{"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/6","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":6,"pages_in_order":108,"rows_per_page":100,"rows":[501,600],"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/5","next":"/task/machine-translation/papers/7","papers":[{"url":"/paper/multilingual-non-autoregressive-machine","slug":"multilingual-non-autoregressive-machine","title":"Multilingual Non-Autoregressive Machine Translation without Knowledge Distillation","date":"2025-02-06","arxiv_id":"2502.04537","repositories_listed":1,"syntology":null},{"url":"/paper/a-comparison-of-translation-performance","slug":"a-comparison-of-translation-performance","title":"A comparison of translation performance between DeepL and Supertext","date":"2025-02-04","arxiv_id":"2502.02577","repositories_listed":1,"syntology":null},{"url":"/paper/beyond-english-evaluating-automated","slug":"beyond-english-evaluating-automated","title":"Beyond English: Evaluating Automated Measurement of Moral Foundations in Non-English Discourse with a Chinese Case Study","date":"2025-02-04","arxiv_id":"2502.02451","repositories_listed":1,"syntology":null},{"url":"/paper/how-to-select-datapoints-for-efficient-human","slug":"how-to-select-datapoints-for-efficient-human","title":"How to Select Datapoints for Efficient Human Evaluation of NLG Models?","date":"2025-01-30","arxiv_id":"2501.18251","repositories_listed":1,"syntology":null},{"url":"/paper/visualizing-uncertainty-in-translation-tasks","slug":"visualizing-uncertainty-in-translation-tasks","title":"Visualizing Uncertainty in Translation Tasks: An Evaluation of LLM Performance and Confidence Metrics","date":"2025-01-26","arxiv_id":"2501.17187","repositories_listed":1,"syntology":null},{"url":"/paper/heritage-an-end-to-end-web-platform-for","slug":"heritage-an-end-to-end-web-platform-for","title":"HERITAGE: An End-to-End Web Platform for Processing Korean Historical Documents in Hanja","date":"2025-01-21","arxiv_id":"2501.11951","repositories_listed":1,"syntology":null},{"url":"/paper/characterizing-the-effects-of-translation-on","slug":"characterizing-the-effects-of-translation-on","title":"Characterizing the Effects of Translation on Intertextuality using Multilingual Embedding Spaces","date":"2025-01-18","arxiv_id":"2501.10731","repositories_listed":1,"syntology":null},{"url":"/paper/afridoc-mt-document-level-mt-corpus-for","slug":"afridoc-mt-document-level-mt-corpus-for","title":"AFRIDOC-MT: Document-level MT Corpus for African Languages","date":"2025-01-10","arxiv_id":"2501.06374","repositories_listed":1,"syntology":null},{"url":"/paper/large-language-models-share-representations","slug":"large-language-models-share-representations","title":"Large Language Models Share Representations of Latent Grammatical Concepts Across Typologically Diverse Languages","date":"2025-01-10","arxiv_id":"2501.06346","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/large-language-models-share-representations#ran","syntology_url":"https://syntology.ai/paper/2501.06346","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.06346"}},"official":{"repos":["jannik-brinkmann/multilingual-features"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/merging-feed-forward-sublayers-for-compressed","slug":"merging-feed-forward-sublayers-for-compressed","title":"Merging Feed-Forward Sublayers for Compressed Transformers","date":"2025-01-10","arxiv_id":"2501.06126","repositories_listed":1,"syntology":null},{"url":"/paper/crossing-language-borders-a-pipeline-for","slug":"crossing-language-borders-a-pipeline-for","title":"Crossing Language Borders: A Pipeline for Indonesian Manhwa Translation","date":"2025-01-03","arxiv_id":"2501.01629","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/m-mad-multidimensional-multi-agent-debate","slug":"m-mad-multidimensional-multi-agent-debate","title":"M-MAD: Multidimensional Multi-Agent Debate Framework for Fine-grained Machine Translation Evaluation","date":"2024-12-28","arxiv_id":"2412.20127","repositories_listed":1,"syntology":null},{"url":"/paper/property-enhanced-instruction-tuning-for","slug":"property-enhanced-instruction-tuning-for","title":"Property Enhanced Instruction Tuning for Multi-task Molecule Generation with Large Language Models","date":"2024-12-24","arxiv_id":"2412.18084","repositories_listed":1,"syntology":null},{"url":"/paper/towards-global-ai-inclusivity-a-large-scale","slug":"towards-global-ai-inclusivity-a-large-scale","title":"Towards Global AI Inclusivity: A Large-Scale Multilingual Terminology Dataset (GIST)","date":"2024-12-24","arxiv_id":"2412.18367","repositories_listed":1,"syntology":null},{"url":"/paper/drt-o1-optimized-deep-reasoning-translation","slug":"drt-o1-optimized-deep-reasoning-translation","title":"DRT-o1: Optimized Deep Reasoning Translation via Long Chain-of-Thought","date":"2024-12-23","arxiv_id":"2412.17498","repositories_listed":1,"syntology":null},{"url":"/paper/multi-agent-sampling-scaling-inference","slug":"multi-agent-sampling-scaling-inference","title":"Multi-Agent Sampling: Scaling Inference Compute for Data Synthesis with Tree Search-Based Agentic Collaboration","date":"2024-12-22","arxiv_id":"2412.17061","repositories_listed":1,"syntology":null},{"url":"/paper/beyond-data-quantity-key-factors-driving","slug":"beyond-data-quantity-key-factors-driving","title":"Beyond Data Quantity: Key Factors Driving Performance in Multilingual Language Models","date":"2024-12-17","arxiv_id":"2412.12500","repositories_listed":1,"syntology":null},{"url":"/paper/enabling-low-resource-language-retrieval","slug":"enabling-low-resource-language-retrieval","title":"Enabling Low-Resource Language Retrieval: Establishing Baselines for Urdu MS MARCO","date":"2024-12-17","arxiv_id":"2412.12997","repositories_listed":1,"syntology":null},{"url":"/paper/mt-lens-an-all-in-one-toolkit-for-better","slug":"mt-lens-an-all-in-one-toolkit-for-better","title":"MT-LENS: An all-in-one Toolkit for Better Machine Translation Evaluation","date":"2024-12-16","arxiv_id":"2412.11615","repositories_listed":1,"syntology":null},{"url":"/paper/analyzing-the-attention-heads-for-pronoun","slug":"analyzing-the-attention-heads-for-pronoun","title":"Analyzing the Attention Heads for Pronoun Disambiguation in Context-aware Machine Translation Models","date":"2024-12-15","arxiv_id":"2412.11187","repositories_listed":1,"syntology":null},{"url":"/paper/roundtripocr-a-data-generation-technique-for","slug":"roundtripocr-a-data-generation-technique-for","title":"RoundTripOCR: A Data Generation Technique for Enhancing Post-OCR Error Correction in Low-Resource Devanagari Languages","date":"2024-12-14","arxiv_id":"2412.15248","repositories_listed":1,"syntology":null},{"url":"/paper/a-comparative-study-of-llms-nmt-models-and","slug":"a-comparative-study-of-llms-nmt-models-and","title":"A Comparative Study of LLMs, NMT Models, and Their Combination in Persian-English Idiom Translation","date":"2024-12-13","arxiv_id":"2412.09993","repositories_listed":1,"syntology":null},{"url":"/paper/annotations-for-exploring-food-tweets-from","slug":"annotations-for-exploring-food-tweets-from","title":"Annotations for Exploring Food Tweets From Multiple Aspects","date":"2024-12-09","arxiv_id":"2412.06179","repositories_listed":1,"syntology":null},{"url":"/paper/retrieval-augmented-machine-translation-with","slug":"retrieval-augmented-machine-translation-with","title":"Retrieval-Augmented Machine Translation with Unstructured Knowledge","date":"2024-12-05","arxiv_id":"2412.04342","repositories_listed":1,"syntology":null},{"url":"/paper/a-multi-way-parallel-named-entity-annotated","slug":"a-multi-way-parallel-named-entity-annotated","title":"A Multi-way Parallel Named Entity Annotated Corpus for English, Tamil and Sinhala","date":"2024-12-03","arxiv_id":"2412.02056","repositories_listed":1,"syntology":null},{"url":"/paper/improving-language-transfer-capability-of","slug":"improving-language-transfer-capability-of","title":"Improving Language Transfer Capability of Decoder-only Architecture in Multilingual Neural Machine Translation","date":"2024-12-03","arxiv_id":"2412.02101","repositories_listed":1,"syntology":null},{"url":"/paper/from-priest-to-doctor-domain-adaptaion-for","slug":"from-priest-to-doctor-domain-adaptaion-for","title":"From Priest to Doctor: Domain Adaptaion for Low-Resource Neural Machine Translation","date":"2024-12-01","arxiv_id":"2412.00966","repositories_listed":1,"syntology":null},{"url":"/paper/a-runtime-adaptive-transformer-neural-network","slug":"a-runtime-adaptive-transformer-neural-network","title":"A Runtime-Adaptive Transformer Neural Network Accelerator on FPGAs","date":"2024-11-27","arxiv_id":"2411.18148","repositories_listed":1,"syntology":null},{"url":"/paper/benchmarking-gpt-4-against-human-translators","slug":"benchmarking-gpt-4-against-human-translators","title":"Benchmarking GPT-4 against Human Translators: A Comprehensive Evaluation Across Languages, Domains, and Expertise Levels","date":"2024-11-21","arxiv_id":"2411.13775","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":1,"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/benchmarking-gpt-4-against-human-translators#ran","syntology_url":"https://syntology.ai/paper/2411.13775","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.13775"}},"official":{"repos":["elliottyan/gpt_versus_mt_experts"],"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/nmt-obfuscator-attack-ignore-a-sentence-in","slug":"nmt-obfuscator-attack-ignore-a-sentence-in","title":"NMT-Obfuscator Attack: Ignore a sentence in translation with only one word","date":"2024-11-19","arxiv_id":"2411.12473","repositories_listed":1,"syntology":null},{"url":"/paper/bangladialecto-an-end-to-end-ai-powered","slug":"bangladialecto-an-end-to-end-ai-powered","title":"BanglaDialecto: An End-to-End AI-Powered Regional Speech Standardization","date":"2024-11-16","arxiv_id":"2411.10879","repositories_listed":1,"syntology":null},{"url":"/paper/a-bayesian-optimization-approach-to-machine","slug":"a-bayesian-optimization-approach-to-machine","title":"A Bayesian Optimization Approach to Machine Translation Reranking","date":"2024-11-14","arxiv_id":"2411.09694","repositories_listed":1,"syntology":null},{"url":"/paper/deceiving-question-answering-models-a-hybrid","slug":"deceiving-question-answering-models-a-hybrid","title":"Deceiving Question-Answering Models: A Hybrid Word-Level Adversarial Approach","date":"2024-11-12","arxiv_id":"2411.08248","repositories_listed":1,"syntology":null},{"url":"/paper/benchmarking-llms-judgments-with-no-gold","slug":"benchmarking-llms-judgments-with-no-gold","title":"Benchmarking LLMs' Judgments with No Gold Standard","date":"2024-11-11","arxiv_id":"2411.07127","repositories_listed":1,"syntology":null},{"url":"/paper/using-language-models-to-disambiguate-lexical","slug":"using-language-models-to-disambiguate-lexical","title":"Using Language Models to Disambiguate Lexical Choices in Translation","date":"2024-11-08","arxiv_id":"2411.05781","repositories_listed":1,"syntology":null},{"url":"/paper/when-does-classical-chinese-help-quantifying","slug":"when-does-classical-chinese-help-quantifying","title":"When Does Classical Chinese Help? Quantifying Cross-Lingual Transfer in Hanja and Kanbun","date":"2024-11-07","arxiv_id":"2411.04822","repositories_listed":1,"syntology":null},{"url":"/paper/context-informed-machine-translation-of-manga","slug":"context-informed-machine-translation-of-manga","title":"Context-Informed Machine Translation of Manga using Multimodal Large Language Models","date":"2024-11-04","arxiv_id":"2411.02589","repositories_listed":1,"syntology":null},{"url":"/paper/moce-adaptive-mixture-of-contextualization","slug":"moce-adaptive-mixture-of-contextualization","title":"MoCE: Adaptive Mixture of Contextualization Experts for Byte-based Neural Machine Translation","date":"2024-11-03","arxiv_id":"2411.01474","repositories_listed":1,"syntology":null},{"url":"/paper/metametrics-mt-tuning-meta-metrics-for","slug":"metametrics-mt-tuning-meta-metrics-for","title":"MetaMetrics-MT: Tuning Meta-Metrics for Machine Translation via Human Preference Calibration","date":"2024-11-01","arxiv_id":"2411.00390","repositories_listed":1,"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/metametrics-mt-tuning-meta-metrics-for#ran","syntology_url":"https://syntology.ai/paper/2411.00390","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.00390"}},"official":{"repos":["meta-metrics/metametrics"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/multilingual-vision-language-pre-training-for","slug":"multilingual-vision-language-pre-training-for","title":"Multilingual Vision-Language Pre-training for the Remote Sensing Domain","date":"2024-10-30","arxiv_id":"2410.23370","repositories_listed":1,"syntology":null},{"url":"/paper/instruction-tuned-llms-succeed-in-document","slug":"instruction-tuned-llms-succeed-in-document","title":"Fine-Grained and Multi-Dimensional Metrics for Document-Level Machine Translation","date":"2024-10-28","arxiv_id":"2410.20941","repositories_listed":1,"syntology":null},{"url":"/paper/speechqe-estimating-the-quality-of-direct","slug":"speechqe-estimating-the-quality-of-direct","title":"SpeechQE: Estimating the Quality of Direct Speech Translation","date":"2024-10-28","arxiv_id":"2410.21485","repositories_listed":1,"syntology":null},{"url":"/paper/sequential-large-language-model-based-hyper","slug":"sequential-large-language-model-based-hyper","title":"Sequential Large Language Model-Based Hyper-parameter Optimization","date":"2024-10-27","arxiv_id":"2410.20302","repositories_listed":1,"syntology":null},{"url":"/paper/how-good-are-llms-for-literary-translation","slug":"how-good-are-llms-for-literary-translation","title":"How Good Are LLMs for Literary Translation, Really? Literary Translation Evaluation with Humans and LLMs","date":"2024-10-24","arxiv_id":"2410.18697","repositories_listed":1,"syntology":null},{"url":"/paper/on-creating-an-english-thai-code-switched","slug":"on-creating-an-english-thai-code-switched","title":"On Creating an English-Thai Code-switched Machine Translation in Medical Domain","date":"2024-10-21","arxiv_id":"2410.16221","repositories_listed":1,"syntology":null},{"url":"/paper/back-to-school-translation-using-grammar","slug":"back-to-school-translation-using-grammar","title":"Back to School: Translation Using Grammar Books","date":"2024-10-20","arxiv_id":"2410.15263","repositories_listed":1,"syntology":{"n":6,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/back-to-school-translation-using-grammar#ran","syntology_url":"https://syntology.ai/paper/2410.15263","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.15263"}},"official":{"repos":["jonathanhus/back-to-school"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/mhumaneval-a-multilingual-benchmark-to","slug":"mhumaneval-a-multilingual-benchmark-to","title":"mHumanEval -- A Multilingual Benchmark to Evaluate Large Language Models for Code Generation","date":"2024-10-19","arxiv_id":"2410.15037","repositories_listed":1,"syntology":null},{"url":"/paper/nlip-lab-iith-multilingual-mt-system-for","slug":"nlip-lab-iith-multilingual-mt-system-for","title":"NLIP_Lab-IITH Multilingual MT System for WAT24 MT Shared Task","date":"2024-10-17","arxiv_id":"2410.13443","repositories_listed":1,"syntology":null},{"url":"/paper/sarcasm-detection-in-a-less-resourced","slug":"sarcasm-detection-in-a-less-resourced","title":"Sarcasm Detection in a Less-Resourced Language","date":"2024-10-16","arxiv_id":"2410.12704","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-assamese-nlp-capabilities","slug":"enhancing-assamese-nlp-capabilities","title":"Enhancing Assamese NLP Capabilities: Introducing a Centralized Dataset Repository","date":"2024-10-15","arxiv_id":"2410.11291","repositories_listed":1,"syntology":null},{"url":"/paper/watching-the-watchers-exposing-gender","slug":"watching-the-watchers-exposing-gender","title":"Watching the Watchers: Exposing Gender Disparities in Machine Translation Quality Estimation","date":"2024-10-14","arxiv_id":"2410.10995","repositories_listed":1,"syntology":null},{"url":"/paper/adapters-for-altering-llm-vocabularies-what","slug":"adapters-for-altering-llm-vocabularies-what","title":"Adapters for Altering LLM Vocabularies: What Languages Benefit the Most?","date":"2024-10-12","arxiv_id":"2410.09644","repositories_listed":1,"syntology":null},{"url":"/paper/slam-aac-enhancing-audio-captioning-with","slug":"slam-aac-enhancing-audio-captioning-with","title":"SLAM-AAC: Enhancing Audio Captioning with Paraphrasing Augmentation and CLAP-Refine through LLMs","date":"2024-10-12","arxiv_id":"2410.09503","repositories_listed":1,"syntology":null},{"url":"/paper/delta-an-online-document-level-translation","slug":"delta-an-online-document-level-translation","title":"DelTA: An Online Document-Level Translation Agent Based on Multi-Level Memory","date":"2024-10-10","arxiv_id":"2410.08143","repositories_listed":1,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":5,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/delta-an-online-document-level-translation#ran","syntology_url":"https://syntology.ai/paper/2410.08143","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.08143"}},"official":{"repos":["yutongwang1216/docmtagent"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/mitigating-the-language-mismatch-and","slug":"mitigating-the-language-mismatch-and","title":"Mitigating the Language Mismatch and Repetition Issues in LLM-based Machine Translation via Model Editing","date":"2024-10-09","arxiv_id":"2410.07054","repositories_listed":1,"syntology":{"n":17,"n_ran":13,"n_constructed":0,"n_ran_checked":12,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":17,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/mitigating-the-language-mismatch-and#ran","syntology_url":"https://syntology.ai/paper/2410.07054","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.07054"}},"official":{"repos":["weichuanw/llm-based-mt-via-model-editing"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/are-large-language-models-state-of-the-art","slug":"are-large-language-models-state-of-the-art","title":"Are Large Language Models State-of-the-art Quality Estimators for Machine Translation of User-generated Content?","date":"2024-10-08","arxiv_id":"2410.06338","repositories_listed":1,"syntology":null},{"url":"/paper/a-test-suite-of-prompt-injection-attacks-for","slug":"a-test-suite-of-prompt-injection-attacks-for","title":"A test suite of prompt injection attacks for LLM-based machine translation","date":"2024-10-07","arxiv_id":"2410.05047","repositories_listed":1,"syntology":null},{"url":"/paper/leveraging-grammar-induction-for-language","slug":"leveraging-grammar-induction-for-language","title":"Leveraging Grammar Induction for Language Understanding and Generation","date":"2024-10-07","arxiv_id":"2410.04878","repositories_listed":1,"syntology":null},{"url":"/paper/neural-machine-translation-system-for-lezgian","slug":"neural-machine-translation-system-for-lezgian","title":"Neural machine translation system for Lezgian, Russian and Azerbaijani languages","date":"2024-10-07","arxiv_id":"2410.05472","repositories_listed":1,"syntology":null},{"url":"/paper/what-do-large-language-models-need-for","slug":"what-do-large-language-models-need-for","title":"What do Large Language Models Need for Machine Translation Evaluation?","date":"2024-10-04","arxiv_id":"2410.03278","repositories_listed":1,"syntology":null},{"url":"/paper/what-the-harm-quantifying-the-tangible-impact","slug":"what-the-harm-quantifying-the-tangible-impact","title":"What the Harm? Quantifying the Tangible Impact of Gender Bias in Machine Translation with a Human-centered Study","date":"2024-10-01","arxiv_id":"2410.00545","repositories_listed":1,"syntology":null},{"url":"/paper/multimodal-llm-enhanced-cross-lingual-cross","slug":"multimodal-llm-enhanced-cross-lingual-cross","title":"Multimodal LLM Enhanced Cross-lingual Cross-modal Retrieval","date":"2024-09-30","arxiv_id":"2409.19961","repositories_listed":1,"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":4,"n_instrument":5,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":12,"phrase":"9 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; 5 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/multimodal-llm-enhanced-cross-lingual-cross#ran","syntology_url":"https://syntology.ai/paper/2409.19961","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.19961"}},"official":{"repos":["lijiabei-7/leccr"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/shifting-from-endangerment-to-rebirth-in-the","slug":"shifting-from-endangerment-to-rebirth-in-the","title":"Shifting from endangerment to rebirth in the Artificial Intelligence Age: An Ensemble Machine Learning Approach for Hawrami Text Classification","date":"2024-09-25","arxiv_id":"2409.16884","repositories_listed":1,"syntology":null},{"url":"/paper/mqm-ape-toward-high-quality-error-annotation","slug":"mqm-ape-toward-high-quality-error-annotation","title":"MQM-APE: Toward High-Quality Error Annotation Predictors with Automatic Post-Editing in LLM Translation Evaluators","date":"2024-09-22","arxiv_id":"2409.14335","repositories_listed":1,"syntology":null},{"url":"/paper/2409-13920","slug":"2409-13920","title":"One Model is All You Need: ByT5-Sanskrit, a Unified Model for Sanskrit NLP Tasks","date":"2024-09-20","arxiv_id":"2409.13920","repositories_listed":1,"syntology":null},{"url":"/paper/evaluation-of-google-translate-for-mandarin","slug":"evaluation-of-google-translate-for-mandarin","title":"Evaluation of Google Translate for Mandarin Chinese translation using sentiment and semantic analysis","date":"2024-09-08","arxiv_id":"2409.04964","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-intrinsic-language-specific","slug":"exploring-intrinsic-language-specific","title":"Exploring Intrinsic Language-specific Subspaces in Fine-tuning Multilingual Neural Machine Translation","date":"2024-09-08","arxiv_id":"2409.05224","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"2 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; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/exploring-intrinsic-language-specific#ran","syntology_url":"https://syntology.ai/paper/2409.05224","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.05224"}},"official":{"repos":["spike0924/lslo"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/vision-fused-attack-advancing-aggressive-and","slug":"vision-fused-attack-advancing-aggressive-and","title":"Vision-fused Attack: Advancing Aggressive and Stealthy Adversarial Text against Neural Machine Translation","date":"2024-09-08","arxiv_id":"2409.05021","repositories_listed":1,"syntology":{"n":4,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"0 ran · 4 unverified","sample_list":"/paper/vision-fused-attack-advancing-aggressive-and#ran","syntology_url":"https://syntology.ai/paper/2409.05021","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.05021"}},"official":{"repos":["levelower/vfa"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":[]}}},{"url":"/paper/pitfalls-and-outlooks-in-using-comet","slug":"pitfalls-and-outlooks-in-using-comet","title":"Pitfalls and Outlooks in Using COMET","date":"2024-08-27","arxiv_id":"2408.15366","repositories_listed":1,"syntology":null},{"url":"/paper/guardians-of-the-machine-translation-meta","slug":"guardians-of-the-machine-translation-meta","title":"Guardians of the Machine Translation Meta-Evaluation: Sentinel Metrics Fall In!","date":"2024-08-25","arxiv_id":"2408.13831","repositories_listed":1,"syntology":null},{"url":"/paper/improving-rare-word-translation-with","slug":"improving-rare-word-translation-with","title":"Improving Rare Word Translation With Dictionaries and Attention Masking","date":"2024-08-17","arxiv_id":"2408.09075","repositories_listed":1,"syntology":null},{"url":"/paper/language-informed-beam-search-decoding-for","slug":"language-informed-beam-search-decoding-for","title":"Language-Informed Beam Search Decoding for Multilingual Machine Translation","date":"2024-08-11","arxiv_id":"2408.05738","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 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; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/language-informed-beam-search-decoding-for#ran","syntology_url":"https://syntology.ai/paper/2408.05738","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.05738"}},"official":{"repos":["yilinyang7/fairseq_multi_fix"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/scoi-syntax-augmented-coverage-based-in","slug":"scoi-syntax-augmented-coverage-based-in","title":"SCOI: Syntax-augmented Coverage-based In-context Example Selection for Machine Translation","date":"2024-08-09","arxiv_id":"2408.04872","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/scoi-syntax-augmented-coverage-based-in#ran","syntology_url":"https://syntology.ai/paper/2408.04872","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.04872"}},"official":{"repos":["jamydon/scoi"],"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":["found_in_text"]}}},{"url":"/paper/simplifying-translations-for-children","slug":"simplifying-translations-for-children","title":"Simplifying Translations for Children: Iterative Simplification Considering Age of Acquisition with LLMs","date":"2024-08-08","arxiv_id":"2408.04217","repositories_listed":1,"syntology":null},{"url":"/paper/trans-tokenization-and-cross-lingual","slug":"trans-tokenization-and-cross-lingual","title":"Trans-Tokenization and Cross-lingual Vocabulary Transfers: Language Adaptation of LLMs for Low-Resource NLP","date":"2024-08-08","arxiv_id":"2408.04303","repositories_listed":1,"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/trans-tokenization-and-cross-lingual#ran","syntology_url":"https://syntology.ai/paper/2408.04303","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.04303"}},"official":{"repos":["lagom-nlp/transtokenizer"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/2408-01394","slug":"2408-01394","title":"Improving Multilingual Neural Machine Translation by Utilizing Semantic and Linguistic Features","date":"2024-08-02","arxiv_id":"2408.01394","repositories_listed":1,"syntology":null},{"url":"/paper/2408-00397","slug":"2408-00397","title":"In-Context Example Selection via Similarity Search Improves Low-Resource Machine Translation","date":"2024-08-01","arxiv_id":"2408.00397","repositories_listed":1,"syntology":null},{"url":"/paper/2408-00624","slug":"2408-00624","title":"SynesLM: A Unified Approach for Audio-visual Speech Recognition and Translation via Language Model and Synthetic Data","date":"2024-08-01","arxiv_id":"2408.00624","repositories_listed":1,"syntology":null},{"url":"/paper/investigating-sparsity-in-recurrent-neural","slug":"investigating-sparsity-in-recurrent-neural","title":"Investigating Sparsity in Recurrent Neural Networks","date":"2024-07-30","arxiv_id":"2407.20601","repositories_listed":1,"syntology":null},{"url":"/paper/granularity-is-crucial-when-applying","slug":"granularity-is-crucial-when-applying","title":"Granularity is crucial when applying differential privacy to text: An investigation for neural machine translation","date":"2024-07-26","arxiv_id":"2407.18789","repositories_listed":1,"syntology":null},{"url":"/paper/beyond-binary-gender-evaluating-gender","slug":"beyond-binary-gender-evaluating-gender","title":"Beyond Binary Gender: Evaluating Gender-Inclusive Machine Translation with Ambiguous Attitude Words","date":"2024-07-23","arxiv_id":"2407.16266","repositories_listed":1,"syntology":null},{"url":"/paper/machine-translation-hallucination-detection","slug":"machine-translation-hallucination-detection","title":"Machine Translation Hallucination Detection for Low and High Resource Languages using Large Language Models","date":"2024-07-23","arxiv_id":"2407.16470","repositories_listed":1,"syntology":null},{"url":"/paper/promises-and-pitfalls-of-generative-masked","slug":"promises-and-pitfalls-of-generative-masked","title":"Promises and Pitfalls of Generative Masked Language Modeling: Theoretical Framework and Practical Guidelines","date":"2024-07-22","arxiv_id":"2407.21046","repositories_listed":1,"syntology":null},{"url":"/paper/covoswitch-machine-translation-of-synthetic","slug":"covoswitch-machine-translation-of-synthetic","title":"CoVoSwitch: Machine Translation of Synthetic Code-Switched Text Based on Intonation Units","date":"2024-07-19","arxiv_id":"2407.14295","repositories_listed":1,"syntology":null},{"url":"/paper/fixed-and-adaptive-simultaneous-machine","slug":"fixed-and-adaptive-simultaneous-machine","title":"Fixed and Adaptive Simultaneous Machine Translation Strategies Using Adapters","date":"2024-07-18","arxiv_id":"2407.13469","repositories_listed":1,"syntology":null},{"url":"/paper/masive-open-ended-affective-state","slug":"masive-open-ended-affective-state","title":"MASIVE: Open-Ended Affective State Identification in English and Spanish","date":"2024-07-16","arxiv_id":"2407.12196","repositories_listed":1,"syntology":null},{"url":"/paper/learning-program-behavioral-models-from","slug":"learning-program-behavioral-models-from","title":"Learning Program Behavioral Models from Synthesized Input-Output Pairs","date":"2024-07-11","arxiv_id":"2407.08597","repositories_listed":1,"syntology":null},{"url":"/paper/arabic-automatic-story-generation-with-large","slug":"arabic-automatic-story-generation-with-large","title":"Arabic Automatic Story Generation with Large Language Models","date":"2024-07-10","arxiv_id":"2407.07551","repositories_listed":1,"syntology":null},{"url":"/paper/how-effective-are-state-space-models-for","slug":"how-effective-are-state-space-models-for","title":"How Effective are State Space Models for Machine Translation?","date":"2024-07-07","arxiv_id":"2407.05489","repositories_listed":1,"syntology":null},{"url":"/paper/rethinking-targeted-adversarial-attacks-for","slug":"rethinking-targeted-adversarial-attacks-for","title":"Rethinking Targeted Adversarial Attacks For Neural Machine Translation","date":"2024-07-07","arxiv_id":"2407.05319","repositories_listed":1,"syntology":null},{"url":"/paper/smurfcat-at-pan-2024-textdetox-alignment-of","slug":"smurfcat-at-pan-2024-textdetox-alignment-of","title":"SmurfCat at PAN 2024 TextDetox: Alignment of Multilingual Transformers for Text Detoxification","date":"2024-07-07","arxiv_id":"2407.05449","repositories_listed":1,"syntology":null},{"url":"/paper/catt-character-based-arabic-tashkeel","slug":"catt-character-based-arabic-tashkeel","title":"CATT: Character-based Arabic Tashkeel Transformer","date":"2024-07-03","arxiv_id":"2407.03236","repositories_listed":1,"syntology":null},{"url":"/paper/evaluating-automatic-metrics-with-incremental","slug":"evaluating-automatic-metrics-with-incremental","title":"Evaluating Automatic Metrics with Incremental Machine Translation Systems","date":"2024-07-03","arxiv_id":"2407.03277","repositories_listed":1,"syntology":null},{"url":"/paper/translatotron-v-ison-an-end-to-end-model-for","slug":"translatotron-v-ison-an-end-to-end-model-for","title":"Translatotron-V(ison): An End-to-End Model for In-Image Machine Translation","date":"2024-07-03","arxiv_id":"2407.02894","repositories_listed":1,"syntology":null},{"url":"/paper/prompt-refinement-with-image-pivot-for-text","slug":"prompt-refinement-with-image-pivot-for-text","title":"Prompt Refinement with Image Pivot for Text-to-Image Generation","date":"2024-06-28","arxiv_id":"2407.00247","repositories_listed":1,"syntology":null},{"url":"/paper/ffn-a-fine-grained-chinese-english-financial","slug":"ffn-a-fine-grained-chinese-english-financial","title":"FFN: a Fine-grained Chinese-English Financial Domain Parallel Corpus","date":"2024-06-27","arxiv_id":"2406.18856","repositories_listed":1,"syntology":null},{"url":"/paper/voices-unheard-nlp-resources-and-models-for","slug":"voices-unheard-nlp-resources-and-models-for","title":"Voices Unheard: NLP Resources and Models for Yorùbá Regional Dialects","date":"2024-06-27","arxiv_id":"2406.19564","repositories_listed":1,"syntology":null},{"url":"/paper/arzen-llm-code-switched-egyptian-arabic","slug":"arzen-llm-code-switched-egyptian-arabic","title":"ArzEn-LLM: Code-Switched Egyptian Arabic-English Translation and Speech Recognition Using LLMs","date":"2024-06-26","arxiv_id":"2406.18120","repositories_listed":1,"syntology":null},{"url":"/paper/prexme-large-scale-prompt-exploration-of-open","slug":"prexme-large-scale-prompt-exploration-of-open","title":"PrExMe! Large Scale Prompt Exploration of Open Source LLMs for Machine Translation and Summarization Evaluation","date":"2024-06-26","arxiv_id":"2406.18528","repositories_listed":1,"syntology":null}],"record_sha256":"ecdd94974cd5dae6fa3fb1d2c5a223b5f63f1af9e587223e15913db0ecec9098","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}