An Unsupervised Morpheme-Based HMM for Hebrew Morphological Disambiguation

Morphological disambiguation is the process of assigning one set of morphological features to each individual word in a text. When the word is ambiguous (there are several possible analyses for the word), a disambiguation procedure based on the word context must be applied. This paper deals with morphological disambiguation of the Hebrew language, which combines morphemes into a word in both agglutinative and fusional ways. We present an unsupervised stochastic model ‐ the only resource we use is a morphological analyzer ‐ which deals with the data sparseness problem caused by the axational morphology of the Hebrew language. We present a text encoding method for languages with axational morphology in which the knowledge of word formation rules (which are quite restricted in Hebrew) helps in the disambiguation. We adapt HMM algorithms for learning and searching this text representation, in such a way that segmentation and tagging can be learned in parallel in one step. Results on a large scale evaluation indicate that this learning improves disambiguation for complex tag sets. Our method is applicable to other languages with ax morphology.

• Publication year

  2006

• Venue

  Annual Meeting of the Association for Computational Linguistics

• Publication date

  2006-07-17

• Fields of study

  Linguistics, Computer Science

• Identifiers
  DOI 10.3115/1220175.1220259
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• POS Tagging of Dialectal Arabic: A Minimally Supervised Approach

  2005cited by this paper
• Choosing an Optimal Architecture for Segmentation and POS-Tagging of Modern Hebrew

  2005cited by this paper
• Arabic Tokenization, Part-of-Speech Tagging and Morphological Disambiguation in One Fell Swoop

  2005influential reference
• A Finite-State Morphological Grammar of Hebrew

  2005cited by this paper
• Automatic Tagging of Arabic Text: From Raw Text to Base Phrase Chunks

  2004cited by this paper
• A Second-Order Hidden Markov Model for Part-of-Speech Tagging

  1999cited by this paper
• Morphological Disambiguation for Hebrew Search Systems

  1999influential reference
• Building Probabilistic Models for Natural Language

  1996influential reference
• Transformation-Based Error-Driven Learning and Natural Language Processing: A Case Study in Part-of-Speech Tagging

  1995cited by this paper
• Learning Morpho-Lexical Probabilities from an Untagged Corpus with an Application to Hebrew

  1995influential reference
• Tagging English Text with a Probabilistic Model

  1994cited by this paper
• Does Baum-Welch Re-estimation Help Taggers?

  1994influential reference
• Speech and Language Processing

  1990influential reference
• On Latin

  1983cited by this paper
• An inequality and associated maximization technique in statistical estimation of probabilistic functions of a Markov process

  1972cited by this paper

• Are All Spanish Doctors Male? Evaluating Gender Bias in German Machine Translation

  2025cites this paper
• A Truly Joint Neural Architecture for Segmentation and Parsing

  2024cites this paper
• Do Pretrained Contextual Language Models Distinguish between Hebrew Homograph Analyses?

  2024cites this paper
• Masking Morphosyntactic Categories to Evaluate Salience for Schizophrenia Diagnosis

  2022cites this paper
• A Second Wave of UD Hebrew Treebanking and Cross-Domain Parsing

  2022cites this paper
• Neural Token Segmentation for High Token-Internal Complexity

  2022cites this paper
• Latest Developments in Morphological Disambiguation Strategies of Modern Hebrew

  2021cites this paper
• Modeling Repressive Policing: Computational Analysis of Protocols from the Israeli State Commission of Inquiry into the October 2000 Events

  2021cites this paper
• Neural Machine Translation without Embeddings

  2020cites this paper
• From SPMRL to NMRL: What Did We Learn (and Unlearn) in a Decade of Parsing Morphologically-Rich Languages (MRLs)?

  2020cites this paper
• Nakdan: Professional Hebrew Diacritizer

  2020cites this paper
• Automatic Construction of Aramaic-Hebrew Translation Lexicon

  2020cites this paper
• A Pointer Network Architecture for Joint Morphological Segmentation and Tagging

  2020influential citation
• A Novel Challenge Set for Hebrew Morphological Disambiguation and Diacritics Restoration

  2020cites this paper
• What’s Wrong with Hebrew NLP? And How to Make it Right

  2019cites this paper
• Historical corpora meet the digital humanities: the Jerusalem Corpus of Emergent Modern Hebrew

  2019cites this paper
• An Algorithmic Scheme for Statistical Thesaurus Construction in a Morphologically Rich Language

  2019cites this paper
• Evaluating Gender Bias in Machine Translation

  2019cites this paper
• Joint Transition-Based Models for Morpho-Syntactic Parsing: Parsing Strategies for MRLs and a Case Study from Modern Hebrew

  2019cites this paper
• A Characterwise Windowed Approach to Hebrew Morphological Segmentation

  2018cites this paper
• Automatic Opinion Extraction from Short Hebrew Texts using Machine Learning Techniques

  2018cites this paper
• Universal Morpho-Syntactic Parsing and the Contribution of Lexica: Analyzing the ONLP Lab Submission to the CoNLL 2018 Shared Task

  2018influential citation
• The Hebrew FrameNet Project

  2016cites this paper
• Data-Driven Morphological Analysis and Disambiguation for Morphologically Rich Languages and Universal Dependencies

  2016cites this paper
• An NLP Pipeline for Coptic

  2016influential citation
• Transition-Based Morphological Disambiguation

  2015cites this paper
• Morphological Disambiguation of Classical Sanskrit

  2015cites this paper
• Context-dependent type-level models for unsupervised morpho-syntactic induction

  2015cites this paper
• The diminishing role of inalienability in the Hebrew possessive dative

  2015cites this paper
• Parallels between cross-linguistic and language-internal variation in Hebrew possessive constructions

  2014cites this paper
• The Responsa Project: Some Promising Future Directions

  2014cites this paper
• Methodology for Connecting Nouns to Their Modifying Adjectives

  2014cites this paper
• The phonetics of intonation in learner varieties of French

  2014cites this paper
• Morphological Tagging of Ugaritic

  2014cites this paper
• Morphological Processing of Semitic Languages

  2014influential citation
• Linguistic category induction and tagging using the paradigmatic context representations with substitute words (Düşey kelime bağlamlarını olası kelimeler ile temsil ederek dil bilimsel sözcük kümeleri ve etikletlerinin bulunması)

  2014influential citation
• Syntax and Parsing of Semitic Languages

  2014cites this paper
• Statistical Machine Translation

  2014cites this paper
• Overview of the SPMRL 2013 Shared Task: A Cross-Framework Evaluation of Parsing Morphologically Rich Languages

  2013cites this paper
• Effect of Out Of Vocabulary Terms on Inferring Eligibility Criteria for a Retrospective Study in Hebrew EHR

  2013cites this paper
• A Unified Morpho-Syntactic Scheme of Stanford Dependencies

  2013cites this paper
• Word Segmentation, Unknown-word Resolution, and Morphological Agreement in a Hebrew Parsing System

  2013influential citation
• A rule-based approach to unknown word recognition in Arabic

  2012cites this paper
• Statistical Thesaurus Construction for a Morphologically Rich Language

  2012cites this paper
• Morphological disambiguation of Hebrew: a case study in classifier combination

  2012influential citation
• Joint Evaluation of Morphological Segmentation and Syntactic Parsing

  2012cites this paper
• Extraction of linguistic resources from multilingual corpora and their exploitation

  2012cites this paper
• Multilingual text generation from structured formal representations

  2012cites this paper
• Universal Morphological Analysis using Structured Nearest Neighbor Prediction

  2011cites this paper
• Part of speech tagging for Arabic

  2011cites this paper
• Modeling Syntactic Context Improves Morphological Segmentation

  2011cites this paper
• Updating of the "Contemporary Chinese Language Word Segmentation Specification for Information Processing"

  2011cites this paper
• Transliterated Pairs Acquisition in Medical Hebrew

  2010cites this paper
• A New Approach to Lexical Disambiguation of Arabic Text

  2010cites this paper
• Hierarchical Joint Learning: Improving Joint Parsing and Named Entity Recognition with Non-Jointly Labeled Data

  2010cites this paper
• Easy-First Dependency Parsing of Modern Hebrew

  2010cites this paper
• Unsupervised Concept Discovery In Hebrew Using Simple Unsupervised Word Prefix Segmentation for Hebrew and Arabic

  2009cites this paper
• Enhancing Unlexicalized Parsing Performance Using a Wide Coverage Lexicon, Fuzzy Tag-Set Mapping, and EM-HMM-Based Lexical Probabilities

  2009cites this paper
• Transformation-Based Error-Driven Learning

  2009cites this paper
• Hebrew possessive datives: corpus evidence for the role of affectedness

  2009cites this paper
• Unsupervised Morphological Disambiguation using Statistical Language Models

  2009cites this paper
• Language resources for Hebrew

  2008cites this paper
• The Fast and the Numerous - Combining Machine and Community Intelligence for Semantic Annotation

  2008cites this paper
• Using Wikipedia Links to Construct Word Segmentation Corpora

  2008cites this paper
• Tagging a Hebrew Corpus: the Case of Participles

  2008cites this paper
• Swordfish2: Using Kernel Density Estimation to Smooth N-gram Histograms for Morphological Analysis

  2008cites this paper
• Part-of-speech tagging of Modern Hebrew text

  2008cites this paper
• Word-Based or Morpheme-Based? Annotation Strategies for Modern Hebrew Clitics

  2008cites this paper
• A Single Generative Model for Joint Morphological Segmentation and Syntactic Parsing

  2008influential citation
• Unsupervised Multilingual Learning for Morphological Segmentation

  2008cites this paper
• Stat-XFER: A General Search-Based Syntax-Driven Framework for Machine Translation

  2008cites this paper
• Identification of Transliterated Foreign Words in Hebrew Script

  2008cites this paper
• Unsupervised Approaches to Sequence Tagging , Morphology Induction , and Lexical Resource Acquisition

  2008cites this paper
• Morphological Disambiguation of Hebrew: A Case Study in Classifier Combination

  2007influential citation
• Joint Morphological and Syntactic Disambiguation

  2007cites this paper
• Morphological Disambiguation of Hebrew

  2007cites this paper
• Explorer Joint Morphological and Syntactic Disambiguation

  2007cites this paper
• SVM Model Tampering and Anchored Learning: A Case Study in Hebrew NP Chunking

  2007cites this paper
• Noun Phrase Chunking in Hebrew: Influence of Lexical and Morphological Features

  2006cites this paper
• Rapid prototyping of a transfer-based Hebrew-to-English machine translation system

  2004cites this paper