Alignment by Agreement

We present an unsupervised approach to symmetric word alignment in which two simple asymmetric models are trained jointly to maximize a combination of data likelihood and agreement between the models. Compared to the standard practice of intersecting predictions of independently-trained models, joint training provides a 32% reduction in AER. Moreover, a simple and efficient pair of HMM aligners provides a 29% reduction in AER over symmetrized IBM model 4 predictions.

• Publication year

  2006

• Venue

  North American Chapter of the Association for Computational Linguistics

• Publication date

  2006-06-04

• Fields of study

  Computer Science

• Identifiers
  DOI 10.3115/1220835.1220849
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• A Maximum Entropy Word Aligner for Arabic-English Machine Translation

  2005cited by this paper
• A Discriminative Matching Approach to Word Alignment

  2005cited by this paper
• A Discriminative Framework for Bilingual Word Alignment

  2005cited by this paper
• Corpus-Based Induction of Syntactic Structure: Models of Dependency and Constituency

  2004cited by this paper
• Improving IBM Word Alignment Model 1

  2004cited by this paper
• Symmetric Word Alignments for Statistical Machine Translation

  2004cited by this paper
• Statistical Phrase-Based Translation

  2003influential reference
• A Systematic Comparison of Various Statistical Alignment Models

  2003influential reference
• Unsupervised Models for Named Entity Classification

  1999cited by this paper
• HMM-Based Word Alignment in Statistical Translation

  1996cited by this paper
• The Mathematics of Statistical Machine Translation: Parameter Estimation

  1993cited by this paper
• The Complexity of Computing the Permanent

  1979cited by this paper

• A novel fusion architecture for detecting Parkinson’s Disease using semi-supervised speech embeddings

  2025cites this paper
• A Novel Fusion Architecture for PD Detection Using Semi-Supervised Speech Embeddings

  2024cites this paper
• Efficiency-Effectiveness Tradeoff of Probabilistic Structured Queries for Cross-Language Information Retrieval

  2024cites this paper
• An Untold Story of Preprocessing Task Evaluation: An Alignment-based Joint Evaluation Approach

  2024cites this paper
• jp-evalb: Robust Alignment-based PARSEVAL Measures

  2024cites this paper
• Meeting the Needs of Low-Resource Languages: The Value of Automatic Alignments via Pretrained Models

  2023cites this paper
• Machine Translation for Historical Research: A Case Study of Aramaic-Ancient Hebrew Translations

  2023cites this paper
• Adopting Neural Translation Model in Data Generation for Inverse Text Normalization

  2023influential citation
• Multiple independent losses scheduling: A simple training method for deep neural networks

  2023cites this paper
• BLADE: Combining Vocabulary Pruning and Intermediate Pretraining for Scaleable Neural CLIR

  2023cites this paper
• Revamping Multilingual Agreement Bidirectionally via Switched Back-translation for Multilingual Neural Machine Translation

  2022cites this paper
• Neural Machine Translation tool from Spanish to English in the Medical Domain

  2022cites this paper
• Graph Neural Networks for Multiparallel Word Alignment

  2022cites this paper
• Word Alignment in the Era of Deep Learning: A Tutorial

  2022cites this paper
• Towards Multilingual Transitivity and Bidirectional Multilingual Agreement for Multilingual Document-level Machine Translation

  2022cites this paper
• Towards a Broad Coverage Named Entity Resource: A Data-Efficient Approach for Many Diverse Languages

  2022cites this paper
• Interpretese vs. Translationese: The Uniqueness of Human Strategies in Simultaneous Interpretation

  2022cites this paper
• Bridging Pre-trained Language Models and Hand-crafted Features for Unsupervised POS Tagging

  2022influential citation
• Weakly Supervised Face Naming with Symmetry-Enhanced Contrastive Loss

  2022cites this paper
• MirrorAlign: A Super Lightweight Unsupervised Word Alignment Model via Cross-Lingual Contrastive Learning

  2021influential citation
• Alignment Attention by Matching Key and Query Distributions

  2021cites this paper
• Multilingual Agreement for Multilingual Neural Machine Translation

  2021cites this paper
• Word Alignment by Fine-tuning Embeddings on Parallel Corpora

  2021cites this paper
• Leveraging Neural Machine Translation for Word Alignment

  2021cites this paper
• Improving Human Text Simplification with Sentence Fusion

  2021cites this paper
• On the diversity of multi-head attention

  2021cites this paper
• SLUA: A Super Lightweight Unsupervised Word Alignment Model via Cross-Lingual Contrastive Learning

  2021influential citation
• On Alignment of Textual Elements in a Parallel Diachronic Corpus

  2020cites this paper
• Improved Word Alignment System for Myanmar-English Machine Translation

  2020cites this paper
• Mask-Align: Self-Supervised Neural Word Alignment

  2020cites this paper
• Using Multilingual Resources to Evaluate CEFRLex for Learner Applications

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

  2020cites this paper
• Computational framework for fusing eye movements and spoken narratives for image annotation

  2020influential citation
• Neural Baselines for Word Alignment

  2020cites this paper
• Corpus Augmentation for Neural Machine Translation with English-Punjabi Parallel Corpora

  2020cites this paper
• End-to-End Neural Word Alignment Outperforms GIZA++

  2020cites this paper
• Mention Extraction and Linking for SQL Query Generation

  2020cites this paper
• Generative latent neural models for automatic word alignment

  2020influential citation
• State-of-the-Art Overview

  2019cites this paper
• Pointer-based Fusion of Bilingual Lexicons into Neural Machine Translation

  2019cites this paper
• Normalyzing Numeronyms - A NLP approach

  2019cites this paper
• Bridging the Gap: Improve Part-of-speech Tagging for Chinese Social Media Texts with Foreign Words

  2019cites this paper
• Joint Modeling for Bidirectional Neural Machine Translation with Contrastive Learning

  2019cites this paper
• Related Work

  2019cites this paper
• Annotation projection for temporal information extraction

  2019cites this paper
• Cross-Lingual Word Embeddings

  2019cites this paper
• Classification automatique des procédés de traduction (Automatic Classification of Translation Processes)

  2019cites this paper
• Towards Recognizing Phrase Translation Processes: Experiments on English-French

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

  2019cites this paper
• Tunisian arabic chat alphabet transliteration using probabilistic finite state transducers

  2019cites this paper
• Abstract Word segmentation using grouped semantic networks

  2019cites this paper
• Unsupervised word discovery for computational language documentation

  2019cites this paper
• An Automatic and a Machine-assisted Method to Clean Bilingual Corpus

  2019cites this paper
• Fusing Dialogue and Gaze From Discussions of 2D and 3D Scenes

  2019cites this paper
• Consistency by Agreement in Zero-Shot Neural Machine Translation

  2019cites this paper
• Improving Bidirectional Decoding with Dynamic Target Semantics in Neural Machine Translation

  2019cites this paper
• Modeling bilingual word associations as connected monolingual networks

  2018cites this paper
• Augmenting Statistical Machine Translation with Subword Translation of Out-of-Vocabulary Words

  2018cites this paper
• An Easily Extensible HMM Word Aligner

  2018cites this paper
• Modernization of old turkish texts

  2018cites this paper
• Low-Resource Contextual Topic Identification on Speech

  2018cites this paper
• Automatic Speech Recognition and Topic Identification for Almost-Zero-Resource Languages

  2018cites this paper
• SNAG: Spoken Narratives and Gaze Dataset

  2018cites this paper
• Using Tectogrammatical Annotation for Studying Actors and Actions in Sallust’s Bellum Catilinae

  2018cites this paper
• Multimodal Alignment for Affective Content

  2018cites this paper
• Statistical Machine Translation of English Text to API Code Usages :

  2018influential citation
• Identifying Semantic Divergences in Parallel Text without Annotations

  2018cites this paper
• A Hybrid Machine Translation Framework for an Improved Translation Workflow

  2018influential citation
• NLP Corpus Observatory – Looking for Constellations in Parallel Corpora to Improve Learners’ Collocational Skills

  2018cites this paper
• Hierarchical Learning of Cross-Language Mappings Through Distributed Vector Representations for Code

  2018influential citation
• Lemma Disambiguation in Multilingual Parallel Corpora

  2018cites this paper
• Building Named Entity Recognition Taggers via Parallel Corpora

  2018cites this paper
• Using Word Vectors to Improve Word Alignments for Low Resource Machine Translation

  2018cites this paper
• The JHU Speech LOREHLT 2017 System: Cross-Language Transfer for Situation-Frame Detection

  2018cites this paper
• Preference learning for machine translation

  2018cites this paper
• Unsupervised Token-wise Alignment to Improve Interpretation of Encoder-Decoder Models

  2018cites this paper
• Machine Translation: A Literature Review

  2018cites this paper
• Multi-Head Attention with Disagreement Regularization

  2018cites this paper
• How to Do Things with Translations Cross-Lingual Phrase Embeddings for Translation Analysis

  2018cites this paper
• Creating a Translation Matrix of the Bible’s Names Across 591 Languages

  2018cites this paper
• Crowdsourcing Text Simplification with Sentence Fusion

  2018cites this paper
• Semantic Role Labeling for Learner Chinese: the Importance of Syntactic Parsing and L2-L1 Parallel Data

  2018cites this paper
• Predicting mild cognitive impairment from spontaneous spoken utterances

  2017cites this paper
• Universal Dependency Parser : A Single Parser for Many Languages on Arc-Swift

  2017cites this paper
• Visual-Linguistic Semantic Alignment: Fusing Human Gaze and Spoken Narratives for Image Region Annotation

  2017cites this paper
• Integrated Speech and Language Technology for Intelligence, Surveillance, and Reconnaissance (ISR)

  2017cites this paper
• The mat sat on the cat: investigating structure in the evaluation of order in machine translation

  2017cites this paper
• Hierarchical Sub-sentential Alignment with IBM Models for Statistical Phrase-based Machine Translation

  2017influential citation
• Induction of latent domains in heterogeneous corpora: a case study of word alignment

  2017cites this paper
• Multilingwis² – Explore Your Parallel Corpus

  2017cites this paper
• Using Co-Captured Face, Gaze, and Verbal Reactions to Images of Varying Emotional Content for Analysis and Semantic Alignment

  2017cites this paper
• Fast BTG-Forest-Based Hierarchical Sub-sentential Alignment

  2017cites this paper
• Semantic Typology and Parallel Corpora: Something about Indefinite Pronouns

  2017cites this paper
• Crossing the border twice: Reimporting prepositions to alleviate L1-specific transfer errors

  2017influential citation
• Similarités Textuelles Sémantiques Translingues : vers la Détection Automatique du Plagiat par Traduction. (Cross Lingual Semantic Textual Similarity Detection : towards Cross-Language Plagiarism Detection)

  2017cites this paper
• Getting the Most out of AMR Parsing

  2017cites this paper
• Neural Automatic Post-Editing Using Prior Alignment and Reranking

  2017influential citation
• Exploring Properties of Intralingual and Interlingual Association Measures Visually

  2017influential citation
• Incident-Driven Machine Translation and Name Tagging for Low-resource Languages

  2017cites this paper
• Automatic creation of a word aligned Sinhala-Tamil parallel corpus

  2017influential citation