A Neural Network Model for Low-Resource Universal Dependency Parsing

Accurate dependency parsing requires large treebanks, which are only available for a few languages. We propose a method that takes advantage of shared structure across languages to build a mature parser using less training data. We propose a model for learning a shared “universal” parser that operates over an interlingual continuous representation of language, along with language-specific mapping components. Compared with supervised learning, our methods give a consistent 8-10% improvement across several treebanks in low-resource simulations.

• Publication year

  2015

• Venue

  Conference on Empirical Methods in Natural Language Processing

• Publication date

  2015-09-01

• Fields of study

  Linguistics, Computer Science

• Identifiers
  DOI 10.18653/v1/D15-1040
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Low Resource Dependency Parsing: Cross-lingual Parameter Sharing in a Neural Network Parser

  2015influential reference
• Universal Dependencies 1.4

  2015cited by this paper
• Unsupervised Dependency Parsing with Transferring Distribution via Parallel Guidance and Entropy Regularization

  2014cited by this paper
• Accelerating t-SNE using tree-based algorithms

  2014cited by this paper
• Billions of Parallel Words for Free: Building and Using the EU Bookshop Corpus

  2014cited by this paper
• An Unsupervised Model for Instance Level Subcategorization Acquisition

  2014influential reference
• Online

  2014cited by this paper
• Dropout: a simple way to prevent neural networks from overfitting

  2014cited by this paper
• A Fast and Accurate Dependency Parser using Neural Networks

  2014cited by this paper
• PanLex: Building a Resource for Panlingual Lexical Translation

  2014influential reference
• Distributed Representations of Words and Phrases and their Compositionality

  2013influential reference
• Target Language Adaptation of Discriminative Transfer Parsers

  2013cited by this paper
• Efficient Estimation of Word Representations in Vector Space

  2013cited by this paper
• Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank

  2013cited by this paper
• Vine Pruning for Efficient Multi-Pass Dependency Parsing

  2012cited by this paper
• Syntactic Transfer Using a Bilingual Lexicon

  2012cited by this paper
• Cross-lingual Word Clusters for Direct Transfer of Linguistic Structure

  2012cited by this paper
• Natural Language Processing (Almost) from Scratch

  2011influential reference
• Adaptive Subgradient Methods for Online Learning and Stochastic Optimization

  2011cited by this paper
• RNNLM - Recurrent Neural Network Language Modeling Toolkit

  2011influential reference
• Text classification with the support of pruned dependency patterns

  2010cited by this paper
• Using a Dependency Parser to Improve SMT for Subject-Object-Verb Languages

  2009cited by this paper
• Cross-Language Parser Adaptation between Related Languages

  2008cited by this paper
• Does Korean have adjectives?*

  2006cited by this paper
• Inductive Dependency Parsing (Text, Speech and Language Technology)

  2006cited by this paper
• Inductive Dependency Parsing

  2006cited by this paper
• Europarl: A Parallel Corpus for Statistical Machine Translation

  2005cited by this paper
• A Shortest Path Dependency Kernel for Relation Extraction

  2005cited by this paper
• Question answering passage retrieval using dependency relations

  2005cited by this paper
• English Verb Classes and Alternations: A Preliminary Investigation

  1993cited by this paper

• Typology Guided Multilingual Position Representations: Case on Dependency Parsing

  2023cites this paper
• Building Dialogue Understanding Models for Low-resource Language Indonesian from Scratch

  2022cites this paper
• From text to talk: Harnessing conversational corpora for humane and diversity-aware language technology

  2022cites this paper
• Evaluating zero-shot transfers and multilingual models for dependency parsing and POS tagging within the low-resource language family Tupían

  2022cites this paper
• UDapter: Typology-based Language Adapters for Multilingual Dependency Parsing and Sequence Labeling

  2022cites this paper
• Discrete Opinion Tree Induction for Aspect-based Sentiment Analysis

  2022cites this paper
• Investigating Language Relationships in Multilingual Sentence Encoders Through the Lens of Linguistic Typology

  2022cites this paper
• Cross-lingual learning for text processing: A survey

  2021cites this paper
• Multi-level Chunk-based Constituent-to-Dependency Treebank Transformation for Tibetan Dependency Parsing

  2021cites this paper
• Towards Language Service Creation and Customization for Low-Resource Languages

  2020cites this paper
• A Survey of the Model Transfer Approaches to Cross-Lingual Dependency Parsing

  2020cites this paper
• UDapter: Language Adaptation for Truly Universal Dependency Parsing

  2020cites this paper
• Low-resource Languages: A Review of Past Work and Future Challenges

  2020cites this paper
• Leveraging Text-to-Scene Generation for Language Elicitation and Documentation

  2019cites this paper
• How to Parse Low-Resource Languages: Cross-Lingual Parsing, Target Language Annotation, or Both?

  2019cites this paper
• From Genesis to Creole Language

  2019cites this paper
• Joint detection of malicious domains and infected clients

  2019cites this paper
• Training parsers for low-resourced languages : improving cross-lingual transfer with monolingual knowledge. (Apprentissage d'analyseurs syntaxiques pour les langues peu dotées : amélioration du transfert cross-lingue grâce à des connaissances monolingues)

  2018cites this paper
• Modeling Language Variation and Universals: A Survey on Typological Linguistics for Natural Language Processing

  2018cites this paper
• Transfer learning for low-resource natural language analysis

  2017cites this paper
• Simulating Dependencies to Improve Parse Error Detection

  2017cites this paper
• Data Augmentation for Low-Resource Neural Machine Translation

  2017cites this paper
• UParse: the Edinburgh system for the CoNLL 2017 UD shared task

  2017cites this paper
• Universal Dependencies Parsing for Colloquial Singaporean English

  2017cites this paper
• Multilingual Semantic Parsing And Code-Switching

  2017cites this paper
• New treebank or repurposed? On the feasibility of cross-lingual parsing of Romance languages with Universal Dependencies†

  2017cites this paper
• On Multilingual Training of Neural Dependency Parsers

  2017cites this paper
• Lexicalized vs. Delexicalized Parsing in Low-Resource Scenarios

  2017cites this paper
• Evaluating Globally Normalized Transition Based Neural Networks for Multilingual Natural Language Understanding

  2017influential citation
• Leveraging Multilingual Training for Limited Resource Event Extraction

  2016cites this paper
• Aligning the foundations of hierarchical statistical machine translation

  2016cites this paper
• Parsing Myanmar ( Burmese ) by Using Japanese as a Pivot

  2016cites this paper
• Semantics-Driven Recognition of Collocations Using Word Embeddings

  2016cites this paper
• An NLP Pipeline for Coptic

  2016cites this paper
• Exploiting Multi-typed Treebanks for Parsing with Deep Multi-task Learning

  2016cites this paper
• A Universal Framework for Inductive Transfer Parsing across Multi-typed Treebanks

  2016influential citation
• Towards a Universal Analyzer of Natural Languages

  2016influential citation
• A Distributed Representation-Based Framework for Cross-Lingual Transfer Parsing

  2016cites this paper
• Many Languages, One Parser

  2016cites this paper
• Cross-Lingual Syntactic Transfer with Limited Resources

  2016cites this paper
• Incrementally Learning a Dependency Parser to Support Language Documentation in Field Linguistics

  2016cites this paper