{"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/29","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":29,"pages_in_order":108,"rows_per_page":100,"rows":[2801,2900],"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/28","next":"/task/machine-translation/papers/30","papers":[{"url":null,"slug":"advancing-neural-network-performance-through","title":"Advancing Neural Network Performance through Emergence-Promoting Initialization Scheme","date":"2024-07-26","arxiv_id":"2407.19044","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-power-of-prompts-evaluating-and","title":"The power of Prompts: Evaluating and Mitigating Gender Bias in MT with LLMs","date":"2024-07-26","arxiv_id":"2407.18786","repositories_listed":0,"syntology":null},{"url":null,"slug":"fine-grained-gender-control-in-machine","title":"Fine-grained Gender Control in Machine Translation with Large Language Models","date":"2024-07-21","arxiv_id":"2407.15154","repositories_listed":0,"syntology":null},{"url":"/paper/generalization-v-s-memorization-tracing","slug":"generalization-v-s-memorization-tracing","title":"Generalization v.s. Memorization: Tracing Language Models' Capabilities Back to Pretraining Data","date":"2024-07-20","arxiv_id":"2407.14985","repositories_listed":0,"syntology":{"n":15,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/generalization-v-s-memorization-tracing#ran","syntology_url":"https://syntology.ai/paper/2407.14985","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.14985"}},"official":null}},{"url":null,"slug":"translate-and-revise-boosting-large-language","title":"Translate-and-Revise: Boosting Large Language Models for Constrained Translation","date":"2024-07-18","arxiv_id":"2407.13164","repositories_listed":0,"syntology":null},{"url":null,"slug":"ancient-korean-archive-translation-comparison","title":"Ancient Korean Archive Translation: Comparison Analysis on Statistical phrase alignment, LLM in-context learning, and inter-methodological approach","date":"2024-07-16","arxiv_id":"2407.11368","repositories_listed":0,"syntology":null},{"url":null,"slug":"llms-in-the-loop-part-1-expert-small-ai","title":"LLMs-in-the-loop Part-1: Expert Small AI Models for Bio-Medical Text Translation","date":"2024-07-16","arxiv_id":"2407.12126","repositories_listed":0,"syntology":null},{"url":null,"slug":"scaling-sign-language-translation","title":"Scaling Sign Language Translation","date":"2024-07-16","arxiv_id":"2407.11855","repositories_listed":0,"syntology":null},{"url":null,"slug":"arafinnlp-2024-the-first-arabic-financial-nlp","title":"AraFinNLP 2024: The First Arabic Financial NLP Shared Task","date":"2024-07-13","arxiv_id":"2407.09818","repositories_listed":0,"syntology":null},{"url":null,"slug":"sphinx-sample-efficient-multilingual","title":"sPhinX: Sample Efficient Multilingual Instruction Fine-Tuning Through N-shot Guided Prompting","date":"2024-07-13","arxiv_id":"2407.09879","repositories_listed":0,"syntology":null},{"url":null,"slug":"dahrs-divergence-aware-hallucination","title":"DAHRS: Divergence-Aware Hallucination-Remediated SRL Projection","date":"2024-07-12","arxiv_id":"2407.09283","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-chapter-to-chapter-context-aware","title":"Towards Chapter-to-Chapter Context-Aware Literary Translation via Large Language Models","date":"2024-07-12","arxiv_id":"2407.08978","repositories_listed":0,"syntology":null},{"url":null,"slug":"rule-based-neural-and-llm-back-translation","title":"Rule-Based, Neural and LLM Back-Translation: Comparative Insights from a Variant of Ladin","date":"2024-07-11","arxiv_id":"2407.08819","repositories_listed":0,"syntology":null},{"url":null,"slug":"tamil-language-computing-the-present-and-the","title":"Tamil Language Computing: the Present and the Future","date":"2024-07-11","arxiv_id":"2407.08618","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-word-order-synchronization-metric-for","title":"An Automatic Quality Metric for Evaluating Simultaneous Interpretation","date":"2024-07-09","arxiv_id":"2407.06650","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-low-resource-nmt-with-a","title":"Enhancing Low-Resource NMT with a Multilingual Encoder and Knowledge Distillation: A Case Study","date":"2024-07-09","arxiv_id":"2407.06538","repositories_listed":0,"syntology":null},{"url":null,"slug":"segment-based-interactive-machine-translation","title":"Segment-Based Interactive Machine Translation for Pre-trained Models","date":"2024-07-09","arxiv_id":"2407.06990","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-models-for-judicial-entity","title":"Large Language Models for Judicial Entity Extraction: A Comparative Study","date":"2024-07-08","arxiv_id":"2407.05786","repositories_listed":0,"syntology":null},{"url":null,"slug":"predicting-word-similarity-in-context-with","title":"Predicting Word Similarity in Context with Referential Translation Machines","date":"2024-07-07","arxiv_id":"2407.06230","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-prediction-of-the-performance-of","title":"Automatic Prediction of the Performance of Every Parser","date":"2024-07-06","arxiv_id":"2407.05116","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-language-learning-through","title":"Enhancing Language Learning through Technology: Introducing a New English-Azerbaijani (Arabic Script) Parallel Corpus","date":"2024-07-06","arxiv_id":"2407.05189","repositories_listed":0,"syntology":null},{"url":null,"slug":"identifying-intensity-of-the-structure-and","title":"Identifying Intensity of the Structure and Content in Tweets and the Discriminative Power of Attributes in Context with Referential Translation Machines","date":"2024-07-06","arxiv_id":"2407.05154","repositories_listed":0,"syntology":null},{"url":null,"slug":"nadi-2024-the-fifth-nuanced-arabic-dialect","title":"NADI 2024: The Fifth Nuanced Arabic Dialect Identification Shared Task","date":"2024-07-06","arxiv_id":"2407.04910","repositories_listed":0,"syntology":null},{"url":null,"slug":"toucan-many-to-many-translation-for-150","title":"Toucan: Many-to-Many Translation for 150 African Language Pairs","date":"2024-07-05","arxiv_id":"2407.04796","repositories_listed":0,"syntology":null},{"url":null,"slug":"finetuning-end-to-end-models-for-estonian","title":"Finetuning End-to-End Models for Estonian Conversational Spoken Language Translation","date":"2024-07-04","arxiv_id":"2407.03809","repositories_listed":0,"syntology":null},{"url":null,"slug":"hera-high-efficiency-matrix-compression-via","title":"QET: Enhancing Quantized LLM Parameters and KV cache Compression through Element Substitution and Residual Clustering","date":"2024-07-04","arxiv_id":"2407.03637","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-case-study-on-context-aware-neural-machine","title":"A Case Study on Context-Aware Neural Machine Translation with Multi-Task Learning","date":"2024-07-03","arxiv_id":"2407.03076","repositories_listed":0,"syntology":null},{"url":null,"slug":"regurgitative-training-the-value-of-real-data","title":"Regurgitative Training: The Value of Real Data in Training Large Language Models","date":"2024-07-03","arxiv_id":"2407.12835","repositories_listed":0,"syntology":null},{"url":null,"slug":"sentence-level-aggregation-of-lexical-metrics","title":"Sentence-level Aggregation of Lexical Metrics Correlates Stronger with Human Judgements than Corpus-level Aggregation","date":"2024-07-03","arxiv_id":"2407.12832","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-to-learn-in-a-noisy-world-self-correcting","title":"How to Learn in a Noisy World? Self-Correcting the Real-World Data Noise on Machine Translation","date":"2024-07-02","arxiv_id":"2407.02208","repositories_listed":0,"syntology":null},{"url":null,"slug":"esale-enhancing-code-summary-alignment","title":"ESALE: Enhancing Code-Summary Alignment Learning for Source Code Summarization","date":"2024-07-01","arxiv_id":"2407.01646","repositories_listed":0,"syntology":null},{"url":null,"slug":"investigating-the-potential-of-sparse","title":"Investigating the potential of Sparse Mixtures-of-Experts for multi-domain neural machine translation","date":"2024-07-01","arxiv_id":"2407.01126","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-portability-strategies-for-open","title":"Language Portability Strategies for Open-domain Dialogue with Pre-trained Language Models from High to Low Resource Languages","date":"2024-07-01","arxiv_id":"2407.01315","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-recipe-of-parallel-corpora-exploitation-for","title":"A Recipe of Parallel Corpora Exploitation for Multilingual Large Language Models","date":"2024-06-29","arxiv_id":"2407.00436","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-massive-multilingual-holistic-bias","title":"Towards Massive Multilingual Holistic Bias","date":"2024-06-29","arxiv_id":"2407.00486","repositories_listed":0,"syntology":null},{"url":null,"slug":"less-is-more-accurate-speech-recognition","title":"Less is More: Accurate Speech Recognition & Translation without Web-Scale Data","date":"2024-06-28","arxiv_id":"2406.19674","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-case-study-on-contextual-machine","title":"A Case Study on Contextual Machine Translation in a Professional Scenario of Subtitling","date":"2024-06-27","arxiv_id":"2407.00108","repositories_listed":0,"syntology":null},{"url":null,"slug":"sparse-regression-for-machine-translation","title":"Sparse Regression for Machine Translation","date":"2024-06-27","arxiv_id":"2406.19478","repositories_listed":0,"syntology":null},{"url":null,"slug":"xtower-a-multilingual-llm-for-explaining-and","title":"xTower: A Multilingual LLM for Explaining and Correcting Translation Errors","date":"2024-06-27","arxiv_id":"2406.19482","repositories_listed":0,"syntology":null},{"url":null,"slug":"blending-llms-into-cascaded-speech","title":"Blending LLMs into Cascaded Speech Translation: KIT's Offline Speech Translation System for IWSLT 2024","date":"2024-06-24","arxiv_id":"2406.16777","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-progression-of-transformers-from-language","title":"The Progression of Transformers from Language to Vision to MOT: A Literature Review on Multi-Object Tracking with Transformers","date":"2024-06-24","arxiv_id":"2406.16784","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-idiomatic-representation-in","title":"Enhancing Idiomatic Representation in Multiple Languages via an Adaptive Contrastive Triplet Loss","date":"2024-06-21","arxiv_id":"2406.15175","repositories_listed":0,"syntology":null},{"url":null,"slug":"shortcomings-of-llms-for-low-resource","title":"Shortcomings of LLMs for Low-Resource Translation: Retrieval and Understanding are Both the Problem","date":"2024-06-21","arxiv_id":"2406.15625","repositories_listed":0,"syntology":null},{"url":null,"slug":"complexity-of-symbolic-representation-in","title":"Complexity of Symbolic Representation in Working Memory of Transformer Correlates with the Complexity of a Task","date":"2024-06-20","arxiv_id":"2406.14213","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-evaluation-practices-in-multilingual","title":"On the Evaluation Practices in Multilingual NLP: Can Machine Translation Offer an Alternative to Human Translations?","date":"2024-06-20","arxiv_id":"2406.14267","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-effective-is-multi-source-pivoting-for","title":"How effective is Multi-source pivoting for Translation of Low Resource Indian Languages?","date":"2024-06-19","arxiv_id":"2406.13332","repositories_listed":0,"syntology":null},{"url":null,"slug":"mmte-corpus-and-metrics-for-evaluating","title":"MMTE: Corpus and Metrics for Evaluating Machine Translation Quality of Metaphorical Language","date":"2024-06-19","arxiv_id":"2406.13698","repositories_listed":0,"syntology":null},{"url":null,"slug":"does-context-help-mitigate-gender-bias-in","title":"Does Context Help Mitigate Gender Bias in Neural Machine Translation?","date":"2024-06-18","arxiv_id":"2406.12364","repositories_listed":0,"syntology":null},{"url":null,"slug":"pfid-privacy-first-inference-delegation","title":"PFID: Privacy First Inference Delegation Framework for LLMs","date":"2024-06-18","arxiv_id":"2406.12238","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-distillation-for-model-stacking-unlocks","title":"Self-Distillation for Model Stacking Unlocks Cross-Lingual NLU in 200+ Languages","date":"2024-06-18","arxiv_id":"2406.12739","repositories_listed":0,"syntology":null},{"url":null,"slug":"lilium-ebay-s-large-language-models-for-e","title":"LiLiuM: eBay's Large Language Models for e-commerce","date":"2024-06-17","arxiv_id":"2406.12023","repositories_listed":0,"syntology":null},{"url":null,"slug":"unveiling-the-power-of-source-source-based","title":"Unveiling the Power of Source: Source-based Minimum Bayes Risk Decoding for Neural Machine Translation","date":"2024-06-17","arxiv_id":"2406.11632","repositories_listed":0,"syntology":null},{"url":null,"slug":"costa-code-switched-speech-translation-using","title":"CoSTA: Code-Switched Speech Translation using Aligned Speech-Text Interleaving","date":"2024-06-16","arxiv_id":"2406.10993","repositories_listed":0,"syntology":null},{"url":null,"slug":"reconsidering-sentence-level-sign-language","title":"Reconsidering Sentence-Level Sign Language Translation","date":"2024-06-16","arxiv_id":"2406.11049","repositories_listed":0,"syntology":null},{"url":null,"slug":"datasets-for-multilingual-answer-sentence","title":"Datasets for Multilingual Answer Sentence Selection","date":"2024-06-14","arxiv_id":"2406.10172","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-autoregressive-training-with","title":"Improving Autoregressive Training with Dynamic Oracles","date":"2024-06-13","arxiv_id":"2406.09393","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficiently-exploring-large-language-models","title":"Efficiently Exploring Large Language Models for Document-Level Machine Translation with In-context Learning","date":"2024-06-11","arxiv_id":"2406.07081","repositories_listed":0,"syntology":null},{"url":null,"slug":"textual-similarity-as-a-key-metric-in-machine","title":"Textual Similarity as a Key Metric in Machine Translation Quality Estimation","date":"2024-06-11","arxiv_id":"2406.07440","repositories_listed":0,"syntology":null},{"url":null,"slug":"symmetric-dot-product-attention-for-efficient","title":"Symmetric Dot-Product Attention for Efficient Training of BERT Language Models","date":"2024-06-10","arxiv_id":"2406.06366","repositories_listed":0,"syntology":null},{"url":null,"slug":"feriji-a-french-zarma-parallel-corpus","title":"Feriji: A French-Zarma Parallel Corpus, Glossary & Translator","date":"2024-06-09","arxiv_id":"2406.05888","repositories_listed":0,"syntology":null},{"url":null,"slug":"do-llms-recognize-me-when-i-is-not-me","title":"Do LLMs Recognize me, When I is not me: Assessment of LLMs Understanding of Turkish Indexical Pronouns in Indexical Shift Contexts","date":"2024-06-08","arxiv_id":"2406.05569","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-the-iwslt2023-speech-translation","title":"Evaluating the IWSLT2023 Speech Translation Tasks: Human Annotations, Automatic Metrics, and Segmentation","date":"2024-06-06","arxiv_id":"2406.03881","repositories_listed":0,"syntology":null},{"url":null,"slug":"recovering-document-annotations-for-sentence","title":"Recovering document annotations for sentence-level bitext","date":"2024-06-06","arxiv_id":"2406.03869","repositories_listed":0,"syntology":null},{"url":null,"slug":"what-is-the-best-way-for-chatgpt-to-translate","title":"What is the Best Way for ChatGPT to Translate Poetry?","date":"2024-06-05","arxiv_id":"2406.03450","repositories_listed":0,"syntology":null},{"url":null,"slug":"prompting-large-language-models-with-human","title":"Prompting Large Language Models with Human Error Markings for Self-Correcting Machine Translation","date":"2024-06-04","arxiv_id":"2406.02267","repositories_listed":0,"syntology":null},{"url":null,"slug":"translation-deserves-better-analyzing","title":"Translation Deserves Better: Analyzing Translation Artifacts in Cross-lingual Visual Question Answering","date":"2024-06-04","arxiv_id":"2406.02331","repositories_listed":0,"syntology":null},{"url":null,"slug":"applying-intrinsic-debiasing-on-downstream","title":"Applying Intrinsic Debiasing on Downstream Tasks: Challenges and Considerations for Machine Translation","date":"2024-06-02","arxiv_id":"2406.00787","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-multilingual-are-large-language-models","title":"How Multilingual Are Large Language Models Fine-Tuned for Translation?","date":"2024-05-30","arxiv_id":"2405.20512","repositories_listed":0,"syntology":null},{"url":null,"slug":"significance-of-chain-of-thought-in-gender","title":"Significance of Chain of Thought in Gender Bias Mitigation for English-Dravidian Machine Translation","date":"2024-05-30","arxiv_id":"2405.19701","repositories_listed":0,"syntology":null},{"url":null,"slug":"critical-learning-periods-leveraging-early","title":"Critical Learning Periods: Leveraging Early Training Dynamics for Efficient Data Pruning","date":"2024-05-29","arxiv_id":"2405.19462","repositories_listed":0,"syntology":null},{"url":null,"slug":"understanding-and-addressing-the-under","title":"Understanding and Addressing the Under-Translation Problem from the Perspective of Decoding Objective","date":"2024-05-29","arxiv_id":"2405.18922","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-sequence-evaluation-based-on","title":"On the Sequence Evaluation based on Stochastic Processes","date":"2024-05-28","arxiv_id":"2405.17764","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-multi-range-theory-of-translation-quality","title":"The Multi-Range Theory of Translation Quality Measurement: MQM scoring models and Statistical Quality Control","date":"2024-05-27","arxiv_id":"2405.16969","repositories_listed":0,"syntology":null},{"url":null,"slug":"m-rag-reinforcing-large-language-model","title":"M-RAG: Reinforcing Large Language Model Performance through Retrieval-Augmented Generation with Multiple Partitions","date":"2024-05-26","arxiv_id":"2405.16420","repositories_listed":0,"syntology":null},{"url":null,"slug":"athena-efficient-block-wise-post-training","title":"Athena: Efficient Block-Wise Post-Training Quantization for Large Language Models Using Second-Order Matrix Derivative Information","date":"2024-05-24","arxiv_id":"2405.17470","repositories_listed":0,"syntology":null},{"url":null,"slug":"sparse-spectral-training-and-inference-on","title":"Sparse Spectral Training and Inference on Euclidean and Hyperbolic Neural Networks","date":"2024-05-24","arxiv_id":"2405.15481","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-language-models-trained-with","title":"Improving Language Models Trained on Translated Data with Continual Pre-Training and Dictionary Learning Analysis","date":"2024-05-23","arxiv_id":"2405.14277","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimizing-example-selection-for-retrieval","title":"Optimizing example selection for retrieval-augmented machine translation with translation memories","date":"2024-05-23","arxiv_id":"2405.15070","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-on-multi-modal-machine-translation","title":"A Survey on Multi-modal Machine Translation: Tasks, Methods and Challenges","date":"2024-05-21","arxiv_id":"2405.12669","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-mle-investigating-searnn-for-low","title":"Beyond MLE: Investigating SEARNN for Low-Resourced Neural Machine Translation","date":"2024-05-20","arxiv_id":"2405.11819","repositories_listed":0,"syntology":null},{"url":null,"slug":"chasing-comet-leveraging-minimum-bayes-risk","title":"Chasing COMET: Leveraging Minimum Bayes Risk Decoding for Self-Improving Machine Translation","date":"2024-05-20","arxiv_id":"2405.11937","repositories_listed":0,"syntology":null},{"url":null,"slug":"cyber-risks-of-machine-translation-critical","title":"Cyber Risks of Machine Translation Critical Errors : Arabic Mental Health Tweets as a Case Study","date":"2024-05-19","arxiv_id":"2405.11668","repositories_listed":0,"syntology":null},{"url":null,"slug":"word-alignment-as-preference-for-machine","title":"Word Alignment as Preference for Machine Translation","date":"2024-05-15","arxiv_id":"2405.09223","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-gender-inclusive-machine","title":"Enhancing Gender-Inclusive Machine Translation with Neomorphemes and Large Language Models","date":"2024-05-14","arxiv_id":"2405.08477","repositories_listed":0,"syntology":null},{"url":null,"slug":"llm-assisted-rule-based-machine-translation","title":"LLM-Assisted Rule Based Machine Translation for Low/No-Resource Languages","date":"2024-05-14","arxiv_id":"2405.08997","repositories_listed":0,"syntology":null},{"url":null,"slug":"using-machine-translation-to-augment","title":"Using Machine Translation to Augment Multilingual Classification","date":"2024-05-09","arxiv_id":"2405.05478","repositories_listed":0,"syntology":null},{"url":null,"slug":"automated-program-repair-emerging-trends-pose","title":"Automated Program Repair: Emerging trends pose and expose problems for benchmarks","date":"2024-05-08","arxiv_id":"2405.05455","repositories_listed":0,"syntology":null},{"url":null,"slug":"fine-tuning-pre-trained-named-entity","title":"Fine-tuning Pre-trained Named Entity Recognition Models For Indian Languages","date":"2024-05-08","arxiv_id":"2405.04829","repositories_listed":0,"syntology":null},{"url":null,"slug":"relay-decoding-concatenating-large-language","title":"Relay Decoding: Concatenating Large Language Models for Machine Translation","date":"2024-05-05","arxiv_id":"2405.02933","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-call-for-socially-aware-language","title":"The Call for Socially Aware Language Technologies","date":"2024-05-03","arxiv_id":"2405.02411","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-for-edit-based-non","title":"Reinforcement Learning for Edit-Based Non-Autoregressive Neural Machine Translation","date":"2024-05-02","arxiv_id":"2405.01280","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-igboapi-dataset-empowering-igbo-language","title":"The IgboAPI Dataset: Empowering Igbo Language Technologies through Multi-dialectal Enrichment","date":"2024-05-02","arxiv_id":"2405.00997","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-sample-specific-encoder","title":"Efficient Sample-Specific Encoder Perturbations","date":"2024-05-01","arxiv_id":"2405.01601","repositories_listed":0,"syntology":null},{"url":null,"slug":"suvach-generated-hindi-qa-benchmark","title":"Suvach -- Generated Hindi QA benchmark","date":"2024-04-30","arxiv_id":"2404.19254","repositories_listed":0,"syntology":null},{"url":null,"slug":"modeling-orthographic-variation-improves-nlp","title":"Modeling Orthographic Variation Improves NLP Performance for Nigerian Pidgin","date":"2024-04-28","arxiv_id":"2404.18264","repositories_listed":0,"syntology":null},{"url":null,"slug":"i-have-an-attention-bridge-to-sell-you","title":"I Have an Attention Bridge to Sell You: Generalization Capabilities of Modular Translation Architectures","date":"2024-04-27","arxiv_id":"2404.17918","repositories_listed":0,"syntology":null},{"url":null,"slug":"quality-estimation-with-k-nearest-neighbors","title":"Quality Estimation with $k$-nearest Neighbors and Automatic Evaluation for Model-specific Quality Estimation","date":"2024-04-27","arxiv_id":"2404.18031","repositories_listed":0,"syntology":null},{"url":null,"slug":"scaffold-bpe-enhancing-byte-pair-encoding","title":"Scaffold-BPE: Enhancing Byte Pair Encoding for Large Language Models with Simple and Effective Scaffold Token Removal","date":"2024-04-27","arxiv_id":"2404.17808","repositories_listed":0,"syntology":null},{"url":null,"slug":"usefulness-of-emotional-prosody-in-neural","title":"Usefulness of Emotional Prosody in Neural Machine Translation","date":"2024-04-27","arxiv_id":"2404.17968","repositories_listed":0,"syntology":null},{"url":null,"slug":"tigqa-an-expert-annotated-question-answering","title":"TIGQA:An Expert Annotated Question Answering Dataset in Tigrinya","date":"2024-04-26","arxiv_id":"2404.17194","repositories_listed":0,"syntology":null}],"record_sha256":"83bb271b879a3b8f6ade67648c7a1ad65c53f52b1b12d333acbd5e86510f3d7d","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}