{"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/27","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":27,"pages_in_order":108,"rows_per_page":100,"rows":[2601,2700],"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/26","next":"/task/machine-translation/papers/28","papers":[{"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":"localizing-ai-evaluating-open-weight-language","title":"Localizing AI: Evaluating Open-Weight Language Models for Languages of Baltic States","date":"2025-01-07","arxiv_id":"2501.03952","repositories_listed":0,"syntology":null},{"url":null,"slug":"semantically-cohesive-word-grouping-in-indian","title":"Semantically Cohesive Word Grouping in Indian Languages","date":"2025-01-07","arxiv_id":"2501.03988","repositories_listed":0,"syntology":null},{"url":null,"slug":"quality-estimation-based-feedback-training","title":"Quality Estimation based Feedback Training for Improving Pronoun Translation","date":"2025-01-06","arxiv_id":"2501.03008","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-few-shot-prompting-for-machine","title":"Adaptive Few-shot Prompting for Machine Translation with Pre-trained Language Models","date":"2025-01-03","arxiv_id":"2501.01679","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-review-of-faithfulness-metrics-for","title":"A review of faithfulness metrics for hallucination assessment in Large Language Models","date":"2024-12-31","arxiv_id":"2501.00269","repositories_listed":0,"syntology":null},{"url":null,"slug":"text-classification-neural-networks-vs","title":"Text Classification: Neural Networks VS Machine Learning Models VS Pre-trained Models","date":"2024-12-30","arxiv_id":"2412.21022","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-entertainment-translation-for","title":"Enhancing Entertainment Translation for Indian Languages using Adaptive Context, Style and LLMs","date":"2024-12-29","arxiv_id":"2412.20440","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-neural-no-resource-language","title":"Towards Neural No-Resource Language Translation: A Comparative Evaluation of Approaches","date":"2024-12-29","arxiv_id":"2412.20584","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-linguistic-examination-of-machine","title":"Cross-Linguistic Examination of Machine Translation Transfer Learning","date":"2024-12-27","arxiv_id":"2501.00045","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploiting-domain-specific-parallel-data-on","title":"Exploiting Domain-Specific Parallel Data on Multilingual Language Models for Low-resource Language Translation","date":"2024-12-27","arxiv_id":"2412.19522","repositories_listed":0,"syntology":null},{"url":null,"slug":"advancing-explainability-in-neural-machine","title":"Advancing Explainability in Neural Machine Translation: Analytical Metrics for Attention and Alignment Consistency","date":"2024-12-24","arxiv_id":"2412.18669","repositories_listed":0,"syntology":null},{"url":null,"slug":"coam-corpus-of-all-type-multiword-expressions","title":"CoAM: Corpus of All-Type Multiword Expressions","date":"2024-12-24","arxiv_id":"2412.18151","repositories_listed":0,"syntology":null},{"url":null,"slug":"ensuring-consistency-for-in-image-translation","title":"Ensuring Consistency for In-Image Translation","date":"2024-12-24","arxiv_id":"2412.18139","repositories_listed":0,"syntology":null},{"url":null,"slug":"m-ped-multi-prompt-ensemble-decoding-for","title":"M-Ped: Multi-Prompt Ensemble Decoding for Large Language Models","date":"2024-12-24","arxiv_id":"2412.18299","repositories_listed":0,"syntology":null},{"url":null,"slug":"multiple-references-with-meaningful","title":"Multiple References with Meaningful Variations Improve Literary Machine Translation","date":"2024-12-24","arxiv_id":"2412.18707","repositories_listed":0,"syntology":null},{"url":null,"slug":"domain-adapted-machine-translation-what-does","title":"Domain adapted machine translation: What does catastrophic forgetting forget and why?","date":"2024-12-23","arxiv_id":"2412.17537","repositories_listed":0,"syntology":null},{"url":null,"slug":"erupd-english-to-roman-urdu-parallel-dataset","title":"ERUPD -- English to Roman Urdu Parallel Dataset","date":"2024-12-23","arxiv_id":"2412.17562","repositories_listed":0,"syntology":null},{"url":null,"slug":"investigating-length-issues-in-document-level","title":"Investigating Length Issues in Document-level Machine Translation","date":"2024-12-23","arxiv_id":"2412.17592","repositories_listed":0,"syntology":null},{"url":null,"slug":"reconsidering-smt-over-nmt-for-closely","title":"Reconsidering SMT Over NMT for Closely Related Languages: A Case Study of Persian-Hindi Pair","date":"2024-12-22","arxiv_id":"2412.16877","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-thorough-investigation-into-the-application","title":"A Thorough Investigation into the Application of Deep CNN for Enhancing Natural Language Processing Capabilities","date":"2024-12-20","arxiv_id":"2412.15900","repositories_listed":0,"syntology":null},{"url":null,"slug":"development-of-a-large-scale-dataset-of-chest","title":"Development of a Large-scale Dataset of Chest Computed Tomography Reports in Japanese and a High-performance Finding Classification Model","date":"2024-12-20","arxiv_id":"2412.15907","repositories_listed":0,"syntology":null},{"url":null,"slug":"promptoptme-error-aware-prompt-compression","title":"PromptOptMe: Error-Aware Prompt Compression for LLM-based MT Evaluation Metrics","date":"2024-12-20","arxiv_id":"2412.16120","repositories_listed":0,"syntology":null},{"url":null,"slug":"mention-attention-for-pronoun-translation","title":"Mention Attention for Pronoun Translation","date":"2024-12-19","arxiv_id":"2412.14829","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-evolution-knowledge-distillation-for-llm","title":"Self-Evolution Knowledge Distillation for LLM-based Machine Translation","date":"2024-12-19","arxiv_id":"2412.15303","repositories_listed":0,"syntology":null},{"url":null,"slug":"time-will-tell-timing-side-channels-via","title":"Time Will Tell: Timing Side Channels via Output Token Count in Large Language Models","date":"2024-12-19","arxiv_id":"2412.15431","repositories_listed":0,"syntology":null},{"url":null,"slug":"transcribing-and-translating-fast-and-slow","title":"Transcribing and Translating, Fast and Slow: Joint Speech Translation and Recognition","date":"2024-12-19","arxiv_id":"2412.15415","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-very-rare-for-all","title":"Language verY Rare for All","date":"2024-12-18","arxiv_id":"2412.13924","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-role-of-handling-attributive-nouns-in","title":"The Role of Handling Attributive Nouns in Improving Chinese-To-English Machine Translation","date":"2024-12-18","arxiv_id":"2412.14323","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-automatic-evaluation-for-image","title":"Towards Automatic Evaluation for Image Transcreation","date":"2024-12-18","arxiv_id":"2412.13717","repositories_listed":0,"syntology":null},{"url":null,"slug":"understanding-and-analyzing-model-robustness","title":"Understanding and Analyzing Model Robustness and Knowledge-Transfer in Multilingual Neural Machine Translation using TX-Ray","date":"2024-12-18","arxiv_id":"2412.13881","repositories_listed":0,"syntology":null},{"url":null,"slug":"make-imagination-clearer-stable-diffusion","title":"Make Imagination Clearer! Stable Diffusion-based Visual Imagination for Multimodal Machine Translation","date":"2024-12-17","arxiv_id":"2412.12627","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-open-source-advantage-in-large-language","title":"The Open Source Advantage in Large Language Models (LLMs)","date":"2024-12-16","arxiv_id":"2412.12004","repositories_listed":0,"syntology":null},{"url":null,"slug":"cater-leveraging-llm-to-pioneer-a","title":"CATER: Leveraging LLM to Pioneer a Multidimensional, Reference-Independent Paradigm in Translation Quality Evaluation","date":"2024-12-15","arxiv_id":"2412.11261","repositories_listed":0,"syntology":null},{"url":null,"slug":"task-oriented-dialog-systems-for-the","title":"Task-Oriented Dialog Systems for the Senegalese Wolof Language","date":"2024-12-15","arxiv_id":"2412.11203","repositories_listed":0,"syntology":null},{"url":null,"slug":"shiksha-a-technical-domain-focused","title":"Shiksha: A Technical Domain focused Translation Dataset and Model for Indian Languages","date":"2024-12-12","arxiv_id":"2412.09025","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-perspective-alignment-for-increasing","title":"Multi-perspective Alignment for Increasing Naturalness in Neural Machine Translation","date":"2024-12-11","arxiv_id":"2412.08473","repositories_listed":0,"syntology":null},{"url":null,"slug":"harnessing-transfer-learning-from-swahili","title":"Harnessing Transfer Learning from Swahili: Advancing Solutions for Comorian Dialects","date":"2024-12-09","arxiv_id":"2412.12143","repositories_listed":0,"syntology":null},{"url":null,"slug":"domain-specific-translation-with-open-source","title":"Domain-Specific Translation with Open-Source Large Language Models: Resource-Oriented Analysis","date":"2024-12-08","arxiv_id":"2412.05862","repositories_listed":0,"syntology":null},{"url":null,"slug":"paraphrase-aligned-machine-translation","title":"Paraphrase-Aligned Machine Translation","date":"2024-12-08","arxiv_id":"2412.05916","repositories_listed":0,"syntology":null},{"url":null,"slug":"promptrefine-enhancing-few-shot-performance","title":"PromptRefine: Enhancing Few-Shot Performance on Low-Resource Indic Languages with Example Selection from Related Example Banks","date":"2024-12-07","arxiv_id":"2412.05710","repositories_listed":0,"syntology":null},{"url":null,"slug":"agent-ai-with-langgraph-a-modular-framework","title":"Agent AI with LangGraph: A Modular Framework for Enhancing Machine Translation Using Large Language Models","date":"2024-12-05","arxiv_id":"2412.03801","repositories_listed":0,"syntology":null},{"url":null,"slug":"bhashaverse-translation-ecosystem-for-indian","title":"BhashaVerse : Translation Ecosystem for Indian Subcontinent Languages","date":"2024-12-05","arxiv_id":"2412.04351","repositories_listed":0,"syntology":null},{"url":null,"slug":"marco-llm-bridging-languages-via-massive","title":"Marco-LLM: Bridging Languages via Massive Multilingual Training for Cross-Lingual Enhancement","date":"2024-12-05","arxiv_id":"2412.04003","repositories_listed":0,"syntology":null},{"url":null,"slug":"representation-purification-for-end-to-end","title":"Representation Purification for End-to-End Speech Translation","date":"2024-12-05","arxiv_id":"2412.04266","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-measure-of-the-system-dependence-of","title":"A Measure of the System Dependence of Automated Metrics","date":"2024-12-04","arxiv_id":"2412.03152","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-2-step-framework-for-automated-literary","title":"A 2-step Framework for Automated Literary Translation Evaluation: Its Promises and Pitfalls","date":"2024-12-02","arxiv_id":"2412.01340","repositories_listed":0,"syntology":null},{"url":null,"slug":"homeostazis-and-sparsity-in-transformer","title":"Homeostasis and Sparsity in Transformer","date":"2024-11-30","arxiv_id":"2412.00503","repositories_listed":0,"syntology":null},{"url":null,"slug":"artificial-intelligence-contribution-to","title":"Artificial intelligence contribution to translation industry: looking back and forward","date":"2024-11-29","arxiv_id":"2411.19855","repositories_listed":0,"syntology":null},{"url":null,"slug":"clinical-document-corpora-and-assorted-domain","title":"Clinical Document Corpora and Assorted Domain Proxies: A Survey of Diversity in Corpus Design, with Focus on German Text Data","date":"2024-11-29","arxiv_id":"2412.00230","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-santali-linguistic-inclusion-building","title":"Towards Santali Linguistic Inclusion: Building the First Santali-to-English Translation Model using mT5 Transformer and Data Augmentation","date":"2024-11-29","arxiv_id":"2411.19726","repositories_listed":0,"syntology":null},{"url":null,"slug":"ustcctsu-at-semeval-2024-task-1-reducing","title":"USTCCTSU at SemEval-2024 Task 1: Reducing Anisotropy for Cross-lingual Semantic Textual Relatedness Task","date":"2024-11-28","arxiv_id":"2411.18990","repositories_listed":0,"syntology":null},{"url":null,"slug":"aligning-pre-trained-models-for-spoken","title":"Aligning Pre-trained Models for Spoken Language Translation","date":"2024-11-27","arxiv_id":"2411.18294","repositories_listed":0,"syntology":null},{"url":null,"slug":"diffslt-enhancing-diversity-in-sign-language","title":"DiffSLT: Enhancing Diversity in Sign Language Translation via Diffusion Model","date":"2024-11-26","arxiv_id":"2411.17248","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-jack-of-all-trades-to-master-of-one","title":"From Jack of All Trades to Master of One: Specializing LLM-based Autoraters to a Test Set","date":"2024-11-23","arxiv_id":"2411.15387","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-mteb-to-mtob-retrieval-augmented","title":"From MTEB to MTOB: Retrieval-Augmented Classification for Descriptive Grammars","date":"2024-11-23","arxiv_id":"2411.15577","repositories_listed":0,"syntology":null},{"url":null,"slug":"swissadt-an-audio-description-translation","title":"SwissADT: An Audio Description Translation System for Swiss Languages","date":"2024-11-22","arxiv_id":"2411.14967","repositories_listed":0,"syntology":null},{"url":null,"slug":"generative-fuzzy-system-for-sequence","title":"Generative Fuzzy System for Sequence Generation","date":"2024-11-21","arxiv_id":"2411.13867","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comparative-study-of-text-retrieval-models","title":"A Comparative Study of Text Retrieval Models on DaReCzech","date":"2024-11-19","arxiv_id":"2411.12921","repositories_listed":0,"syntology":null},{"url":null,"slug":"low-resource-machine-translation-what-for-who","title":"Low-resource Machine Translation: what for? who for? An observational study on a dedicated Tetun language translation service","date":"2024-11-19","arxiv_id":"2411.12262","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-shortcut-learning-in-multilingual","title":"On the Shortcut Learning in Multilingual Neural Machine Translation","date":"2024-11-15","arxiv_id":"2411.10581","repositories_listed":0,"syntology":null},{"url":null,"slug":"systolic-arrays-and-structured-pruning-co","title":"Systolic Arrays and Structured Pruning Co-design for Efficient Transformers in Edge Systems","date":"2024-11-15","arxiv_id":"2411.10285","repositories_listed":0,"syntology":null},{"url":null,"slug":"code-mixed-llm-improve-large-language-models","title":"Code-mixed LLM: Improve Large Language Models' Capability to Handle Code-Mixing through Reinforcement Learning from AI Feedback","date":"2024-11-13","arxiv_id":"2411.09073","repositories_listed":0,"syntology":null},{"url":null,"slug":"direct-speech-to-speech-neural-machine","title":"Direct Speech-to-Speech Neural Machine Translation: A Survey","date":"2024-11-13","arxiv_id":"2411.14453","repositories_listed":0,"syntology":null},{"url":null,"slug":"refining-translations-with-llms-a-constraint","title":"Refining Translations with LLMs: A Constraint-Aware Iterative Prompting Approach","date":"2024-11-13","arxiv_id":"2411.08348","repositories_listed":0,"syntology":null},{"url":null,"slug":"theoretical-analysis-of-byte-pair-encoding","title":"Theoretical Analysis of Byte-Pair Encoding","date":"2024-11-13","arxiv_id":"2411.08671","repositories_listed":0,"syntology":null},{"url":null,"slug":"isochrony-controlled-speech-to-text","title":"Isochrony-Controlled Speech-to-Text Translation: A study on translating from Sino-Tibetan to Indo-European Languages","date":"2024-11-11","arxiv_id":"2411.07387","repositories_listed":0,"syntology":null},{"url":null,"slug":"cull-mt-compression-using-language-and-layer","title":"CULL-MT: Compression Using Language and Layer pruning for Machine Translation","date":"2024-11-10","arxiv_id":"2411.06506","repositories_listed":0,"syntology":null},{"url":null,"slug":"fineweb-edu-ar-machine-translated-corpus-to","title":"Fineweb-Edu-Ar: Machine-translated Corpus to Support Arabic Small Language Models","date":"2024-11-10","arxiv_id":"2411.06402","repositories_listed":0,"syntology":null},{"url":null,"slug":"quasi-random-multi-sample-inference-for-large","title":"Quasi-random Multi-Sample Inference for Large Language Models","date":"2024-11-09","arxiv_id":"2411.06251","repositories_listed":0,"syntology":null},{"url":null,"slug":"fine-grained-reward-optimization-for-machine","title":"Fine-Grained Reward Optimization for Machine Translation using Error Severity Mappings","date":"2024-11-08","arxiv_id":"2411.05986","repositories_listed":0,"syntology":null},{"url":null,"slug":"prompt-engineering-using-gpt-for-word-level","title":"Prompt Engineering Using GPT for Word-Level Code-Mixed Language Identification in Low-Resource Dravidian Languages","date":"2024-11-06","arxiv_id":"2411.04025","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-models-and-cycle-consistency-for","title":"Language Models and Cycle Consistency for Self-Reflective Machine Translation","date":"2024-11-05","arxiv_id":"2411.02791","repositories_listed":0,"syntology":null},{"url":null,"slug":"predictor-corrector-enhanced-transformers","title":"Predictor-Corrector Enhanced Transformers with Exponential Moving Average Coefficient Learning","date":"2024-11-05","arxiv_id":"2411.03042","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-llms-for-mt-in-crisis-scenarios-a","title":"Leveraging LLMs for MT in Crisis Scenarios: a blueprint for low-resource languages","date":"2024-10-31","arxiv_id":"2410.23890","repositories_listed":0,"syntology":null},{"url":null,"slug":"anticipating-future-with-large-language-model","title":"Anticipating Future with Large Language Model for Simultaneous Machine Translation","date":"2024-10-29","arxiv_id":"2410.22499","repositories_listed":0,"syntology":null},{"url":null,"slug":"crat-a-multi-agent-framework-for-causality","title":"CRAT: A Multi-Agent Framework for Causality-Enhanced Reflective and Retrieval-Augmented Translation with Large Language Models","date":"2024-10-28","arxiv_id":"2410.21067","repositories_listed":0,"syntology":null},{"url":null,"slug":"current-state-of-the-art-of-bias-detection","title":"Current State-of-the-Art of Bias Detection and Mitigation in Machine Translation for African and European Languages: a Review","date":"2024-10-28","arxiv_id":"2410.21126","repositories_listed":0,"syntology":null},{"url":null,"slug":"grammamt-improving-machine-translation-with","title":"GrammaMT: Improving Machine Translation with Grammar-Informed In-Context Learning","date":"2024-10-24","arxiv_id":"2410.18702","repositories_listed":0,"syntology":null},{"url":null,"slug":"llm-tree-search","title":"LLM Tree Search","date":"2024-10-24","arxiv_id":"2410.19117","repositories_listed":0,"syntology":null},{"url":null,"slug":"we-augmented-whisper-with-knn-and-you-won-t","title":"kNN For Whisper And Its Effect On Bias And Speaker Adaptation","date":"2024-10-24","arxiv_id":"2410.18850","repositories_listed":0,"syntology":null},{"url":null,"slug":"dialectal-and-low-resource-machine","title":"Dialectal and Low-Resource Machine Translation for Aromanian","date":"2024-10-23","arxiv_id":"2410.17728","repositories_listed":0,"syntology":null},{"url":null,"slug":"responsible-multilingual-large-language","title":"Responsible Multilingual Large Language Models: A Survey of Development, Applications, and Societal Impact","date":"2024-10-23","arxiv_id":"2410.17532","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-general-purpose-large-language-models","title":"Can General-Purpose Large Language Models Generalize to English-Thai Machine Translation ?","date":"2024-10-22","arxiv_id":"2410.17145","repositories_listed":0,"syntology":null},{"url":null,"slug":"analyzing-context-contributions-in-llm-based","title":"Analyzing Context Contributions in LLM-based Machine Translation","date":"2024-10-21","arxiv_id":"2410.16246","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-terminology-integration-for-llm","title":"Efficient Terminology Integration for LLM-based Translation in Specialized Domains","date":"2024-10-21","arxiv_id":"2410.15690","repositories_listed":0,"syntology":null},{"url":null,"slug":"generalized-probabilistic-attention-mechanism","title":"Generalized Probabilistic Attention Mechanism in Transformers","date":"2024-10-21","arxiv_id":"2410.15578","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-from-others-mistakes-finetuning","title":"Learning from others' mistakes: Finetuning machine translation models with span-level error annotations","date":"2024-10-21","arxiv_id":"2410.16509","repositories_listed":0,"syntology":null},{"url":null,"slug":"subword-embedding-from-bytes-gains-privacy","title":"Subword Embedding from Bytes Gains Privacy without Sacrificing Accuracy and Complexity","date":"2024-10-21","arxiv_id":"2410.16410","repositories_listed":0,"syntology":null},{"url":null,"slug":"grammatical-error-correction-for-low-resource","title":"Grammatical Error Correction for Low-Resource Languages: The Case of Zarma","date":"2024-10-20","arxiv_id":"2410.15539","repositories_listed":0,"syntology":null},{"url":null,"slug":"analyzing-context-utilization-of-llms-in","title":"Analyzing Context Utilization of LLMs in Document-Level Translation","date":"2024-10-18","arxiv_id":"2410.14391","repositories_listed":0,"syntology":null},{"url":null,"slug":"mitigating-embedding-collapse-in-diffusion","title":"Improving Vector-Quantized Image Modeling with Latent Consistency-Matching Diffusion","date":"2024-10-18","arxiv_id":"2410.14758","repositories_listed":0,"syntology":null},{"url":null,"slug":"swaquad-24-qa-benchmark-dataset-in-swahili","title":"SwaQuAD-24: QA Benchmark Dataset in Swahili","date":"2024-10-18","arxiv_id":"2410.14289","repositories_listed":0,"syntology":null},{"url":null,"slug":"boosting-llm-translation-skills-without","title":"Boosting LLM Translation Skills without General Ability Loss via Rationale Distillation","date":"2024-10-17","arxiv_id":"2410.13944","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":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 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":"intgrad-mt-eliciting-llms-machine-translation","title":"IntGrad MT: Eliciting LLMs' Machine Translation Capabilities with Sentence Interpolation and Gradual MT","date":"2024-10-15","arxiv_id":"2410.11693","repositories_listed":0,"syntology":null},{"url":null,"slug":"is-hate-lost-in-translation-evaluation-of","title":"\"Is Hate Lost in Translation?\": Evaluation of Multilingual LGBTQIA+ Hate Speech Detection","date":"2024-10-15","arxiv_id":"2410.11230","repositories_listed":0,"syntology":null},{"url":null,"slug":"pmmt-preference-alignment-in-multilingual","title":"PMMT: Preference Alignment in Multilingual Machine Translation via LLM Distillation","date":"2024-10-15","arxiv_id":"2410.11410","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-human-only-evaluating-human-machine","title":"Beyond Human-Only: Evaluating Human-Machine Collaboration for Collecting High-Quality Translation Data","date":"2024-10-14","arxiv_id":"2410.11056","repositories_listed":0,"syntology":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}],"record_sha256":"81b152ac2090b966b2927e4a1bcddbe9a73aa4c1f66d3d5d6a99a7769fd929be","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}