{"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":"/method/sentencepiece","slug":"sentencepiece","name":"SentencePiece","full_name":"SentencePiece","full_name_withheld":false,"description_markdown":"**SentencePiece** is a subword tokenizer and detokenizer for natural language processing. It performs subword segmentation, supporting the byte-pair-encoding ([BPE](https://paperswithcode.com/method/bpe)) algorithm and unigram language model, and then converts this text into an id sequence guarantee perfect reproducibility of the normalization and subword segmentation.","description_state":"present","introduced_year":null,"introduced_by":{"title":null,"paper":null,"first_author":null,"n_authors":0,"url_abs":null,"archive_paper_url":null},"source":{"url":"http://arxiv.org/abs/1808.06226v1","title":"SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Natural Language Processing","area_id":"natural-language-processing","collection":"Tokenizers","url":"/methods/category/tokenizers","pwc_aliases":[]}],"n_papers_tagged":908,"archive_num_papers":null,"papers_newest_first":[{"paper":null,"slug":"a-multi-dataset-evaluation-of-models-for","title":"A Multi-Dataset Evaluation of Models for Automated Vulnerability Repair","date":"2025-06-05","arxiv_id":"2506.04987","n_code_links":0,"syntology":null},{"paper":null,"slug":"decom-renorm-merge-model-merging-on-the-right","title":"Decom-Renorm-Merge: Model Merging on the Right Space Improves Multitasking","date":"2025-05-29","arxiv_id":"2505.23117","n_code_links":0,"syntology":null},{"paper":"/paper/shioenv-a-cli-behavior-capturing-environment","slug":"shioenv-a-cli-behavior-capturing-environment","title":"ShIOEnv: A CLI Behavior-Capturing Environment Enabling Grammar-Guided Command Synthesis for Dataset Curation","date":"2025-05-23","arxiv_id":"2505.18374","n_code_links":1,"syntology":null},{"paper":null,"slug":"comparative-analysis-of-subword-tokenization","title":"Comparative analysis of subword tokenization approaches for Indian languages","date":"2025-05-22","arxiv_id":"2505.16868","n_code_links":0,"syntology":null},{"paper":"/paper/logicase-effective-test-case-generation-from","slug":"logicase-effective-test-case-generation-from","title":"LogiCase: Effective Test Case Generation from Logical Description in Competitive Programming","date":"2025-05-21","arxiv_id":"2505.15039","n_code_links":0,"syntology":{"ran":11,"of":19,"n_ran_checked":5,"n_instrument":6,"unverified":8,"pointer_only":19,"phrase":"11 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 6 where Syntology's instrument failed) · 8 unverified","official":null}},{"paper":"/paper/eeg-to-text-translation-a-model-for","slug":"eeg-to-text-translation-a-model-for","title":"EEG-to-Text Translation: A Model for Deciphering Human Brain Activity","date":"2025-05-20","arxiv_id":"2505.13936","n_code_links":1,"syntology":null},{"paper":"/paper/masking-in-multi-hop-qa-an-analysis-of-how","slug":"masking-in-multi-hop-qa-an-analysis-of-how","title":"Masking in Multi-hop QA: An Analysis of How Language Models Perform with Context Permutation","date":"2025-05-16","arxiv_id":"2505.11754","n_code_links":1,"syntology":null},{"paper":null,"slug":"multilingual-machine-translation-with-quantum","title":"Multilingual Machine Translation with Quantum Encoder Decoder Attention-based Convolutional Variational Circuits","date":"2025-05-14","arxiv_id":"2505.09407","n_code_links":0,"syntology":null},{"paper":null,"slug":"comparative-sentiment-analysis-of-public","title":"Comparative sentiment analysis of public perception: Monkeypox vs. COVID-19 behavioral insights","date":"2025-05-12","arxiv_id":"2505.07430","n_code_links":0,"syntology":null},{"paper":"/paper/cardioformer-advancing-ai-in-ecg-analysis","slug":"cardioformer-advancing-ai-in-ecg-analysis","title":"Cardioformer: Advancing AI in ECG Analysis with Multi-Granularity Patching and ResNet","date":"2025-05-08","arxiv_id":"2505.05538","n_code_links":1,"syntology":null},{"paper":null,"slug":"performance-evaluation-of-large-language-1","title":"Performance Evaluation of Large Language Models in Bangla Consumer Health Query Summarization","date":"2025-05-08","arxiv_id":"2505.05070","n_code_links":0,"syntology":null},{"paper":"/paper/gascade-grouped-summarization-of-adverse-drug","slug":"gascade-grouped-summarization-of-adverse-drug","title":"GASCADE: Grouped Summarization of Adverse Drug Event for Enhanced Cancer Pharmacovigilance","date":"2025-05-07","arxiv_id":"2505.04284","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-review-of-dna-restriction-free-overlapping","title":"A review of DNA restriction-free overlapping sequence cloning techniques for synthetic biology","date":"2025-05-06","arxiv_id":"2505.03681","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-character-based-diffusion-embedding","title":"A Character-based Diffusion Embedding Algorithm for Enhancing the Generation Quality of Generative Linguistic Steganographic Texts","date":"2025-05-02","arxiv_id":"2505.00977","n_code_links":0,"syntology":null},{"paper":null,"slug":"jaccdiv-a-metric-and-benchmark-for","title":"JaccDiv: A Metric and Benchmark for Quantifying Diversity of Generated Marketing Text in the Music Industry","date":"2025-04-29","arxiv_id":"2504.20849","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-are-qualified-benchmark","title":"Large Language Models are Qualified Benchmark Builders: Rebuilding Pre-Training Datasets for Advancing Code Intelligence Tasks","date":"2025-04-28","arxiv_id":"2504.19444","n_code_links":0,"syntology":null},{"paper":null,"slug":"fast-powerformer-a-memory-efficient","title":"Fast-Powerformer: A Memory-Efficient Transformer for Accurate Mid-Term Wind Power Forecasting","date":"2025-04-15","arxiv_id":"2504.10923","n_code_links":0,"syntology":null},{"paper":"/paper/sigma-a-dataset-for-text-to-code-semantic","slug":"sigma-a-dataset-for-text-to-code-semantic","title":"Sigma: A dataset for text-to-code semantic parsing with statistical analysis","date":"2025-04-05","arxiv_id":"2504.04301","n_code_links":1,"syntology":null},{"paper":null,"slug":"advancing-sentiment-analysis-in-tamil-english","title":"Advancing Sentiment Analysis in Tamil-English Code-Mixed Texts: Challenges and Transformer-Based Solutions","date":"2025-03-30","arxiv_id":"2503.23295","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-knowledge-graph-completion-with","title":"Enhancing Knowledge Graph Completion with Entity Neighborhood and Relation Context","date":"2025-03-29","arxiv_id":"2503.23205","n_code_links":0,"syntology":null},{"paper":"/paper/scaling-down-text-encoders-of-text-to-image","slug":"scaling-down-text-encoders-of-text-to-image","title":"Scaling Down Text Encoders of Text-to-Image Diffusion Models","date":"2025-03-25","arxiv_id":"2503.19897","n_code_links":1,"syntology":null},{"paper":"/paper/exploring-training-and-inference-scaling-laws","slug":"exploring-training-and-inference-scaling-laws","title":"Exploring Training and Inference Scaling Laws in Generative Retrieval","date":"2025-03-24","arxiv_id":"2503.18941","n_code_links":1,"syntology":null},{"paper":null,"slug":"predicting-the-road-ahead-a-knowledge-graph","title":"Predicting the Road Ahead: A Knowledge Graph based Foundation Model for Scene Understanding in Autonomous Driving","date":"2025-03-24","arxiv_id":"2503.18730","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-code-llm-training-with-programmer","title":"Enhancing Code LLM Training with Programmer Attention","date":"2025-03-19","arxiv_id":"2503.14936","n_code_links":0,"syntology":null},{"paper":null,"slug":"arled-leveraging-led-based-arman-model-for","title":"ARLED: Leveraging LED-based ARMAN Model for Abstractive Summarization of Persian Long Documents","date":"2025-03-13","arxiv_id":"2503.10233","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-longformer-based-framework-for-accurate-and","title":"A LongFormer-Based Framework for Accurate and Efficient Medical Text Summarization","date":"2025-03-10","arxiv_id":"2503.06888","n_code_links":0,"syntology":null},{"paper":"/paper/roamify-designing-and-evaluating-an-llm-based","slug":"roamify-designing-and-evaluating-an-llm-based","title":"Roamify: Designing and Evaluating an LLM Based Google Chrome Extension for Personalised Itinerary Planning","date":"2025-03-10","arxiv_id":"2504.10489","n_code_links":1,"syntology":null},{"paper":null,"slug":"seeing-delta-parameters-as-jpeg-images-data","title":"Seeing Delta Parameters as JPEG Images: Data-Free Delta Compression with Discrete Cosine Transform","date":"2025-03-09","arxiv_id":"2503.06676","n_code_links":0,"syntology":null},{"paper":null,"slug":"moemoe-question-guided-dense-and-scalable","title":"MoEMoE: Question Guided Dense and Scalable Sparse Mixture-of-Expert for Multi-source Multi-modal Answering","date":"2025-03-08","arxiv_id":"2503.06296","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-transformer-model-for-predicting-chemical","title":"A Transformer Model for Predicting Chemical Reaction Products from Generic Templates","date":"2025-03-04","arxiv_id":"2503.05810","n_code_links":0,"syntology":null},{"paper":"/paper/multimodal-representation-alignment-for-image","slug":"multimodal-representation-alignment-for-image","title":"Multimodal Representation Alignment for Image Generation: Text-Image Interleaved Control Is Easier Than You Think","date":"2025-02-27","arxiv_id":"2502.20172","n_code_links":1,"syntology":null},{"paper":null,"slug":"ldgen-enhancing-text-to-image-synthesis-via","title":"LDGen: Enhancing Text-to-Image Synthesis via Large Language Model-Driven Language Representation","date":"2025-02-25","arxiv_id":"2502.18302","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-fine-tuning-approach-for-t5-using-knowledge","title":"A Fine-Tuning Approach for T5 Using Knowledge Graphs to Address Complex Tasks","date":"2025-02-23","arxiv_id":"2502.16484","n_code_links":0,"syntology":null},{"paper":null,"slug":"corrections-meet-explanations-a-unified","title":"Corrections Meet Explanations: A Unified Framework for Explainable Grammatical Error Correction","date":"2025-02-21","arxiv_id":"2502.15261","n_code_links":0,"syntology":null},{"paper":null,"slug":"empowering-llms-with-logical-reasoning-a","title":"Empowering LLMs with Logical Reasoning: A Comprehensive Survey","date":"2025-02-21","arxiv_id":"2502.15652","n_code_links":0,"syntology":null},{"paper":"/paper/bridging-text-and-vision-a-multi-view-text","slug":"bridging-text-and-vision-a-multi-view-text","title":"Bridging Text and Vision: A Multi-View Text-Vision Registration Approach for Cross-Modal Place Recognition","date":"2025-02-20","arxiv_id":"2502.14195","n_code_links":1,"syntology":null},{"paper":null,"slug":"order-agnostic-identifier-for-large-language","title":"Order-agnostic Identifier for Large Language Model-based Generative Recommendation","date":"2025-02-15","arxiv_id":"2502.10833","n_code_links":0,"syntology":null},{"paper":"/paper/a-large-scale-benchmark-for-vietnamese","slug":"a-large-scale-benchmark-for-vietnamese","title":"A Large-Scale Benchmark for Vietnamese Sentence Paraphrases","date":"2025-02-11","arxiv_id":"2502.07188","n_code_links":1,"syntology":null},{"paper":null,"slug":"robust-and-secure-code-watermarking-for-large","title":"Robust and Secure Code Watermarking for Large Language Models via ML/Crypto Codesign","date":"2025-02-04","arxiv_id":"2502.02068","n_code_links":0,"syntology":null},{"paper":null,"slug":"explainable-ai-for-sentiment-analysis-of","title":"Explainable AI for Sentiment Analysis of Human Metapneumovirus (HMPV) Using XLNet","date":"2025-02-01","arxiv_id":"2502.01663","n_code_links":0,"syntology":null},{"paper":null,"slug":"general-embedding-vs-task-specific-embedding","title":"General Embedding vs. Task-Specific Embedding: A Comparative Approach to Enhancing NLP Performance","date":"2025-01-30","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/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","n_code_links":1,"syntology":null},{"paper":null,"slug":"diffusion-based-text-to-music-generation-with","title":"Diffusion based Text-to-Music Generation with Global and Local Text based Conditioning","date":"2025-01-24","arxiv_id":"2501.14680","n_code_links":0,"syntology":null},{"paper":"/paper/confidence-estimation-for-error-detection-in","slug":"confidence-estimation-for-error-detection-in","title":"Confidence Estimation for Error Detection in Text-to-SQL Systems","date":"2025-01-16","arxiv_id":"2501.09527","n_code_links":1,"syntology":null},{"paper":"/paper/exploring-robustness-of-multilingual-llms-on","slug":"exploring-robustness-of-multilingual-llms-on","title":"Exploring Robustness of Multilingual LLMs on Real-World Noisy Data","date":"2025-01-14","arxiv_id":"2501.08322","n_code_links":1,"syntology":null},{"paper":"/paper/mathreader-text-to-speech-for-mathematical","slug":"mathreader-text-to-speech-for-mathematical","title":"MathReader : Text-to-Speech for Mathematical Documents","date":"2025-01-13","arxiv_id":"2501.07088","n_code_links":1,"syntology":null},{"paper":null,"slug":"bridging-dialects-translating-standard-bangla","title":"Bridging Dialects: Translating Standard Bangla to Regional Variants Using Neural Models","date":"2025-01-10","arxiv_id":"2501.05749","n_code_links":0,"syntology":null},{"paper":null,"slug":"integrating-llms-with-its-recent-advances","title":"Integrating LLMs with ITS: Recent Advances, Potentials, Challenges, and Future Directions","date":"2025-01-08","arxiv_id":"2501.04437","n_code_links":0,"syntology":null},{"paper":"/paper/how-to-select-pre-trained-code-models-for","slug":"how-to-select-pre-trained-code-models-for","title":"How to Select Pre-Trained Code Models for Reuse? A Learning Perspective","date":"2025-01-07","arxiv_id":"2501.03783","n_code_links":1,"syntology":null},{"paper":null,"slug":"empowering-bengali-education-with-ai-solving","title":"Empowering Bengali Education with AI: Solving Bengali Math Word Problems through Transformer Models","date":"2025-01-05","arxiv_id":"2501.02599","n_code_links":0,"syntology":null},{"paper":"/paper/belin-a-novel-corpus-for-bengali-religious","slug":"belin-a-novel-corpus-for-bengali-religious","title":"BeliN: A Novel Corpus for Bengali Religious News Headline Generation using Contextual Feature Fusion","date":"2025-01-02","arxiv_id":"2501.01069","n_code_links":1,"syntology":null},{"paper":null,"slug":"reformer-generating-radio-fakes-for-data","title":"ReFormer: Generating Radio Fakes for Data Augmentation","date":"2024-12-31","arxiv_id":"2501.00282","n_code_links":0,"syntology":null},{"paper":"/paper/yad-leveraging-t5-for-improved-automatic","slug":"yad-leveraging-t5-for-improved-automatic","title":"YAD: Leveraging T5 for Improved Automatic Diacritization of Yorùbá Text","date":"2024-12-28","arxiv_id":"2412.20218","n_code_links":1,"syntology":null},{"paper":null,"slug":"assessing-text-classification-methods-for","title":"Assessing Text Classification Methods for Cyberbullying Detection on Social Media Platforms","date":"2024-12-27","arxiv_id":"2412.19928","n_code_links":0,"syntology":null},{"paper":null,"slug":"feature-alignment-based-knowledge","title":"Feature Alignment-Based Knowledge Distillation for Efficient Compression of Large Language Models","date":"2024-12-27","arxiv_id":"2412.19449","n_code_links":0,"syntology":null},{"paper":null,"slug":"hand-hierarchical-attention-network-for-multi","title":"HAND: Hierarchical Attention Network for Multi-Scale Handwritten Document Recognition and Layout Analysis","date":"2024-12-25","arxiv_id":"2412.18981","n_code_links":0,"syntology":null},{"paper":null,"slug":"optimizing-large-language-models-with-an","title":"Optimizing Large Language Models with an Enhanced LoRA Fine-Tuning Algorithm for Efficiency and Robustness in NLP Tasks","date":"2024-12-25","arxiv_id":"2412.18729","n_code_links":0,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":null,"slug":"htr-jand-handwritten-text-recognition-with","title":"HTR-JAND: Handwritten Text Recognition with Joint Attention Network and Knowledge Distillation","date":"2024-12-24","arxiv_id":"2412.18524","n_code_links":0,"syntology":null},{"paper":"/paper/an-experimental-evaluation-of-japanese","slug":"an-experimental-evaluation-of-japanese","title":"An Experimental Evaluation of Japanese Tokenizers for Sentiment-Based Text Classification","date":"2024-12-23","arxiv_id":"2412.17361","n_code_links":1,"syntology":null},{"paper":null,"slug":"identifying-cyberbullying-roles-in-social","title":"Identifying Cyberbullying Roles in Social Media","date":"2024-12-21","arxiv_id":"2412.16417","n_code_links":0,"syntology":null},{"paper":null,"slug":"adversarial-robustness-through-dynamic","title":"Adversarial Robustness through Dynamic Ensemble Learning","date":"2024-12-20","arxiv_id":"2412.16254","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-llms-obfuscate-code-a-systematic-analysis","title":"Can LLMs Obfuscate Code? A Systematic Analysis of Large Language Models into Assembly Code Obfuscation","date":"2024-12-20","arxiv_id":"2412.16135","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-first-multilingual-model-for-the","title":"The First Multilingual Model For The Detection of Suicide Texts","date":"2024-12-20","arxiv_id":"2412.15498","n_code_links":0,"syntology":null},{"paper":null,"slug":"llmcl-gec-advancing-grammatical-error","title":"LLMCL-GEC: Advancing Grammatical Error Correction with LLM-Driven Curriculum Learning","date":"2024-12-17","arxiv_id":"2412.12541","n_code_links":0,"syntology":null},{"paper":null,"slug":"graph-guided-textual-explanation-generation","title":"Graph-Guided Textual Explanation Generation Framework","date":"2024-12-16","arxiv_id":"2412.12318","n_code_links":0,"syntology":null},{"paper":null,"slug":"neural-text-normalization-for-luxembourgish","title":"Neural Text Normalization for Luxembourgish using Real-Life Variation Data","date":"2024-12-12","arxiv_id":"2412.09383","n_code_links":0,"syntology":null},{"paper":null,"slug":"text-generation-models-for-luxembourgish-with","title":"Text Generation Models for Luxembourgish with Limited Data: A Balanced Multilingual Strategy","date":"2024-12-12","arxiv_id":"2412.09415","n_code_links":0,"syntology":null},{"paper":"/paper/are-clinical-t5-models-better-for-clinical","slug":"are-clinical-t5-models-better-for-clinical","title":"Are Clinical T5 Models Better for Clinical Text?","date":"2024-12-08","arxiv_id":"2412.05845","n_code_links":1,"syntology":null},{"paper":null,"slug":"leveraging-large-language-models-for-20","title":"Leveraging Large Language Models for Comparative Literature Summarization with Reflective Incremental Mechanisms","date":"2024-12-03","arxiv_id":"2412.02149","n_code_links":0,"syntology":null},{"paper":"/paper/sitse-sinhala-text-simplification-dataset-and","slug":"sitse-sinhala-text-simplification-dataset-and","title":"SiTSE: Sinhala Text Simplification Dataset and Evaluation","date":"2024-12-02","arxiv_id":"2412.01293","n_code_links":1,"syntology":null},{"paper":"/paper/a-comprehensive-guide-to-explainable-ai-from","slug":"a-comprehensive-guide-to-explainable-ai-from","title":"A Comprehensive Guide to Explainable AI: From Classical Models to LLMs","date":"2024-12-01","arxiv_id":"2412.00800","n_code_links":1,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-extensive-evaluation-of-factual","title":"An Extensive Evaluation of Factual Consistency in Large Language Models for Data-to-Text Generation","date":"2024-11-28","arxiv_id":"2411.19203","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-survey-on-cutting-edge-relation-extraction","title":"A survey on cutting-edge relation extraction techniques based on language models","date":"2024-11-27","arxiv_id":"2411.18157","n_code_links":0,"syntology":null},{"paper":"/paper/linguistic-laws-meet-protein-sequences-a","slug":"linguistic-laws-meet-protein-sequences-a","title":"Linguistic Laws Meet Protein Sequences: A Comparative Analysis of Subword Tokenization Methods","date":"2024-11-26","arxiv_id":"2411.17669","n_code_links":1,"syntology":null},{"paper":null,"slug":"generative-fuzzy-system-for-sequence","title":"Generative Fuzzy System for Sequence Generation","date":"2024-11-21","arxiv_id":"2411.13867","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-combined-encoder-and-transformer-approach","title":"A Combined Encoder and Transformer Approach for Coherent and High-Quality Text Generation","date":"2024-11-19","arxiv_id":"2411.12157","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-multi-class-disease-classification","title":"Enhancing Multi-Class Disease Classification: Neoplasms, Cardiovascular, Nervous System, and Digestive Disorders Using Advanced LLMs","date":"2024-11-19","arxiv_id":"2411.12712","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-multimodal-models-for-enhanced","title":"Leveraging Multimodal Models for Enhanced Neuroimaging Diagnostics in Alzheimer's Disease","date":"2024-11-12","arxiv_id":"2411.07871","n_code_links":0,"syntology":null},{"paper":"/paper/regress-don-t-guess-a-regression-like-loss-on","slug":"regress-don-t-guess-a-regression-like-loss-on","title":"Regress, Don't Guess -- A Regression-like Loss on Number Tokens for Language Models","date":"2024-11-04","arxiv_id":"2411.02083","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["tum-ai/number-token-loss"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/training-free-regional-prompting-for","slug":"training-free-regional-prompting-for","title":"Training-free Regional Prompting for Diffusion Transformers","date":"2024-11-04","arxiv_id":"2411.02395","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["instantX-research/Regional-Prompting-FLUX"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/protransformer-robustify-transformers-via","slug":"protransformer-robustify-transformers-via","title":"ProTransformer: Robustify Transformers via Plug-and-Play Paradigm","date":"2024-10-30","arxiv_id":"2410.23182","n_code_links":1,"syntology":null},{"paper":"/paper/building-a-coding-assistant-via-the-retrieval","slug":"building-a-coding-assistant-via-the-retrieval","title":"Building A Coding Assistant via the Retrieval-Augmented Language Model","date":"2024-10-21","arxiv_id":"2410.16229","n_code_links":1,"syntology":null},{"paper":null,"slug":"unlocking-legal-knowledge-a-multilingual","title":"Unlocking Legal Knowledge: A Multilingual Dataset for Judicial Summarization in Switzerland","date":"2024-10-17","arxiv_id":"2410.13456","n_code_links":0,"syntology":null},{"paper":null,"slug":"tokenization-and-morphology-in-multilingual","title":"Tokenization and Morphology in Multilingual Language Models: A Comparative Analysis of mT5 and ByT5","date":"2024-10-15","arxiv_id":"2410.11627","n_code_links":0,"syntology":null},{"paper":"/paper/rethinking-legal-judgement-prediction-in-a","slug":"rethinking-legal-judgement-prediction-in-a","title":"Rethinking Legal Judgement Prediction in a Realistic Scenario in the Era of Large Language Models","date":"2024-10-14","arxiv_id":"2410.10542","n_code_links":1,"syntology":null},{"paper":"/paper/sana-efficient-high-resolution-image","slug":"sana-efficient-high-resolution-image","title":"SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformers","date":"2024-10-14","arxiv_id":"2410.10629","n_code_links":2,"syntology":null},{"paper":null,"slug":"single-ground-truth-is-not-enough-add","title":"Single Ground Truth Is Not Enough: Add Linguistic Variability to Aspect-based Sentiment Analysis Evaluation","date":"2024-10-13","arxiv_id":"2410.09807","n_code_links":0,"syntology":null},{"paper":"/paper/enhancing-sparql-generation-by-triplet-order","slug":"enhancing-sparql-generation-by-triplet-order","title":"Enhancing SPARQL Generation by Triplet-order-sensitive Pre-training","date":"2024-10-08","arxiv_id":"2410.05731","n_code_links":1,"syntology":null},{"paper":null,"slug":"leveraging-free-energy-in-pretraining-model","title":"Leveraging free energy in pretraining model selection for improved fine-tuning","date":"2024-10-08","arxiv_id":"2410.05612","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-transfer-learning-based-peer-review","title":"Deep Transfer Learning Based Peer Review Aggregation and Meta-review Generation for Scientific Articles","date":"2024-10-05","arxiv_id":"2410.04202","n_code_links":0,"syntology":null},{"paper":"/paper/sieve-general-purpose-data-filtering-system","slug":"sieve-general-purpose-data-filtering-system","title":"GPT-4o as the Gold Standard: A Scalable and General Purpose Approach to Filter Language Model Pretraining Data","date":"2024-10-03","arxiv_id":"2410.02755","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-llm-fine-tuning-for-text-to-sqls-by","title":"Enhancing LLM Fine-tuning for Text-to-SQLs by SQL Quality Measurement","date":"2024-10-02","arxiv_id":"2410.01869","n_code_links":0,"syntology":null},{"paper":null,"slug":"glmha-a-guided-low-rank-multi-head-self","title":"GLMHA A Guided Low-rank Multi-Head Self-Attention for Efficient Image Restoration and Spectral Reconstruction","date":"2024-10-01","arxiv_id":"2410.00380","n_code_links":0,"syntology":null},{"paper":null,"slug":"abstractive-summarization-of-low-resourced","title":"Abstractive Summarization of Low resourced Nepali language using Multilingual Transformers","date":"2024-09-29","arxiv_id":"2409.19566","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-automatic-keyphrase-labelling-with","title":"Enhancing Automatic Keyphrase Labelling with Text-to-Text Transfer Transformer (T5) Architecture: A Framework for Keyphrase Generation and Filtering","date":"2024-09-25","arxiv_id":"2409.16760","n_code_links":0,"syntology":null},{"paper":null,"slug":"probing-omissions-and-distortions-in","title":"Probing Omissions and Distortions in Transformer-based RDF-to-Text Models","date":"2024-09-25","arxiv_id":"2409.16707","n_code_links":0,"syntology":null},{"paper":null,"slug":"do-the-right-thing-just-debias-multi-category","title":"Do the Right Thing, Just Debias! Multi-Category Bias Mitigation Using LLMs","date":"2024-09-24","arxiv_id":"2409.16371","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-academic-skills-assessment-with-nlp","title":"Improving Academic Skills Assessment with NLP and Ensemble Learning","date":"2024-09-23","arxiv_id":"2409.19013","n_code_links":0,"syntology":null}],"papers_shown":100,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":908,"with_a_code_link":438,"where_syntology_ran_a_sample":111,"not_listed_spam_title":0,"listed":908,"listed_where_code_ran":111,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":96,"every_run_a_failure_of_syntologys_instrument":15,"listed_with_a_run_with_no_instrument_failure":96,"listed_every_run_a_failure_of_syntologys_instrument":15,"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"},"papers_where_code_ran":111,"papers_where_code_ran_first_page":"/method/sentencepiece/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not isolate this method inside it.","pages":[{"order":"archive","page":2,"of":10,"url":"/method/sentencepiece/papers/2","json":"/method/sentencepiece/papers/2.json","rows":100},{"order":"archive","page":3,"of":10,"url":"/method/sentencepiece/papers/3","json":"/method/sentencepiece/papers/3.json","rows":100},{"order":"archive","page":4,"of":10,"url":"/method/sentencepiece/papers/4","json":"/method/sentencepiece/papers/4.json","rows":100},{"order":"archive","page":5,"of":10,"url":"/method/sentencepiece/papers/5","json":"/method/sentencepiece/papers/5.json","rows":100},{"order":"archive","page":6,"of":10,"url":"/method/sentencepiece/papers/6","json":"/method/sentencepiece/papers/6.json","rows":100},{"order":"archive","page":7,"of":10,"url":"/method/sentencepiece/papers/7","json":"/method/sentencepiece/papers/7.json","rows":100},{"order":"archive","page":8,"of":10,"url":"/method/sentencepiece/papers/8","json":"/method/sentencepiece/papers/8.json","rows":100},{"order":"archive","page":9,"of":10,"url":"/method/sentencepiece/papers/9","json":"/method/sentencepiece/papers/9.json","rows":100},{"order":"archive","page":10,"of":10,"url":"/method/sentencepiece/papers/10","json":"/method/sentencepiece/papers/10.json","rows":8},{"order":"ran","page":1,"of":2,"url":"/method/sentencepiece/papers/ran/1","json":"/method/sentencepiece/papers/ran/1.json","rows":100},{"order":"ran","page":2,"of":2,"url":"/method/sentencepiece/papers/ran/2","json":"/method/sentencepiece/papers/ran/2.json","rows":11}],"tasks":[{"task":"/task/language-modelling","name":"Language Modelling","papers":154},{"task":"/task/language-modeling","name":"Language Modeling","papers":123},{"task":"/task/question-answering","name":"Question Answering","papers":104},{"task":"/task/sentence","name":"Sentence","papers":82},{"task":"/task/decoder","name":"Decoder","papers":78},{"task":"/task/text-generation","name":"Text Generation","papers":73},{"task":"/task/translation","name":"Translation","papers":61},{"task":"/task/machine-translation","name":"Machine Translation","papers":55},{"task":"/task/transfer-learning","name":"Transfer Learning","papers":54},{"task":"/task/retrieval","name":"Retrieval","papers":47},{"task":"/task/sentiment-analysis","name":"Sentiment Analysis","papers":41},{"task":"/task/natural-language-understanding","name":"Natural Language Understanding","papers":37},{"task":"/task/data-augmentation","name":"Data Augmentation","papers":29},{"task":"/task/text-classification","name":"Text Classification","papers":29},{"task":"/task/natural-language-inference","name":"Natural Language Inference","papers":26},{"task":"/task/reading-comprehension","name":"Reading Comprehension","papers":24},{"task":"/task/text-classification-1","name":"text-classification","papers":24},{"task":"/task/abstractive-text-summarization","name":"Abstractive Text Summarization","papers":23},{"task":"/task/semantic-parsing","name":"Semantic Parsing","papers":23},{"task":"/task/articles","name":"Articles","papers":21}],"tasks_shown":20,"n_tasks":560,"usage_by_year":[{"year":"2018","papers":1},{"year":"2019","papers":27},{"year":"2020","papers":97},{"year":"2021","papers":154},{"year":"2022","papers":185},{"year":"2023","papers":219},{"year":"2024","papers":174},{"year":"2025","papers":51}],"row_source":"embedded","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/sentencepiece"},"syntology_read_at":"2026-10-05T00:36:11+00:00","syntology":{"source":"Syntology's have check for this name (the free coverage lookup), read from Syntology's graph","have_url":"https://syntology.ai/api/graph/have?x=SentencePiece","read_at":"2026-10-05T01:01:48+00:00","query":"SentencePiece","kind":"method","have":"declared_code","tier":"repo_known","verified_implementation":false,"level":null,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":{"method":"SentencePiece","origin_arxiv_id":"1808.06226"},"resolution":"exact","resolved_name_differs":false,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":"unknown","archive_paper_arxiv_id":null,"repositories":{"listed":3,"in_graph":3,"list_truncated":false,"strongest_link":"mentioned_in_paper"},"retrieve_with":null,"name_competition":{"verdict":"sole_bearer","may_be_wrong_sense":false,"bearers_found":1,"served":{"arxiv_id":"1808.06226","citations":4273},"leading_other_bearer":null,"n_other_bearers_listed":0,"note":"Nothing else in this corpus is named 'SentencePiece'. That is a statement about this corpus and not about the field: short names are reused, and a sense we never collected cannot show up here. Confirm `served.arxiv_id` if you had a specific paper in mind."},"name_competition_text":null,"near_matches":null,"code_nearby":[],"code_nearby_caption":null,"origin_paper":{"arxiv_id":"1808.06226","page":"/paper/sentencepiece-a-simple-and-language-1","syntology_url":"https://syntology.ai/paper/1808.06226","in_graph_layer":false,"samples":0},"line":"repository known, no verified implementation (declared_code; repositories: 3 listed of 3 in the graph, strongest link: mentioned in the paper). The archive credits no paper with an arXiv id for this method, so whether this answer (about arXiv:1808.06226) is about this method is not checked.","level_legend":null},"syntology_have_state":"loaded","record_sha256":"b4f9fca8f3b9579e6c90f9809da1611b0fc7d9f90db2dedaa704bc474aec0194","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}