Stanza: A Python Natural Language Processing Toolkit for Many Human Languages
Not on the map. Why?
Abstract (arXiv)
We introduce Stanza, an open-source Python natural language processing toolkit supporting 66 human languages. Compared to existing widely used toolkits, Stanza features a language-agnostic fully neural pipeline for text analysis, including tokenization, multi-word token expansion, lemmatization, part-of-speech and morphological feature tagging, dependency parsing, and named entity recognition. We have trained Stanza on a total of 112 datasets, including the Universal Dependencies treebanks and other multilingual corpora, and show that the same neural architecture generalizes well and achieves competitive performance on all languages tested. Additionally, Stanza includes a native Python interface to the widely used Java Stanford CoreNLP software, which further extends its functionality to cover other tasks such as coreference resolution and relation extraction. Source code, documentation, and pretrained models for 66 languages are available at https://stanfordnlp.github.io/stanza.
Key facts. Cited by 719 papers in the map (data through 7 Oct 2026). First posted on arXiv 16 Mar 2020.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 137; 2022: 122; 2023: 139; 2024: 121; 2025: 107; 2026: 93.
719 papers.
Sort:
By area:
- 2022Training-Free Structured Diffusion Guidance for Compositional Text-to-Image Synthesiscited by 386
- 2021How Much Can CLIP Benefit Vision-and-Language Tasks?cited by 321
- 2022CoAuthor: Designing a Human-AI Collaborative Writing Dataset for Exploring Language Model Capabilitiescited by 245
- 2022Large Language Models are Few-Shot Clinical Information Extractorscited by 206
- 2023The BigScience ROOTS Corpus: A 1.6TB Composite Multilingual Datasetcited by 148
- 2021ContractNLI: A Dataset for Document-level Natural Language Inference for Contractscited by 145
- 2021End-to-End Training of Multi-Document Reader and Retriever for Open-Domain Question Answeringcited by 133
- 2023MAGE: Machine-generated Text Detection in the Wildcited by 130
- 2023Training Language Models with Language Feedback at Scalecited by 125
- 2024MIGC: Multi-Instance Generation Controller for Text-to-Image Synthesiscited by 123
- 2021CLIFF: Contrastive Learning for Improving Faithfulness and Factuality in Abstractive Summarizationcited by 120
- 2021LGESQL: Line Graph Enhanced Text-to-SQL Model with Mixed Local and Non-Local Relationscited by 119
38 more
- 2022CLIP Models are Few-shot Learners: Empirical Studies on VQA and Visual Entailmentcited by 113
- 2023A Critical Evaluation of Evaluations for Long-form Question Answeringcited by 111
- 2021Fully Hyperbolic Neural Networkscited by 107
- 2023The Curious Decline of Linguistic Diversity: Training Language Models on Synthetic Textcited by 97
- 2021Is GPT-3 Text Indistinguishable from Human Text? Scarecrow: A Framework for Scrutinizing Machine Textcited by 89
- 2022RoentGen: Vision-Language Foundation Model for Chest X-ray Generationcited by 89
- 2022RASAT: Integrating Relational Structures into Pretrained Seq2Seq Model for Text-to-SQLcited by 85
- 2022Improving the Factual Correctness of Radiology Report Generation with Semantic Rewardscited by 82
- 2021Joint Learning of Localized Representations from Medical Images and Reportscited by 81
- 2023Sentence Embedding Leaks More Information than You Expect: Generative Embedding Inversion Attack to Recover the Whole Sentencecited by 81
- 2023Large language models effectively leverage document-level context for literary translation, but critical errors persistcited by 80
- 2021End-to-End Training of Neural Retrievers for Open-Domain Question Answeringcited by 75
- 2021Improving Faithfulness in Abstractive Summarization with Contrast Candidate Generation and Selectioncited by 75
- 2023Dictionary-based Phrase-level Prompting of Large Language Models for Machine Translationcited by 74
- 2021Understanding by Understanding Not: Modeling Negation in Language Modelscited by 73
- 2021Vision-and-Language or Vision-for-Language? On Cross-Modal Influence in Multimodal Transformerscited by 71
- 2022TweetNLP: Cutting-Edge Natural Language Processing for Social Mediacited by 71
- 2021Trankit: A Light-Weight Transformer-based Toolkit for Multilingual Natural Language Processingcited by 68
- 2021Knowledge Matters: Radiology Report Generation with General and Specific Knowledgecited by 68
- 2021Common Sense Beyond English: Evaluating and Improving Multilingual Language Models for Commonsense Reasoningcited by 64
- 2023Contrasting Linguistic Patterns in Human and LLM-Generated News Textcited by 62
- 2021Conditional probing: measuring usable information beyond a baselinecited by 61
- 2023FactKG: Fact Verification via Reasoning on Knowledge Graphscited by 57
- 2021How to Adapt Your Pretrained Multilingual Model to 1600 Languagescited by 54
- 2024Toward Visual Grounding: A Surveycited by 52
- 2022Perturbation Augmentation for Fairer NLPcited by 51
- 2023Fighting Fire with Fire: The Dual Role of LLMs in Crafting and Detecting Elusive Disinformationcited by 51
- 2021Language Model as an Annotator: Exploring DialoGPT for Dialogue Summarizationcited by 46
- 2021NeuTral Rewriter: A Rule-Based and Neural Approach to Automatic Rewriting into Gender-Neutral Alternativescited by 46
- 2022Expanding Pretrained Models to Thousands More Languages via Lexicon-based Adaptationcited by 44
- 2021Controlling Hallucinations at Word Level in Data-to-Text Generationcited by 41
- 2021When is BERT Multilingual? Isolating Crucial Ingredients for Cross-lingual Transfercited by 41
- 2022Local-Global Context Aware Transformer for Language-Guided Video Segmentationcited by 41
- 2021Ask what's missing and what's useful: Improving Clarification Question Generation using Global Knowledgecited by 40
- 2022Multilingual Generative Language Models for Zero-Shot Cross-Lingual Event Argument Extractioncited by 40
- 2021Systematic Generalization with Edge Transformerscited by 38
- 2024Benchmarking Linguistic Diversity of Large Language Modelscited by 37
- 2021Diagnosing Vision-and-Language Navigation: What Really Matterscited by 36
50 most cited of 719 All 719 (JSON)
- 2026Compound interpretation is based on analogy1 Oct 2026
- 2026Synthetic Data Characterization via Training Dynamics30 Sep 2026
- 2026Using LMs to Model the Effects of Context and Coreference during Sentence Comprehension26 Sep 2026
- 2026ChunkRank: Model-Aware Text Chunking and Abstention-Aware Answer Selection for LLM Pipelines24 Sep 2026
- 2026Can Classical Semantic-Extractive Summarization Be Evaluated in Hindi? A Replication Study24 Sep 2026
- 2026ThaiTrees: Thai Syntactic Dependency Trees Across Domains23 Sep 2026
- 2026PANORAMA: Panoptic Grounded Captioning via Mask Proposal Selection16 Sep 2026
- 2026Modeling the Developmental Shift in Telicity Acquisition16 Sep 2026
- 2026Doc2FRC: Length-Consistent Document-Level Machine Translation via Fixed-Range Chunking11 Sep 2026
- 2026SalamandraTA at WMT 2026 Terminology Shared Task: Hard Examples Are Better Teachers9 Sep 2026
- 2026Correction as Annotation: Bootstrapping a Dependency Parser for Documentary Medieval Latin5 Sep 2026
- 2026DPH Parser: A Bottom-Up Grammar-Driven Parser for Joint Constituency and Dependency Analysis5 Sep 2026
38 more
- 2026A Layered Taxonomy for Chinese Learner Grammatical Error Annotation2 Sep 2026
- 2026Beyond Magnitude: Contrastive Routing for Modular Mixture-of-Experts1 Sep 2026
- 2026Using Prosody to Predict Syntactic Structure31 Aug 2026
- 2026Mapping Written Words to Spoken Words in a Different Language Using Only Visual Grounding27 Aug 2026
- 2026Figurative Justice: Detecting metaphors in Hindi judgements with qualitative assessment and transformers23 Aug 2026
- 2026SynFlow: A Multidimensional Diachronic Semantic Analysis Toolkit19 Aug 2026
- 2026Left-Branching Transformers Excel at Right-Branching Languages: Data Shapes Word Order Preferences in Language Models15 Aug 2026
- 2026Comparing British and American Audio Description of Movies10 Aug 2026
- 2026A Grounded and Decomposed Framework for Relation-Level Hallucination Evaluation in Abstractive Summarization8 Aug 2026
- 2026SAGA: Score-Weighted Adaptive Generation Alignment for Low-Resource Nordic Language Models6 Aug 2026
- 2026Language Models Generalize to Human-like Word Order Preferences5 Aug 2026
- 2026ANNOTARES: A Dataset for Extracting Logical Structures from German Statutory Texts4 Aug 2026
- 2026ChronoLens: Measuring Language Change Across Time, Languages, and Linguistic Levels4 Aug 2026
- 2026Rectify Then Diffuse: Disentangling Concepts Before Denoising Trajectory Unfolds4 Aug 2026
- 2026The Role of Disfluencies in Speech Translation3 Aug 2026
- 2026Lightweight Person-Place Relation Extraction from Historical Newspapers with Dependency Graphs and Proximity Features22 Jul 2026
- 2026Do It Right! A Methodology for Successful NLP System Development6 Jul 2026
- 2026CORTEX: High-Quality Cross-Domain Organization of Web-Scale Corpora through Ontological Corpus Graph29 Jun 2026
- 2026Which Tokens Need Context? A Reference-Based Analysis of Translation Responsibility Using Fertility and Entropy28 Jun 2026
- 2026Mapping Political-Elite Networks in Europe with a Multilingual Joint Entity-Relation Extraction Pipeline25 Jun 2026
- 2026FreeStory: Training-Free Character Consistency for Free-Form Visual Storytelling23 Jun 2026
- 2026Speaking in Self-Assessing Tongues: On the Verbalized Confidence of LLMs in Machine Translation15 Jun 2026
- 2026When Does Mixing Help? Analyzing Query Embedding Interpolation in Multilingual Dense Retrieval11 Jun 2026
- 2026AfriSUD: A Dependency Treebank Collection for Evaluating Models on African Languages10 Jun 2026
- 2026Summarization is Not Dead Yet6 Jun 2026
- 2026Uncovering Temporal Framing in the News29 May 2026
- 2026CorPipe at CRAC 2026: Empty Nodes and Cross-Lingual Transfer in Multilingual Coreference Resolution28 May 2026
- 2026LLMBridge: An LLM Pipeline for End-to-end Referential Bridging Resolution in English27 May 2026
- 2026Breaking the Script Barrier: Enabling Automatic Alignment for PoS-based ASR Error Analysis in Non-Latin Scripts27 May 2026
- 2026Testing the Deliteralization Hypothesis in Human and Machine Translation25 May 2026
- 2026AI-Associated Lexical Shifts Across 34 Languages: Cross-Lingual Convergence and Diachronic Uptake in News Writing25 May 2026
- 2026Exploration of Perceptual Speech Features for Clinical Decision-Support in Mental Health Care23 May 2026
- 2026Robust LLM Watermarking with Minimal Semantic Distortion for IP Protection22 May 2026
- 2026A Reproducible Universal Dependencies-Style Pipeline for Katharevousa Greek Parliamentary Text21 May 2026
- 2026Whose Voice Counts? Mapping Stakeholder Perspectives on AI Through Public Submissions to the U.S. Government21 May 2026
- 2026CAIT: A Syntactic Parsing Toolkit for Child-Adult InTeractions19 May 2026
- 2026TILT: Improving Compositional Generation in Diffusion Models with a Model-Intrinsic Reward16 May 2026
- 2026Edit-level Majority Voting Mitigates Over-Correction in LLM-based Grammatical Error Correction13 May 2026
50 newest of 719 All 719 (JSON)
- 2022RoentGen: Vision-Language Foundation Model for Chest X-ray Generationcited by 89
- 2023GroundVLP: Harnessing Zero-shot Visual Grounding from Vision-Language Pre-training and Open-Vocabulary Object Detectioncited by 20
- 2024Magnet: We Never Know How Text-to-Image Diffusion Models Work, Until We Learn How Vision-Language Models Functioncited by 19
- 2023GIVL: Improving Geographical Inclusivity of Vision-Language Models with Pre-Training Methodscited by 11
- 2023World-to-Words: Grounded Open Vocabulary Acquisition through Fast Mapping in Vision-Language Modelscited by 10
- 2024mOSCAR: A Large-scale Multilingual and Multimodal Document-level Corpuscited by 8
- 2025From Head to Tail: Towards Balanced Representation in Large Vision-Language Models through Adaptive Data Calibrationcited by 8
- 2025Scaling Laws for Conditional Emergence of Multilingual Image Captioning via Generalization from Translationcited by 0
- 2026ViX-Ray: A Vietnamese Chest X-Ray Dataset for Vision-Language Modelscited by 0
- 2026Learning to See What You Need: Gaze Attention for Multimodal Large Language Modelscited by 0
- 2026Learning to See What You Need: Gaze Attention for Multimodal Large Language Models13 May 2026
- 2026ViX-Ray: A Vietnamese Chest X-Ray Dataset for Vision-Language Models16 Mar 2026
- 2025From Head to Tail: Towards Balanced Representation in Large Vision-Language Models through Adaptive Data Calibration17 Mar 2025
- 2025Scaling Laws for Conditional Emergence of Multilingual Image Captioning via Generalization from Translation12 Mar 2025
- 2024Magnet: We Never Know How Text-to-Image Diffusion Models Work, Until We Learn How Vision-Language Models Function30 Sep 2024
- 2024mOSCAR: A Large-scale Multilingual and Multimodal Document-level Corpus13 Jun 2024
- 2023GroundVLP: Harnessing Zero-shot Visual Grounding from Vision-Language Pre-training and Open-Vocabulary Object Detection22 Dec 2023
- 2023World-to-Words: Grounded Open Vocabulary Acquisition through Fast Mapping in Vision-Language Models14 Jun 2023
- 2023GIVL: Improving Geographical Inclusivity of Vision-Language Models with Pre-Training Methods5 Jan 2023
- 2022RoentGen: Vision-Language Foundation Model for Chest X-ray Generation23 Nov 2022
- 2022Training-Free Structured Diffusion Guidance for Compositional Text-to-Image Synthesiscited by 386
- 2024Diffusion Lens: Interpreting Text Encoders in Text-to-Image Pipelinescited by 28
- 2026Parallelism and Generation Order in Masked Diffusion Language Models: Limits Today, Potential Tomorrowcited by 8
- 2025Steer Away From Mode Collisions: Improving Composition In Diffusion Modelscited by 4
- 2023Semantic Guidance Tuning for Text-To-Image Diffusion Modelscited by 1
- 2026Rectify Then Diffuse: Disentangling Concepts Before Denoising Trajectory Unfoldscited by 1
- 2025PiCo: Enhancing Text-Image Alignment with Improved Noise Selection and Precise Mask Control in Diffusion Modelscited by 0
- 2026TILT: Improving Compositional Generation in Diffusion Models with a Model-Intrinsic Rewardcited by 0
- 2026Rectify Then Diffuse: Disentangling Concepts Before Denoising Trajectory Unfolds4 Aug 2026
- 2026TILT: Improving Compositional Generation in Diffusion Models with a Model-Intrinsic Reward16 May 2026
- 2026Parallelism and Generation Order in Masked Diffusion Language Models: Limits Today, Potential Tomorrow22 Jan 2026
- 2025Steer Away From Mode Collisions: Improving Composition In Diffusion Models30 Sep 2025
- 2025PiCo: Enhancing Text-Image Alignment with Improved Noise Selection and Precise Mask Control in Diffusion Models6 May 2025
- 2024Diffusion Lens: Interpreting Text Encoders in Text-to-Image Pipelines9 Mar 2024
- 2023Semantic Guidance Tuning for Text-To-Image Diffusion Models26 Dec 2023
- 2022Training-Free Structured Diffusion Guidance for Compositional Text-to-Image Synthesis9 Dec 2022
- 2021End-to-End Training of Multi-Document Reader and Retriever for Open-Domain Question Answeringcited by 133
- 2025XRAG: Cross-lingual Retrieval-Augmented Generationcited by 9
- 2024Context-Driven Index Trimming: A Data Quality Perspective to Enhancing Precision of RALMscited by 5
- 2024Retrieval-Augmented Code Generation for Situated Action Generation: A Case Study on Minecraftcited by 4
- 2026Use Graph When It Needs: Efficiently and Adaptively Integrating Retrieval-Augmented Generation with Graphscited by 3
- 2024You Only Use Reactive Attention Slice For Long Context Retrievalcited by 1
- 2026Adaptive Chunking: Optimizing Chunking-Method Selection for RAGcited by 1
- 2026Adaptive Chunking: Optimizing Chunking-Method Selection for RAG26 Mar 2026
- 2026Use Graph When It Needs: Efficiently and Adaptively Integrating Retrieval-Augmented Generation with Graphs3 Feb 2026
- 2025XRAG: Cross-lingual Retrieval-Augmented Generation15 May 2025
- 2024You Only Use Reactive Attention Slice For Long Context Retrieval3 Sep 2024
- 2024Context-Driven Index Trimming: A Data Quality Perspective to Enhancing Precision of RALMs10 Aug 2024
- 2024Retrieval-Augmented Code Generation for Situated Action Generation: A Case Study on Minecraft25 Jun 2024
- 2021End-to-End Training of Multi-Document Reader and Retriever for Open-Domain Question Answering9 Jun 2021
- 2023Training Language Models with Language Feedback at Scalecited by 125
- 2025SimulPL: Aligning Human Preferences in Simultaneous Machine Translationcited by 7
- 2025Alleviating Distribution Shift in Synthetic Data for Machine Translation Quality Estimationcited by 4
- 2026SAGA: Score-Weighted Adaptive Generation Alignment for Low-Resource Nordic Language Modelscited by 0
- 2026SAGA: Score-Weighted Adaptive Generation Alignment for Low-Resource Nordic Language Models6 Aug 2026
- 2025Alleviating Distribution Shift in Synthetic Data for Machine Translation Quality Estimation27 Feb 2025
- 2025SimulPL: Aligning Human Preferences in Simultaneous Machine Translation2 Feb 2025
- 2023Training Language Models with Language Feedback at Scale28 Mar 2023
- 2023Rephrase, Augment, Reason: Visual Grounding of Questions for Vision-Language Modelscited by 14
- 2024CHECKWHY: Causal Fact Verification via Argument Structurecited by 9
- 2025ExpliCa: Evaluating Explicit Causal Reasoning in Large Language Modelscited by 3
- 2025LFC-DA: Logical Formula-Controlled Data Augmentation for Enhanced Logical Reasoningcited by 0
- 2025LFC-DA: Logical Formula-Controlled Data Augmentation for Enhanced Logical Reasoning5 Nov 2025
- 2025ExpliCa: Evaluating Explicit Causal Reasoning in Large Language Models21 Feb 2025
- 2024CHECKWHY: Causal Fact Verification via Argument Structure20 Aug 2024
- 2023Rephrase, Augment, Reason: Visual Grounding of Questions for Vision-Language Models9 Oct 2023
- 2024Revisiting Who's Harry Potter: Towards Targeted Unlearning from a Causal Intervention Perspectivecited by 33
- 2025Sparse-Autoencoder-Guided Internal Representation Unlearning for Large Language Modelscited by 3
- 2026Robust LLM Watermarking with Minimal Semantic Distortion for IP Protectioncited by 1
- 2026Robust LLM Watermarking with Minimal Semantic Distortion for IP Protection22 May 2026
- 2025Sparse-Autoencoder-Guided Internal Representation Unlearning for Large Language Models19 Sep 2025
- 2024Revisiting Who's Harry Potter: Towards Targeted Unlearning from a Causal Intervention Perspective24 Jul 2024
- 2021How Much Can CLIP Benefit Vision-and-Language Tasks?cited by 321
- 2022CoAuthor: Designing a Human-AI Collaborative Writing Dataset for Exploring Language Model Capabilitiescited by 245
- 2022Large Language Models are Few-Shot Clinical Information Extractorscited by 206
- 2023The BigScience ROOTS Corpus: A 1.6TB Composite Multilingual Datasetcited by 148
- 2021ContractNLI: A Dataset for Document-level Natural Language Inference for Contractscited by 145
- 2023MAGE: Machine-generated Text Detection in the Wildcited by 130
- 2024MIGC: Multi-Instance Generation Controller for Text-to-Image Synthesiscited by 123
- 2021CLIFF: Contrastive Learning for Improving Faithfulness and Factuality in Abstractive Summarizationcited by 120
- 2021LGESQL: Line Graph Enhanced Text-to-SQL Model with Mixed Local and Non-Local Relationscited by 119
- 2022CLIP Models are Few-shot Learners: Empirical Studies on VQA and Visual Entailmentcited by 113
- 2023A Critical Evaluation of Evaluations for Long-form Question Answeringcited by 111
- 2021Fully Hyperbolic Neural Networkscited by 107
12 most cited of 679 All 679 (JSON)
- 2026Compound interpretation is based on analogy1 Oct 2026
- 2026Using LMs to Model the Effects of Context and Coreference during Sentence Comprehension26 Sep 2026
- 2026ChunkRank: Model-Aware Text Chunking and Abstention-Aware Answer Selection for LLM Pipelines24 Sep 2026
- 2026Can Classical Semantic-Extractive Summarization Be Evaluated in Hindi? A Replication Study24 Sep 2026
- 2026ThaiTrees: Thai Syntactic Dependency Trees Across Domains23 Sep 2026
- 2026PANORAMA: Panoptic Grounded Captioning via Mask Proposal Selection16 Sep 2026
- 2026Modeling the Developmental Shift in Telicity Acquisition16 Sep 2026
- 2026Doc2FRC: Length-Consistent Document-Level Machine Translation via Fixed-Range Chunking11 Sep 2026
- 2026SalamandraTA at WMT 2026 Terminology Shared Task: Hard Examples Are Better Teachers9 Sep 2026
- 2026Correction as Annotation: Bootstrapping a Dependency Parser for Documentary Medieval Latin5 Sep 2026
- 2026DPH Parser: A Bottom-Up Grammar-Driven Parser for Joint Constituency and Dependency Analysis5 Sep 2026
- 2026A Layered Taxonomy for Chinese Learner Grammatical Error Annotation2 Sep 2026
12 newest of 679 All 679 (JSON)