{"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/machine-translation/papers/26","list_of":"/task/machine-translation","task":"Machine Translation","archive":{"snapshot":"2025-07-28"},"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)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":26,"pages_in_order":108,"rows_per_page":100,"rows":[2501,2600],"of":10752,"counts":{"archive_papers_tagged":10752,"with_a_code_link":2444,"where_syntology_ran_a_sample":477,"not_listed_spam_title":0,"listed":10752,"listed_where_code_ran":477,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":381,"every_run_a_failure_of_syntologys_instrument":96,"listed_with_a_run_with_no_instrument_failure":381,"listed_every_run_a_failure_of_syntologys_instrument":96,"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"},"first_page":"/task/machine-translation","prev":"/task/machine-translation/papers/25","next":"/task/machine-translation/papers/27","papers":[{"url":null,"slug":"clirudit-cross-lingual-information-retrieval","title":"CLIRudit: Cross-Lingual Information Retrieval of Scientific Documents","date":"2025-04-22","arxiv_id":"2504.16264","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-evaluation-metrics-for-document","title":"Automatic Evaluation Metrics for Document-level Translation: Overview, Challenges and Trends","date":"2025-04-21","arxiv_id":"2504.14804","repositories_listed":0,"syntology":null},{"url":null,"slug":"translation-analytics-for-freelancers-i","title":"Translation Analytics for Freelancers: I. Introduction, Data Preparation, Baseline Evaluations","date":"2025-04-20","arxiv_id":"2504.14619","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-multimodal-recaptioning-framework-to","title":"A Multimodal Recaptioning Framework to Account for Perceptual Diversity in Multilingual Vision-Language Modeling","date":"2025-04-19","arxiv_id":"2504.14359","repositories_listed":0,"syntology":null},{"url":null,"slug":"are-ai-agents-the-new-machine-translation","title":"Are AI agents the new machine translation frontier? Challenges and opportunities of single- and multi-agent systems for multilingual digital communication","date":"2025-04-17","arxiv_id":"2504.12891","repositories_listed":0,"syntology":null},{"url":null,"slug":"adat-time-series-aware-adaptive-transformer","title":"ADAT: Time-Series-Aware Adaptive Transformer Architecture for Sign Language Translation","date":"2025-04-16","arxiv_id":"2504.11942","repositories_listed":0,"syntology":null},{"url":null,"slug":"deja-vu-multilingual-llm-evaluation-through","title":"Déjà Vu: Multilingual LLM Evaluation through the Lens of Machine Translation Evaluation","date":"2025-04-16","arxiv_id":"2504.11829","repositories_listed":0,"syntology":null},{"url":null,"slug":"multilingual-contextualization-of-large","title":"Multilingual Contextualization of Large Language Models for Document-Level Machine Translation","date":"2025-04-16","arxiv_id":"2504.12140","repositories_listed":0,"syntology":null},{"url":null,"slug":"askqe-question-answering-as-automatic","title":"AskQE: Question Answering as Automatic Evaluation for Machine Translation","date":"2025-04-15","arxiv_id":"2504.11582","repositories_listed":0,"syntology":null},{"url":null,"slug":"automated-python-translation","title":"Automated Python Translation","date":"2025-04-15","arxiv_id":"2504.11290","repositories_listed":0,"syntology":null},{"url":null,"slug":"morphtok-morphologically-grounded","title":"MorphTok: Morphologically Grounded Tokenization for Indian Languages","date":"2025-04-14","arxiv_id":"2504.10335","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-models-as-span-annotators","title":"Large Language Models as Span Annotators","date":"2025-04-11","arxiv_id":"2504.08697","repositories_listed":0,"syntology":null},{"url":null,"slug":"context-aware-monolingual-human-evaluation-of","title":"Context-Aware Monolingual Human Evaluation of Machine Translation","date":"2025-04-10","arxiv_id":"2504.07685","repositories_listed":0,"syntology":null},{"url":null,"slug":"deepseek-vs-o3-mini-how-well-can-reasoning","title":"DeepSeek vs. o3-mini: How Well can Reasoning LLMs Evaluate MT and Summarization?","date":"2025-04-10","arxiv_id":"2504.08120","repositories_listed":0,"syntology":null},{"url":null,"slug":"extending-creamt-leveraging-large-language","title":"Extending CREAMT: Leveraging Large Language Models for Literary Translation Post-Editing","date":"2025-04-03","arxiv_id":"2504.03045","repositories_listed":0,"syntology":null},{"url":null,"slug":"limitations-of-religious-data-and-the","title":"Limitations of Religious Data and the Importance of the Target Domain: Towards Machine Translation for Guinea-Bissau Creole","date":"2025-04-03","arxiv_id":"2504.02674","repositories_listed":0,"syntology":null},{"url":null,"slug":"bridging-the-linguistic-divide-a-survey-on","title":"Bridging the Linguistic Divide: A Survey on Leveraging Large Language Models for Machine Translation","date":"2025-04-02","arxiv_id":"2504.01919","repositories_listed":0,"syntology":null},{"url":null,"slug":"contrastscore-towards-higher-quality-less","title":"ContrastScore: Towards Higher Quality, Less Biased, More Efficient Evaluation Metrics with Contrastive Evaluation","date":"2025-04-02","arxiv_id":"2504.02106","repositories_listed":0,"syntology":null},{"url":null,"slug":"overcoming-vocabulary-constraints-with-pixel","title":"Overcoming Vocabulary Constraints with Pixel-level Fallback","date":"2025-04-02","arxiv_id":"2504.02122","repositories_listed":0,"syntology":null},{"url":null,"slug":"is-llm-the-silver-bullet-to-low-resource","title":"Is LLM the Silver Bullet to Low-Resource Languages Machine Translation?","date":"2025-03-31","arxiv_id":"2503.24102","repositories_listed":0,"syntology":null},{"url":null,"slug":"you-cannot-feed-two-birds-with-one-score-the","title":"You Cannot Feed Two Birds with One Score: the Accuracy-Naturalness Tradeoff in Translation","date":"2025-03-31","arxiv_id":"2503.24013","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-impact-of-code-switched-synthetic-data","title":"The Impact of Code-switched Synthetic Data Quality is Task Dependent: Insights from MT and ASR","date":"2025-03-30","arxiv_id":"2503.23576","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-vanilla-fine-tuning-leveraging","title":"Beyond Vanilla Fine-Tuning: Leveraging Multistage, Multilingual, and Domain-Specific Methods for Low-Resource Machine Translation","date":"2025-03-28","arxiv_id":"2503.22582","repositories_listed":0,"syntology":null},{"url":null,"slug":"non-monotonic-attention-based-read-write","title":"Non-Monotonic Attention-based Read/Write Policy Learning for Simultaneous Translation","date":"2025-03-28","arxiv_id":"2503.22051","repositories_listed":0,"syntology":null},{"url":null,"slug":"sociotechnical-effects-of-machine-translation","title":"Sociotechnical Effects of Machine Translation","date":"2025-03-26","arxiv_id":"2503.20959","repositories_listed":0,"syntology":null},{"url":null,"slug":"training-in-translation-tools-and","title":"Training in translation tools and technologies: Findings of the EMT survey 2023","date":"2025-03-26","arxiv_id":"2503.22735","repositories_listed":0,"syntology":null},{"url":null,"slug":"hausanlp-at-semeval-2025-task-2-entity-aware","title":"HausaNLP at SemEval-2025 Task 2: Entity-Aware Fine-tuning vs. Prompt Engineering in Entity-Aware Machine Translation","date":"2025-03-25","arxiv_id":"2503.19702","repositories_listed":0,"syntology":null},{"url":null,"slug":"low-resource-machine-translation-for-code","title":"Low-resource Machine Translation for Code-switched Kazakh-Russian Language Pair","date":"2025-03-25","arxiv_id":"2503.20007","repositories_listed":0,"syntology":null},{"url":null,"slug":"pad-towards-efficient-data-generation-for","title":"PAD: Towards Efficient Data Generation for Transfer Learning Using Phrase Alignment","date":"2025-03-24","arxiv_id":"2503.18250","repositories_listed":0,"syntology":null},{"url":null,"slug":"natural-language-generation-1","title":"Natural Language Generation","date":"2025-03-20","arxiv_id":"2503.16728","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-vocabularizing-training-for-neural","title":"Self-Vocabularizing Training for Neural Machine Translation","date":"2025-03-18","arxiv_id":"2503.13837","repositories_listed":0,"syntology":null},{"url":null,"slug":"new-trends-for-modern-machine-translation","title":"New Trends for Modern Machine Translation with Large Reasoning Models","date":"2025-03-13","arxiv_id":"2503.10351","repositories_listed":0,"syntology":null},{"url":null,"slug":"florenz-scaling-laws-for-systematic","title":"Florenz: Scaling Laws for Systematic Generalization in Vision-Language Models","date":"2025-03-12","arxiv_id":"2503.09443","repositories_listed":0,"syntology":null},{"url":null,"slug":"contextual-cues-in-machine-translation","title":"Contextual Cues in Machine Translation: Investigating the Potential of Multi-Source Input Strategies in LLMs and NMT Systems","date":"2025-03-10","arxiv_id":"2503.07195","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-lingual-ipa-contrastive-learning-for","title":"Cross-Lingual IPA Contrastive Learning for Zero-Shot NER","date":"2025-03-10","arxiv_id":"2503.07214","repositories_listed":0,"syntology":null},{"url":null,"slug":"assumed-identities-quantifying-gender-bias-in","title":"Assumed Identities: Quantifying Gender Bias in Machine Translation of Gender-Ambiguous Occupational Terms","date":"2025-03-06","arxiv_id":"2503.04372","repositories_listed":0,"syntology":null},{"url":null,"slug":"comparative-study-of-zero-shot-cross-lingual","title":"Comparative Study of Zero-Shot Cross-Lingual Transfer for Bodo POS and NER Tagging Using Gemini 2.0 Flash Thinking Experimental Model","date":"2025-03-06","arxiv_id":"2503.04405","repositories_listed":0,"syntology":null},{"url":null,"slug":"open-source-large-language-models-as","title":"Open-Source Large Language Models as Multilingual Crowdworkers: Synthesizing Open-Domain Dialogues in Several Languages With No Examples in Targets and No Machine Translation","date":"2025-03-05","arxiv_id":"2503.03462","repositories_listed":0,"syntology":null},{"url":null,"slug":"batchgemba-token-efficient-machine","title":"BatchGEMBA: Token-Efficient Machine Translation Evaluation with Batched Prompting and Prompt Compression","date":"2025-03-04","arxiv_id":"2503.02756","repositories_listed":0,"syntology":null},{"url":null,"slug":"fouriernat-a-fourier-mixing-based-non","title":"FourierNAT: A Fourier-Mixing-Based Non-Autoregressive Transformer for Parallel Sequence Generation","date":"2025-03-04","arxiv_id":"2503.07630","repositories_listed":0,"syntology":null},{"url":null,"slug":"co-creation-for-sign-language-processing-and","title":"Co-creation for Sign Language Processing and Machine Translation","date":"2025-03-03","arxiv_id":"2503.01553","repositories_listed":0,"syntology":null},{"url":null,"slug":"direct-speech-to-speech-translation-a-review","title":"Direct Speech to Speech Translation: A Review","date":"2025-03-03","arxiv_id":"2503.04799","repositories_listed":0,"syntology":null},{"url":null,"slug":"arabizi-vs-llms-can-the-genie-understand-the","title":"Arabizi vs LLMs: Can the Genie Understand the Language of Aladdin?","date":"2025-02-28","arxiv_id":"2502.20973","repositories_listed":0,"syntology":null},{"url":null,"slug":"do-language-models-understand-honorific","title":"Do Language Models Understand Honorific Systems in Javanese?","date":"2025-02-28","arxiv_id":"2502.20864","repositories_listed":0,"syntology":null},{"url":"/paper/alleviating-distribution-shift-in-synthetic","slug":"alleviating-distribution-shift-in-synthetic","title":"Alleviating Distribution Shift in Synthetic Data for Machine Translation Quality Estimation","date":"2025-02-27","arxiv_id":"2502.19941","repositories_listed":0,"syntology":{"n":11,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/alleviating-distribution-shift-in-synthetic#ran","syntology_url":"https://syntology.ai/paper/2502.19941","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.19941"}},"official":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":"r1-t1-fully-incentivizing-translation","title":"R1-T1: Fully Incentivizing Translation Capability in LLMs via Reasoning Learning","date":"2025-02-27","arxiv_id":"2502.19735","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-human-evaluation-in-machine","title":"Enhancing Human Evaluation in Machine Translation with Comparative Judgment","date":"2025-02-25","arxiv_id":"2502.17797","repositories_listed":0,"syntology":null},{"url":null,"slug":"urdullama-1-0-dataset-curation-preprocessing","title":"UrduLLaMA 1.0: Dataset Curation, Preprocessing, and Evaluation in Low-Resource Settings","date":"2025-02-24","arxiv_id":"2502.16961","repositories_listed":0,"syntology":null},{"url":null,"slug":"using-machine-learning-to-detect-fraudulent","title":"Using Machine Learning to Detect Fraudulent SMSs in Chichewa","date":"2025-02-24","arxiv_id":"2502.16947","repositories_listed":0,"syntology":null},{"url":"/paper/latim-measuring-latent-token-to-token","slug":"latim-measuring-latent-token-to-token","title":"LaTIM: Measuring Latent Token-to-Token Interactions in Mamba Models","date":"2025-02-21","arxiv_id":"2502.15612","repositories_listed":0,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/latim-measuring-latent-token-to-token#ran","syntology_url":"https://syntology.ai/paper/2502.15612","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.15612"}},"official":null}},{"url":null,"slug":"effects-of-prompt-length-on-domain-specific","title":"Effects of Prompt Length on Domain-specific Tasks for Large Language Models","date":"2025-02-20","arxiv_id":"2502.14255","repositories_listed":0,"syntology":null},{"url":null,"slug":"multislav-using-cross-lingual-knowledge","title":"MultiSlav: Using Cross-Lingual Knowledge Transfer to Combat the Curse of Multilinguality","date":"2025-02-20","arxiv_id":"2502.14509","repositories_listed":0,"syntology":null},{"url":null,"slug":"non-euclidean-hierarchical-representational","title":"Non-Euclidean Hierarchical Representational Learning using Hyperbolic Graph Neural Networks for Environmental Claim Detection","date":"2025-02-19","arxiv_id":"2502.13628","repositories_listed":0,"syntology":null},{"url":null,"slug":"translation-in-the-hands-of-many-centering","title":"Translation in the Hands of Many:Centering Lay Users in Machine Translation Interactions","date":"2025-02-19","arxiv_id":"2502.13780","repositories_listed":0,"syntology":null},{"url":null,"slug":"lmn-a-tool-for-generating-machine-enforceable","title":"LMN: A Tool for Generating Machine Enforceable Policies from Natural Language Access Control Rules using LLMs","date":"2025-02-18","arxiv_id":"2502.12460","repositories_listed":0,"syntology":null},{"url":null,"slug":"translate-smart-not-hard-cascaded-translation","title":"Translate Smart, not Hard: Cascaded Translation Systems with Quality-Aware Deferral","date":"2025-02-18","arxiv_id":"2502.12701","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-o1-like-llms-unlocking-reasoning","title":"Evaluating o1-Like LLMs: Unlocking Reasoning for Translation through Comprehensive Analysis","date":"2025-02-17","arxiv_id":"2502.11544","repositories_listed":0,"syntology":null},{"url":null,"slug":"identifying-gender-stereotypes-and-biases-in","title":"Identifying Gender Stereotypes and Biases in Automated Translation from English to Italian using Similarity Networks","date":"2025-02-17","arxiv_id":"2502.11611","repositories_listed":0,"syntology":null},{"url":"/paper/ancholik-ner-a-benchmark-dataset-for-bangla","slug":"ancholik-ner-a-benchmark-dataset-for-bangla","title":"ANCHOLIK-NER: A Benchmark Dataset for Bangla Regional Named Entity Recognition","date":"2025-02-16","arxiv_id":"2502.11198","repositories_listed":0,"syntology":null},{"url":null,"slug":"asymmetric-conflict-and-synergy-in-post","title":"Asymmetric Conflict and Synergy in Post-training for LLM-based Multilingual Machine Translation","date":"2025-02-16","arxiv_id":"2502.11223","repositories_listed":0,"syntology":null},{"url":null,"slug":"injecting-domain-specific-knowledge-into","title":"Injecting Domain-Specific Knowledge into Large Language Models: A Comprehensive Survey","date":"2025-02-15","arxiv_id":"2502.10708","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-translation-of-emergent","title":"Unsupervised Translation of Emergent Communication","date":"2025-02-11","arxiv_id":"2502.07552","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-text-style-transfer-evaluation-are","title":"Evaluating Text Style Transfer Evaluation: Are There Any Reliable Metrics?","date":"2025-02-07","arxiv_id":"2502.04718","repositories_listed":0,"syntology":null},{"url":null,"slug":"bouquet-dataset-benchmark-and-open-initiative","title":"BOUQuET: dataset, Benchmark and Open initiative for Universal Quality Evaluation in Translation","date":"2025-02-06","arxiv_id":"2502.04314","repositories_listed":0,"syntology":null},{"url":null,"slug":"dolfin-document-level-financial-test-set-for","title":"DOLFIN -- Document-Level Financial test set for Machine Translation","date":"2025-02-05","arxiv_id":"2502.03053","repositories_listed":0,"syntology":null},{"url":"/paper/multilingual-machine-translation-with-open","slug":"multilingual-machine-translation-with-open","title":"Multilingual Machine Translation with Open Large Language Models at Practical Scale: An Empirical Study","date":"2025-02-04","arxiv_id":"2502.02481","repositories_listed":0,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"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, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/multilingual-machine-translation-with-open#ran","syntology_url":"https://syntology.ai/paper/2502.02481","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.02481"}},"official":null}},{"url":null,"slug":"when-end-to-end-is-overkill-rethinking","title":"When End-to-End is Overkill: Rethinking Cascaded Speech-to-Text Translation","date":"2025-02-01","arxiv_id":"2502.00377","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-efficient-approach-for-machine-translation","title":"An Efficient Approach for Machine Translation on Low-resource Languages: A Case Study in Vietnamese-Chinese","date":"2025-01-31","arxiv_id":"2501.19314","repositories_listed":0,"syntology":null},{"url":null,"slug":"brain-inspired-sparse-training-enables","title":"Brain-inspired sparse training enables Transformers and LLMs to perform as fully connected","date":"2025-01-31","arxiv_id":"2501.19107","repositories_listed":0,"syntology":null},{"url":null,"slug":"overestimation-in-llm-evaluation-a-controlled","title":"Overestimation in LLM Evaluation: A Controlled Large-Scale Study on Data Contamination's Impact on Machine Translation","date":"2025-01-30","arxiv_id":"2501.18771","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-language-approach-for-quranic-qa","title":"Cross-Language Approach for Quranic QA","date":"2025-01-29","arxiv_id":"2501.17449","repositories_listed":0,"syntology":null},{"url":null,"slug":"few-shot-optimized-framework-for","title":"Few-Shot Optimized Framework for Hallucination Detection in Resource-Limited NLP Systems","date":"2025-01-28","arxiv_id":"2501.16616","repositories_listed":0,"syntology":null},{"url":null,"slug":"misspellings-in-natural-language-processing-a","title":"Misspellings in Natural Language Processing: A survey","date":"2025-01-28","arxiv_id":"2501.16836","repositories_listed":0,"syntology":null},{"url":null,"slug":"mitigating-hallucinated-translations-in-large","title":"Mitigating Hallucinated Translations in Large Language Models with Hallucination-focused Preference Optimization","date":"2025-01-28","arxiv_id":"2501.17295","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comparison-of-data-filtering-techniques-for","title":"A comparison of data filtering techniques for English-Polish LLM-based machine translation in the biomedical domain","date":"2025-01-27","arxiv_id":"2501.16533","repositories_listed":0,"syntology":null},{"url":null,"slug":"adacot-rethinking-cross-lingual-factual","title":"AdaCoT: Rethinking Cross-Lingual Factual Reasoning through Adaptive Chain-of-Thought","date":"2025-01-27","arxiv_id":"2501.16154","repositories_listed":0,"syntology":null},{"url":null,"slug":"dialup-modeling-the-language-continuum-by","title":"DialUp! Modeling the Language Continuum by Adapting Models to Dialects and Dialects to Models","date":"2025-01-27","arxiv_id":"2501.16581","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluation-of-nmt-assisted-grammar-transfer","title":"Evaluation of NMT-Assisted Grammar Transfer for a Multi-Language Configurable Data-to-Text System","date":"2025-01-27","arxiv_id":"2501.16135","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-estonian-text-simplification","title":"Improving Estonian Text Simplification through Pretrained Language Models and Custom Datasets","date":"2025-01-26","arxiv_id":"2501.15624","repositories_listed":0,"syntology":null},{"url":null,"slug":"quantum-enhanced-attention-mechanism-in-nlp-a","title":"Quantum-Enhanced Attention Mechanism in NLP: A Hybrid Classical-Quantum Approach","date":"2025-01-26","arxiv_id":"2501.15630","repositories_listed":0,"syntology":null},{"url":null,"slug":"faster-machine-translation-ensembling-with","title":"Faster Machine Translation Ensembling with Reinforcement Learning and Competitive Correction","date":"2025-01-25","arxiv_id":"2501.15219","repositories_listed":0,"syntology":null},{"url":null,"slug":"idiom-detection-in-sorani-kurdish-texts","title":"Idiom Detection in Sorani Kurdish Texts","date":"2025-01-24","arxiv_id":"2501.14528","repositories_listed":0,"syntology":null},{"url":null,"slug":"locoml-a-framework-for-real-world-ml","title":"LoCoML: A Framework for Real-World ML Inference Pipelines","date":"2025-01-24","arxiv_id":"2501.14165","repositories_listed":0,"syntology":null},{"url":null,"slug":"crpo-confidence-reward-driven-preference","title":"CRPO: Confidence-Reward Driven Preference Optimization for Machine Translation","date":"2025-01-23","arxiv_id":"2501.13927","repositories_listed":0,"syntology":null},{"url":null,"slug":"domain-specific-machine-translation-to","title":"Domain-Specific Machine Translation to Translate Medicine Brochures in English to Sorani Kurdish","date":"2025-01-23","arxiv_id":"2501.13609","repositories_listed":0,"syntology":null},{"url":null,"slug":"predicting-compact-phrasal-rewrites-with","title":"Predicting Compact Phrasal Rewrites with Large Language Models for ASR Post Editing","date":"2025-01-23","arxiv_id":"2501.13831","repositories_listed":0,"syntology":null},{"url":null,"slug":"think-outside-the-data-colonial-biases-and","title":"Think Outside the Data: Colonial Biases and Systemic Issues in Automated Moderation Pipelines for Low-Resource Languages","date":"2025-01-23","arxiv_id":"2501.13836","repositories_listed":0,"syntology":null},{"url":null,"slug":"extend-adversarial-policy-against-neural","title":"Extend Adversarial Policy Against Neural Machine Translation via Unknown Token","date":"2025-01-21","arxiv_id":"2501.12183","repositories_listed":0,"syntology":null},{"url":null,"slug":"proverbs-run-in-pairs-evaluating-proverb","title":"Proverbs Run in Pairs: Evaluating Proverb Translation Capability of Large Language Model","date":"2025-01-21","arxiv_id":"2501.11953","repositories_listed":0,"syntology":null},{"url":null,"slug":"ai-in-support-of-diversity-and-inclusion","title":"AI in Support of Diversity and Inclusion","date":"2025-01-16","arxiv_id":"2501.09534","repositories_listed":0,"syntology":null},{"url":null,"slug":"solving-the-unsolvable-translating-case-law","title":"Solving the Unsolvable: Translating Case Law in Hong Kong","date":"2025-01-16","arxiv_id":"2501.09444","repositories_listed":0,"syntology":null},{"url":null,"slug":"doc-guided-sent2sent-a-sent2sent-agent-with","title":"Doc-Guided Sent2Sent++: A Sent2Sent++ Agent with Doc-Guided memory for Document-level Machine Translation","date":"2025-01-15","arxiv_id":"2501.08523","repositories_listed":0,"syntology":null},{"url":null,"slug":"vibidirectionmt-eval-machine-translation-for","title":"ViBidirectionMT-Eval: Machine Translation for Vietnamese-Chinese and Vietnamese-Lao language pair","date":"2025-01-15","arxiv_id":"2501.08621","repositories_listed":0,"syntology":null},{"url":null,"slug":"quantifying-the-importance-of-data-alignment","title":"Quantifying the Importance of Data Alignment in Downstream Model Performance","date":"2025-01-14","arxiv_id":"2501.08496","repositories_listed":0,"syntology":null},{"url":null,"slug":"addressing-speaker-gender-bias-in-large-scale","title":"Addressing speaker gender bias in large scale speech translation systems","date":"2025-01-10","arxiv_id":"2501.05989","repositories_listed":0,"syntology":null},{"url":null,"slug":"bridging-dialects-translating-standard-bangla","title":"Bridging Dialects: Translating Standard Bangla to Regional Variants Using Neural Models","date":"2025-01-10","arxiv_id":"2501.05749","repositories_listed":0,"syntology":null},{"url":null,"slug":"finnish-squad-a-simple-approach-to-machine","title":"Finnish SQuAD: A Simple Approach to Machine Translation of Span Annotations","date":"2025-01-10","arxiv_id":"2501.05963","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-impact-of-model-scaling-on-seen-and","title":"The Impact of Model Scaling on Seen and Unseen Language Performance","date":"2025-01-10","arxiv_id":"2501.05629","repositories_listed":0,"syntology":null},{"url":null,"slug":"investigating-numerical-translation-with","title":"Investigating Numerical Translation with Large Language Models","date":"2025-01-09","arxiv_id":"2501.04927","repositories_listed":0,"syntology":null}],"record_sha256":"cad6891cd8dc836280b60992c0936cb753704477ad5e811e554be937b1af16af","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}