Cross-Lingual Morphological Tagging for Low-Resource Languages

Morphologically rich languages often lack the annotated linguistic resources required to develop accurate natural language processing tools. We propose models suitable for training morphological taggers with rich tagsets for low-resource languages without using direct supervision. Our approach extends existing approaches of projecting part-of-speech tags across languages, using bitext to infer constraints on the possible tags for a given word type or token. We propose a tagging model using Wsabie, a discriminative embeddingbased model with rank-based learning. In our evaluation on 11 languages, on average this model performs on par with a baseline weakly-supervised HMM, while being more scalable. Multilingual experiments show that the method performs best when projecting between related language pairs. Despite the inherently lossy projection, we show that the morphological tags predicted by our models improve the downstream performance of a parser by +0.6 LAS on average.

• Publication year

  2016

• Venue

  Annual Meeting of the Association for Computational Linguistics

• Publication date

  2016-06-01

• Fields of study

  Linguistics, Computer Science

• Identifiers
  DOI 10.18653/v1/P16-1184arXiv 1606.04279
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Paradigm classification in supervised learning of morphology

  2015cited by this paper
• Universal Dependencies : A cross-linguistic typology

  2015cited by this paper
• Robust Morphological Tagging with Word Representations

  2015cited by this paper
• A Language-Independent Feature Schema for Inflectional Morphology

  2015cited by this paper
• Morpho-syntactic Lexicon Generation Using Graph-based Semi-supervised Learning

  2015cited by this paper
• A Universal Feature Schema for Rich Morphological Annotation and Fine-Grained Cross-Lingual Part-of-Speech Tagging

  2015cited by this paper
• What Can We Get From 1000 Tokens? A Case Study of Multilingual POS Tagging For Resource-Poor Languages

  2014cited by this paper
• Automatic speech recognition for under-resourced languages: A survey

  2014cited by this paper
• Cross-Lingual Part-of-Speech Tagging through Ambiguous Learning

  2014cited by this paper
• Universal Stanford dependencies: A cross-linguistic typology

  2014cited by this paper
• Distributed Representations of Words and Phrases and their Compositionality

  2013cited by this paper
• Cross-Lingual Discriminative Learning of Sequence Models with Posterior Regularization

  2013cited by this paper
• Token and Type Constraints for Cross-Lingual Part-of-Speech Tagging

  2013influential reference
• Supervised Learning of Complete Morphological Paradigms

  2013cited by this paper
• A Simple, Fast, and Effective Reparameterization of IBM Model 2

  2013cited by this paper
• Cross-lingual Word Clusters for Direct Transfer of Linguistic Structure

  2012influential reference
• Wiki-ly Supervised Part-of-Speech Tagging

  2012influential reference
• WSABIE: Scaling Up to Large Vocabulary Image Annotation

  2011influential reference
• Unsupervised Part-of-Speech Tagging with Bilingual Graph-Based Projections

  2011influential reference
• A Universal Part-of-Speech Tagset

  2011cited by this paper
• Transition-based Dependency Parsing with Rich Non-local Features

  2011cited by this paper
• Painless Unsupervised Learning with Features

  2010cited by this paper
• Statistical Parsing of Morphologically Rich Languages (SPMRL) What, How and Whither

  2010cited by this paper
• The CoNLL-2009 Shared Task: Syntactic and Semantic Dependencies in Multiple Languages

  2009cited by this paper
• Reusable Tagset Conversion Using Tagset Drivers

  2008cited by this paper
• Unsupervised Multilingual Learning for Morphological Segmentation

  2008cited by this paper
• Distributed Word Clustering for Large Scale Class-Based Language Modeling in Machine Translation

  2008cited by this paper
• Applying Morphology Generation Models to Machine Translation

  2008cited by this paper
• Unsupervised models for morpheme segmentation and morphology learning

  2007cited by this paper
• Automatically Inducing a Part-of-Speech Tagger by Projecting from Multiple Source Languages Across Aligned Corpora

  2005cited by this paper
• Europarl: A Parallel Corpus for Statistical Machine Translation

  2005cited by this paper
• Inducing Multilingual Text Analysis Tools via Robust Projection across Aligned Corpora

  2001cited by this paper
• Proceedings

  1947cited by this paper

• Computational Methods for Language Documentation and Description

  2026cites this paper
• Hybrid Neural-LLM Pipeline for Morphological Glossing in Endangered Language Documentation: A Case Study of Jungar Tuvan

  2026cites this paper
• A BERT-Based Approach for Part-of-Speech Tagging in the Low-Resource Context of Sardinian

  2025cites this paper
• A Systematic Comparison of Statistical and Neural Frameworks for Spanish POS Tagging

  2025cites this paper
• LIMBA: An Open-Source Framework for the Preservation and Valorization of Low-Resource Languages using Generative Models

  2024cites this paper
• NCC: Neural concept compression for multilingual document recommendation

  2023cites this paper
• Meeting the Needs of Low-Resource Languages: The Value of Automatic Alignments via Pretrained Models

  2023cites this paper
• Unsupervised Stem-based Cross-lingual Part-of-Speech Tagging for Morphologically Rich Low-Resource Languages

  2022cites this paper
• Towards Unsupervised Morphological Analysis of Polysynthetic Languages

  2022cites this paper
• Graph-Based Multilingual Label Propagation for Low-Resource Part-of-Speech Tagging

  2022influential citation
• Deciphering and Characterizing Out-of-Vocabulary Words for Morphologically Rich Languages

  2022cites this paper
• Morphological Processing of Low-Resource Languages: Where We Are and What’s Next

  2022cites this paper
• Optimal Size-Performance Tradeoffs: Weighing PoS Tagger Models

  2021cites this paper
• Unsupervised Morphological Segmentation and Part-of-Speech Tagging for Low-Resource Scenarios

  2021cites this paper
• Highly Efficient Parts of Speech Tagging in Low Resource Languages with Improved Hidden Markov Model and Deep Learning

  2021cites this paper
• Cross-Register Projection for Headline Part of Speech Tagging

  2021cites this paper
• Generalized Supervised Attention for Text Generation

  2021cites this paper
• Computational Morphology with Neural Network Approaches

  2021influential citation
• Cross-lingual learning for text processing: A survey

  2021cites this paper
• Low-resource Languages: A Review of Past Work and Future Challenges

  2020cites this paper
• Reconciling historical data and modern computational models in corpus creation

  2020cites this paper
• Morphological Disambiguation of South Sámi with FSTs and Neural Networks

  2020cites this paper
• Evaluating Neural Morphological Taggers for Sanskrit

  2020cites this paper
• Fine-grained Morphosyntactic Analysis and Generation Tools for More Than One Thousand Languages

  2020cites this paper
• KINNEWS and KIRNEWS: Benchmarking Cross-Lingual Text Classification for Kinyarwanda and Kirundi

  2020cites this paper
• Unsupervised Cross-Lingual Part-of-Speech Tagging for Truly Low-Resource Scenarios

  2020influential citation
• Lingual-Agnostic Meta-Learning for Low-Resource Part-of-Speech Tagging

  2020cites this paper
• Proceedings of the Society for Computation in Linguistics Proceedings of the Society for Computation in Linguistics

  2020cites this paper
• NeuMorph

  2019cites this paper
• Neural morphosyntactic tagging for Rusyn

  2019cites this paper
• Morphosyntactic Disambiguation in an Endangered Language Setting

  2019cites this paper
• Learning Morphosyntactic Analyzers from the Bible via Iterative Annotation Projection across 26 Languages

  2019cites this paper
• Adversarial Multitask Learning for Joint Multi-Feature and Multi-Dialect Morphological Modeling

  2019cites this paper
• Crosslingual Document Embedding as Reduced-Rank Ridge Regression

  2019cites this paper
• Towards Combining Multitask and Multilingual Learning

  2019cites this paper
• Neural sequence-to-sequence models for low-resource morphology

  2019cites this paper
• Initial Experiments In Cross-Lingual Morphological Analysis Using Morpheme Segmentation

  2019cites this paper
• CMU-01 at the SIGMORPHON 2019 Shared Task on Crosslinguality and Context in Morphology

  2019cites this paper
• Fast and Scalable Expansion of Natural Language Understanding Functionality for Intelligent Agents

  2018cites this paper
• Near or Far, Wide Range Zero-Shot Cross-Lingual Dependency Parsing

  2018cites this paper
• On Difficulties of Cross-Lingual Transfer with Order Differences: A Case Study on Dependency Parsing

  2018cites this paper
• Automatic Glossing in a Low-Resource Setting for Language Documentation

  2018cites this paper
• Neural Factor Graph Models for Cross-lingual Morphological Tagging

  2018cites this paper
• Cross-lingual Character-Level Neural Morphological Tagging

  2017cites this paper
• Model Transfer for Tagging Low-resource Languages using a Bilingual Dictionary

  2017cites this paper
• A Rich Morphological Tagger for English: Exploring the Cross-Linguistic Tradeoff Between Morphology and Syntax

  2017cites this paper
• One-Shot Neural Cross-Lingual Transfer for Paradigm Completion

  2017cites this paper
• Multi-source morphosyntactic tagging for spoken Rusyn

  2017cites this paper