"syntology":null},{"url":"/paper/sinhala-transliteration-a-comparative","slug":"sinhala-transliteration-a-comparative","title":"Sinhala Transliteration: A Comparative Analysis Between Rule-based and Seq2Seq Approaches","date":"2024-12-31","arxiv_id":"2501.00529","repositories_listed":1,"syntology":null},{"url":"/paper/romanized-to-native-malayalam-script","slug":"romanized-to-native-malayalam-script","title":"Romanized to Native Malayalam Script Transliteration Using an Encoder-Decoder Framework","date":"2024-12-13","arxiv_id":"2412.09957","repositories_listed":1,"syntology":null},{"url":"/paper/gr-nlp-toolkit-an-open-source-nlp-toolkit-for","slug":"gr-nlp-toolkit-an-open-source-nlp-toolkit-for","title":"GR-NLP-TOOLKIT: An Open-Source NLP Toolkit for Modern Greek","date":"2024-12-11","arxiv_id":"2412.08520","repositories_listed":1,"syntology":null},{"url":"/paper/how-transliterations-improve-crosslingual","slug":"how-transliterations-improve-crosslingual","title":"How Transliterations Improve Crosslingual Alignment","date":"2024-09-25","arxiv_id":"2409.17326","repositories_listed":1,"syntology":null},{"url":"/paper/can-small-language-models-learn-unlearn-and","slug":"can-small-language-models-learn-unlearn-and","title":"Can Small Language Models Learn, Unlearn, and Retain Noise Patterns?","date":"2024-07-01","arxiv_id":"2407.00996","repositories_listed":1,"syntology":null},{"url":"/paper/breaking-the-script-barrier-in-multilingual","slug":"breaking-the-script-barrier-in-multilingual","title":"Breaking the Script Barrier in Multilingual Pre-Trained Language Models with Transliteration-Based Post-Training Alignment","date":"2024-06-28","arxiv_id":"2406.19759","repositories_listed":1,"syntology":null},{"url":"/paper/jailbreaking-llms-with-arabic-transliteration","slug":"jailbreaking-llms-with-arabic-transliteration","title":"Jailbreaking LLMs with Arabic Transliteration and Arabizi","date":"2024-06-26","arxiv_id":"2406.18725","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/jailbreaking-llms-with-arabic-transliteration#ran","syntology_url":"https://syntology.ai/paper/2406.18725","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.18725"}},"official":{"repos":["securedl/arabic_jailbreak"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/transmi-a-framework-to-create-strong","slug":"transmi-a-framework-to-create-strong","title":"TransMI: A Framework to Create Strong Baselines from Multilingual Pretrained Language Models for Transliterated Data","date":"2024-05-16","arxiv_id":"2405.09913","repositories_listed":1,"syntology":null},{"url":"/paper/paranames-1-0-creating-an-entity-name-corpus","slug":"paranames-1-0-creating-an-entity-name-corpus","title":"ParaNames 1.0: Creating an Entity Name Corpus for 400+ Languages using Wikidata","date":"2024-05-15","arxiv_id":"2405.09496","repositories_listed":1,"syntology":null},{"url":"/paper/translico-a-contrastive-learning-framework-to","slug":"translico-a-contrastive-learning-framework-to","title":"TransliCo: A Contrastive Learning Framework to Address the Script Barrier in Multilingual Pretrained Language Models","date":"2024-01-12","arxiv_id":"2401.06620","repositories_listed":1,"syntology":null},{"url":"/paper/towards-scene-text-to-scene-text-translation","slug":"towards-scene-text-to-scene-text-translation","title":"Show Me the World in My Language: Establishing the First Baseline for Scene-Text to Scene-Text Translation","date":"2023-08-06","arxiv_id":"2308.03024","repositories_listed":1,"syntology":null},{"url":"/paper/taqyim-evaluating-arabic-nlp-tasks-using","slug":"taqyim-evaluating-arabic-nlp-tasks-using","title":"Taqyim: Evaluating Arabic NLP Tasks Using ChatGPT Models","date":"2023-06-28","arxiv_id":"2306.16322","repositories_listed":1,"syntology":null},{"url":"/paper/deepscribe-localization-and-classification-of","slug":"deepscribe-localization-and-classification-of","title":"DeepScribe: Localization and Classification of Elamite Cuneiform Signs Via Deep Learning","date":"2023-06-02","arxiv_id":"2306.01268","repositories_listed":1,"syntology":null},{"url":"/paper/multilingual-text-to-speech-synthesis-for","slug":"multilingual-text-to-speech-synthesis-for","title":"Multilingual Text-to-Speech Synthesis for Turkic Languages Using Transliteration","date":"2023-05-25","arxiv_id":"2305.15749","repositories_listed":1,"syntology":null},{"url":"/paper/xtreme-up-a-user-centric-scarce-data","slug":"xtreme-up-a-user-centric-scarce-data","title":"XTREME-UP: A User-Centric Scarce-Data Benchmark for Under-Represented Languages","date":"2023-05-19","arxiv_id":"2305.11938","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/xtreme-up-a-user-centric-scarce-data#ran","syntology_url":"https://syntology.ai/paper/2305.11938","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.11938"}},"official":{"repos":["google-research/xtreme-up"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/beyond-arabic-software-for-perso-arabic","slug":"beyond-arabic-software-for-perso-arabic","title":"Beyond Arabic: Software for Perso-Arabic Script Manipulation","date":"2023-01-26","arxiv_id":"2301.11406","repositories_listed":1,"syntology":null},{"url":"/paper/question-answering-classification-for-amharic","slug":"question-answering-classification-for-amharic","title":"Question Answering Classification for Amharic Social Media Community Based Questions","date":"2022-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/a-machine-transliteration-tool-between-uzbek","slug":"a-machine-transliteration-tool-between-uzbek","title":"A machine transliteration tool between Uzbek alphabets","date":"2022-05-19","arxiv_id":"2205.09578","repositories_listed":1,"syntology":null},{"url":"/paper/paranames-a-massively-multilingual-entity","slug":"paranames-a-massively-multilingual-entity","title":"ParaNames: A Massively Multilingual Entity Name Corpus","date":"2022-02-28","arxiv_id":"2202.14035","repositories_listed":1,"syntology":null},{"url":"/paper/does-transliteration-help-multilingual","slug":"does-transliteration-help-multilingual","title":"Does Transliteration Help Multilingual Language Modeling?","date":"2022-01-29","arxiv_id":"2201.12501","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/does-transliteration-help-multilingual#ran","syntology_url":"https://syntology.ai/paper/2201.12501","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.12501"}},"official":{"repos":["ibraheem-moosa/xlm-indic"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/iiitt-dravidian-codemix-fire2021","slug":"iiitt-dravidian-codemix-fire2021","title":"IIITT@Dravidian-CodeMix-FIRE2021: Transliterate or translate? Sentiment analysis of code-mixed text in Dravidian languages","date":"2021-11-15","arxiv_id":"2111.07906","repositories_listed":1,"syntology":null},{"url":"/paper/orthographic-transliteration-for-kabyle","slug":"orthographic-transliteration-for-kabyle","title":"Orthographic Transliteration for Kabyle Speech Recognition","date":"2021-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/role-of-language-relatedness-in-multilingual","slug":"role-of-language-relatedness-in-multilingual","title":"Role of Language Relatedness in Multilingual Fine-tuning of Language Models: A Case Study in Indo-Aryan Languages","date":"2021-09-22","arxiv_id":"2109.10534","repositories_listed":1,"syntology":null},{"url":"/paper/cross-lingual-text-classification-of","slug":"cross-lingual-text-classification-of","title":"Cross-Lingual Text Classification of Transliterated Hindi and Malayalam","date":"2021-08-31","arxiv_id":"2108.13620","repositories_listed":1,"syntology":null},{"url":"/paper/sn-computer-science-towards-offensive","slug":"sn-computer-science-towards-offensive","title":"Towards Offensive Language Identification for Tamil Code-Mixed YouTube Comments and Posts","date":"2021-08-24","arxiv_id":"2108.10939","repositories_listed":1,"syntology":null},{"url":"/paper/specializing-multilingual-language-models-an","slug":"specializing-multilingual-language-models-an","title":"Specializing Multilingual Language Models: An Empirical Study","date":"2021-06-16","arxiv_id":"2106.09063","repositories_listed":1,"syntology":null},{"url":"/paper/exploiting-language-relatedness-for-low-web","slug":"exploiting-language-relatedness-for-low-web","title":"Exploiting Language Relatedness for Low Web-Resource Language Model Adaptation: An Indic Languages Study","date":"2021-06-07","arxiv_id":"2106.03958","repositories_listed":1,"syntology":null},{"url":"/paper/neural-string-edit-distance","slug":"neural-string-edit-distance","title":"Neural String Edit Distance","date":"2021-04-16","arxiv_id":"2104.08388","repositories_listed":1,"syntology":null},{"url":"/paper/on-biasing-transformer-attention-towards","slug":"on-biasing-transformer-attention-towards","title":"On Biasing Transformer Attention Towards Monotonicity","date":"2021-04-08","arxiv_id":"2104.03945","repositories_listed":1,"syntology":null},{"url":"/paper/a-large-scale-evaluation-of-neural-machine","slug":"a-large-scale-evaluation-of-neural-machine","title":"A Large-scale Evaluation of Neural Machine Transliteration for Indic Languages","date":"2021-04-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/towards-offensive-language-identification-for","slug":"towards-offensive-language-identification-for","title":"Towards Offensive Language Identification for Dravidian Languages","date":"2021-04-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/klpt-kurdish-language-processing-toolkit","slug":"klpt-kurdish-language-processing-toolkit","title":"KLPT – Kurdish Language Processing Toolkit","date":"2020-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/leveraging-multilingual-news-websites-for","slug":"leveraging-multilingual-news-websites-for","title":"Leveraging Multilingual News Websites for Building a Kurdish Parallel Corpus","date":"2020-10-04","arxiv_id":"2010.01554","repositories_listed":1,"syntology":null},{"url":"/paper/a-multi-cascaded-deep-model-for-bilingual-sms","slug":"a-multi-cascaded-deep-model-for-bilingual-sms","title":"A Multi-cascaded Deep Model for Bilingual SMS Classification","date":"2019-11-29","arxiv_id":"1911.13066","repositories_listed":1,"syntology":null},{"url":"/paper/event-detection-in-twitter-a-keyword-volume","slug":"event-detection-in-twitter-a-keyword-volume","title":"Event detection in Twitter: A keyword volume approach","date":"2019-01-03","arxiv_id":"1901.00570","repositories_listed":1,"syntology":null},{"url":"/paper/a-rule-based-kurdish-text-transliteration","slug":"a-rule-based-kurdish-text-transliteration","title":"A Rule-based Kurdish Text Transliteration System","date":"2018-11-26","arxiv_id":"1811.10278","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-sequence-labeling-with-actor-critic","slug":"efficient-sequence-labeling-with-actor-critic","title":"Efficient Sequence Labeling with Actor-Critic Training","date":"2018-09-30","arxiv_id":"1810.00428","repositories_listed":1,"syntology":null},{"url":"/paper/bootstrapping-transliteration-with","slug":"bootstrapping-transliteration-with","title":"Bootstrapping Transliteration with Constrained Discovery for Low-Resource Languages","date":"2018-09-20","arxiv_id":"1809.07807","repositories_listed":1,"syntology":null},{"url":"/paper/design-challenges-in-named-entity","slug":"design-challenges-in-named-entity","title":"Design Challenges in Named Entity Transliteration","date":"2018-08-07","arxiv_id":"1808.02563","repositories_listed":1,"syntology":null},{"url":"/paper/neural-machine-translation-techniques-for","slug":"neural-machine-translation-techniques-for","title":"Neural Machine Translation Techniques for Named Entity Transliteration","date":"2018-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/creating-a-translation-matrix-of-the-bibleas","slug":"creating-a-translation-matrix-of-the-bibleas","title":"Creating a Translation Matrix of the Bible's Names Across 591 Languages","date":"2018-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/creating-large-scale-multilingual-cognate","slug":"creating-large-scale-multilingual-cognate","title":"Creating Large-Scale Multilingual Cognate Tables","date":"2018-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/how-grammatical-is-character-level-neural","slug":"how-grammatical-is-character-level-neural","title":"How Grammatical is Character-level Neural Machine Translation? Assessing MT Quality with Contrastive Translation Pairs","date":"2016-12-14","arxiv_id":"1612.04629","repositories_listed":1,"syntology":null},{"url":"/paper/sequence-to-sequence-neural-network-models","slug":"sequence-to-sequence-neural-network-models","title":"Sequence-to-sequence neural network models for transliteration","date":"2016-10-29","arxiv_id":"1610.09565","repositories_listed":1,"syntology":null},{"url":"/paper/an-empirical-study-of-chinese-name-matching","slug":"an-empirical-study-of-chinese-name-matching","title":"An Empirical Study of Chinese Name Matching and Applications","date":"2015-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/bilingual-dictionaries-for-all-eu-languages","slug":"bilingual-dictionaries-for-all-eu-languages","title":"Bilingual dictionaries for all EU languages","date":"2014-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/context-independent-term-mapper-for-european","slug":"context-independent-term-mapper-for-european","title":"Context Independent Term Mapper for European Languages","date":"2013-09-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/an-ensemble-model-of-word-based-and-character","slug":"an-ensemble-model-of-word-based-and-character","title":"An Ensemble Model of Word-based and Character-based Models for Japanese and Chinese Input Method","date":"2012-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":null,"slug":"optimizing-multilingual-text-to-speech-with","title":"Optimizing Multilingual Text-To-Speech with Accents & Emotions","date":"2025-06-19","arxiv_id":"2506.16310","repositories_listed":0,"syntology":null},{"url":null,"slug":"rethinking-hate-speech-detection-on-social","title":"Rethinking Hate Speech Detection on Social Media: Can LLMs Replace Traditional Models?","date":"2025-06-15","arxiv_id":"2506.12744","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-specialization-benchmarking-llms-for","title":"Beyond Specialization: Benchmarking LLMs for Transliteration of Indian Languages","date":"2025-05-26","arxiv_id":"2505.19851","repositories_listed":0,"syntology":null},{"url":null,"slug":"lost-in-transliteration-bridging-the-script","title":"Lost in Transliteration: Bridging the Script Gap in Neural IR","date":"2025-05-13","arxiv_id":"2505.08411","repositories_listed":0,"syntology":null},{"url":null,"slug":"bridging-the-gap-an-intermediate-language-for","title":"Bridging the Gap: An Intermediate Language for Enhanced and Cost-Effective Grapheme-to-Phoneme Conversion with Homographs with Multiple Pronunciations Disambiguation","date":"2025-05-10","arxiv_id":"2505.06599","repositories_listed":0,"syntology":null},{"url":null,"slug":"proper-name-diacritization-for-arabic","title":"Proper Name Diacritization for Arabic Wikipedia: A Benchmark Dataset","date":"2025-05-05","arxiv_id":"2505.02656","repositories_listed":0,"syntology":null},{"url":null,"slug":"low-resource-transliteration-for-roman-urdu","title":"Low-Resource Transliteration for Roman-Urdu and Urdu Using Transformer-Based Models","date":"2025-03-27","arxiv_id":"2503.21530","repositories_listed":0,"syntology":null},{"url":null,"slug":"connecting-the-persian-speaking-world-through","title":"Connecting the Persian-speaking World through Transliteration","date":"2025-02-27","arxiv_id":"2502.20047","repositories_listed":0,"syntology":null},{"url":null,"slug":"nusaaksara-a-multimodal-and-multilingual","title":"NusaAksara: A Multimodal and Multilingual Benchmark for Preserving Indonesian Indigenous Scripts","date":"2025-02-25","arxiv_id":"2502.18148","repositories_listed":0,"syntology":null},{"url":null,"slug":"linguistic-analysis-of-sinhala-youtube","title":"Linguistic Analysis of Sinhala YouTube Comments on Sinhala Music Videos: A Dataset Study","date":"2025-01-28","arxiv_id":"2501.18633","repositories_listed":0,"syntology":null},{"url":null,"slug":"indonlp-2025-shared-task-on-real-time-reverse","title":"IndoNLP 2025: Shared Task on Real-Time Reverse Transliteration for Romanized Indo-Aryan languages","date":"2025-01-10","arxiv_id":"2501.05816","repositories_listed":0,"syntology":null},{"url":null,"slug":"when-llms-struggle-reference-less-translation","title":"When LLMs Struggle: Reference-less Translation Evaluation for Low-resource Languages","date":"2025-01-08","arxiv_id":"2501.04473","repositories_listed":0,"syntology":null},{"url":null,"slug":"lama-ut-language-agnostic-multilingual-asr","title":"LAMA-UT: Language Agnostic Multilingual ASR through Orthography Unification and Language-Specific Transliteration","date":"2024-12-19","arxiv_id":"2412.15299","repositories_listed":0,"syntology":null},{"url":null,"slug":"transliterated-zero-shot-domain-adaptation","title":"Transliterated Zero-Shot Domain Adaptation for Automatic Speech Recognition","date":"2024-12-15","arxiv_id":"2412.11185","repositories_listed":0,"syntology":null},{"url":null,"slug":"polyipa-multilingual-phoneme-to-grapheme","title":"PolyIPA -- Multilingual Phoneme-to-Grapheme Conversion Model","date":"2024-12-12","arxiv_id":"2412.09102","repositories_listed":0,"syntology":null},{"url":null,"slug":"ayutthayaalpha-a-thai-latin-script","title":"AyutthayaAlpha: A Thai-Latin Script Transliteration Transformer","date":"2024-12-05","arxiv_id":"2412.03877","repositories_listed":0,"syntology":null},{"url":"/paper/towards-cross-cultural-machine-translation","slug":"towards-cross-cultural-machine-translation","title":"Towards Cross-Cultural Machine Translation with Retrieval-Augmented Generation from Multilingual Knowledge Graphs","date":"2024-10-17","arxiv_id":"2410.14057","repositories_listed":0,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/towards-cross-cultural-machine-translation#ran","syntology_url":"https://syntology.ai/paper/2410.14057","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.14057"}},"official":null}},{"url":null,"slug":"chakmanmt-a-low-resource-machine-translation","title":"ChakmaNMT: A Low-resource Machine Translation On Chakma Language","date":"2024-10-14","arxiv_id":"2410.10219","repositories_listed":0,"syntology":null},{"url":null,"slug":"uniglyph-a-seven-segment-script-for-universal","title":"UniGlyph: A Seven-Segment Script for Universal Language Representation","date":"2024-10-11","arxiv_id":"2410.08974","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-two-stage-transliteration-approach-to","title":"A two-stage transliteration approach to improve performance of a multilingual ASR","date":"2024-10-09","arxiv_id":"2410.14709","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-the-role-of-transliteration-in-in","title":"Exploring the Role of Transliteration in In-Context Learning for Low-resource Languages Written in Non-Latin Scripts","date":"2024-07-02","arxiv_id":"2407.02320","repositories_listed":0,"syntology":null},{"url":null,"slug":"review-of-computational-epigraphy","title":"Review of Computational Epigraphy","date":"2024-06-03","arxiv_id":"2406.06570","repositories_listed":0,"syntology":null},{"url":null,"slug":"swa-bhasha-message-based-singlish-to-sinhala","title":"Swa Bhasha: Message-Based Singlish to Sinhala Transliteration","date":"2024-04-20","arxiv_id":"2404.13350","repositories_listed":0,"syntology":null},{"url":null,"slug":"charles-translator-a-machine-translation","title":"Charles Translator: A Machine Translation System between Ukrainian and Czech","date":"2024-04-10","arxiv_id":"2404.06964","repositories_listed":0,"syntology":null},{"url":null,"slug":"cost-performance-optimization-for-processing","title":"Cost-Performance Optimization for Processing Low-Resource Language Tasks Using Commercial LLMs","date":"2024-03-08","arxiv_id":"2403.05434","repositories_listed":0,"syntology":null},{"url":null,"slug":"training-a-bilingual-language-model-by","title":"Training a Bilingual Language Model by Mapping Tokens onto a Shared Character Space","date":"2024-02-25","arxiv_id":"2402.16065","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-lingual-transfer-from-related-languages","title":"Cross-Lingual Transfer from Related Languages: Treating Low-Resource Maltese as Multilingual Code-Switching","date":"2024-01-30","arxiv_id":"2401.16895","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-detection-for-transliterated-content","title":"Language Detection for Transliterated Content","date":"2024-01-09","arxiv_id":"2401.04619","repositories_listed":0,"syntology":null},{"url":null,"slug":"code-mixed-text-to-speech-synthesis-under-low","title":"Code-Mixed Text to Speech Synthesis under Low-Resource Constraints","date":"2023-12-02","arxiv_id":"2312.01103","repositories_listed":0,"syntology":null},{"url":null,"slug":"character-level-bangla-text-to-ipa","title":"Character-Level Bangla Text-to-IPA Transcription Using Transformer Architecture with Sequence Alignment","date":"2023-11-07","arxiv_id":"2311.03792","repositories_listed":0,"syntology":null},{"url":null,"slug":"benllmeval-a-comprehensive-evaluation-into","title":"BenLLMEval: A Comprehensive Evaluation into the Potentials and Pitfalls of Large Language Models on Bengali NLP","date":"2023-09-22","arxiv_id":"2309.13173","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-linguistic-similarity-and-zero-shot","title":"Exploring Linguistic Similarity and Zero-Shot Learning for Multilingual Translation of Dravidian Languages","date":"2023-08-10","arxiv_id":"2308.05574","repositories_listed":0,"syntology":null},{"url":null,"slug":"multilingual-neural-machine-translation-2","title":"Multilingual Neural Machine Translation System for Indic to Indic Languages","date":"2023-06-22","arxiv_id":"2306.12693","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-cross-lingual-mappings-for-data","title":"Learning Cross-lingual Mappings for Data Augmentation to Improve Low-Resource Speech Recognition","date":"2023-06-14","arxiv_id":"2306.08577","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-transliteration-between-sindhi","title":"Towards Transliteration between Sindhi Scripts from Devanagari to Perso-Arabic","date":"2023-05-12","arxiv_id":"2305.07365","repositories_listed":0,"syntology":null},{"url":null,"slug":"investigating-lexical-sharing-in-multilingual","title":"Investigating Lexical Sharing in Multilingual Machine Translation for Indian Languages","date":"2023-05-04","arxiv_id":"2305.03207","repositories_listed":0,"syntology":null},{"url":null,"slug":"romanization-based-large-scale-adaptation-of","title":"Romanization-based Large-scale Adaptation of Multilingual Language Models","date":"2023-04-18","arxiv_id":"2304.08865","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-language-agnostic-wer","title":"Unsupervised Language agnostic WER Standardization","date":"2023-03-09","arxiv_id":"2303.05046","repositories_listed":0,"syntology":null},{"url":null,"slug":"epik-eliminating-multi-model-pipelines-with","title":"EPIK: Eliminating multi-model Pipelines with Knowledge-distillation","date":"2022-11-27","arxiv_id":"2211.14920","repositories_listed":0,"syntology":null},{"url":"/paper/benchmarking-evaluation-metrics-for-code","slug":"benchmarking-evaluation-metrics-for-code","title":"Benchmarking Evaluation Metrics for Code-Switching Automatic Speech Recognition","date":"2022-11-22","arxiv_id":"2211.16319","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-zero-shot-code-switched-speech","title":"Towards Zero-Shot Code-Switched Speech Recognition","date":"2022-11-02","arxiv_id":"2211.01458","repositories_listed":0,"syntology":null},{"url":null,"slug":"dude-dual-decoder-multilingual-asr-for-indian","title":"DuDe: Dual-Decoder Multilingual ASR for Indian Languages using Common Label Set","date":"2022-10-30","arxiv_id":"2210.16739","repositories_listed":0,"syntology":null},{"url":null,"slug":"gui-at-mixmt-2022-english-hinglish-an-mt","title":"Gui at MixMT 2022 : English-Hinglish: An MT approach for translation of code mixed data","date":"2022-10-21","arxiv_id":"2210.12215","repositories_listed":0,"syntology":null},{"url":null,"slug":"english-to-bengali-multimodal-neural-machine","title":"English to Bengali Multimodal Neural Machine Translation using Transliteration-based Phrase Pairs Augmentation","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"investigation-of-english-to-hindi-multimodal","title":"Investigation of English to Hindi Multimodal Neural Machine Translation using Transliteration-based Phrase Pairs Augmentation","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"investigation-of-multilingual-neural-machine","title":"Investigation of Multilingual Neural Machine Translation for Indian Languages","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"syntology_records":6,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":6,"papers_where_code_ran_first_page":"/task/transliteration/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":5,"url":"/task/transliteration/papers/2","json":"/task/transliteration/papers/2.json","rows":100},{"order":"archive","page":3,"of":5,"url":"/task/transliteration/papers/3","json":"/task/transliteration/papers/3.json","rows":100},{"order":"archive","page":4,"of":5,"url":"/task/transliteration/papers/4","json":"/task/transliteration/papers/4.json","rows":100},{"order":"archive","page":5,"of":5,"url":"/task/transliteration/papers/5","json":"/task/transliteration/papers/5.json","rows":35},{"order":"ran","page":1,"of":1,"url":"/task/transliteration/papers/ran/1","json":"/task/transliteration/papers/ran/1.json","rows":6}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"8403154b8fcdbaf82fffcab81bb59f94cdca6dce23706ae0d965e5722fd0bb3d","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}