Cross-lingual Transfer of Named Entity Recognizers without Parallel Corpora
Published 1 January 2015Open access
Ayah Zirikly
Citations34
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
In addition to global de-lexicalized features, this work introduces multilingual gazetteers that are generated using graph propagation, and cross-lingual word representation mappings without the use of parallel data.
Abstract
Ayah Zirikly, Masato Hagiwara. Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 2: Short Papers). 2015.
Keywords
Computer Science
IEEE Transactions on Knowledge and Data EngineeringA Survey on Transfer Learning
23,164 Citations2009Sinno Jialin Pan, Qiang Yang
The relationship between transfer learning and other related machine learning techniques such as domain adaptation, multitask learning and sample selection bias, as well as covariate shift are discussed.
arXiv (Cornell University)Distributed Representations of Words and Phrases and their Compositionality
18,086 Citations2013Tomáš Mikolov, Ilya Sutskever +3 more
This paper presents a simple method for finding phrases in text, and shows that learning good vector representations for millions of phrases is possible and describes a simple alternative to the hierarchical softmax called negative sampling.
ScholarlyCommons (University of Pennsylvania)Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data
12,978 Citations2001John Lafferty, Andrew McCallum +1 more
This work presents iterative parameter estimation algorithms for conditional random fields and compares the performance of the resulting models to HMMs and MEMMs on synthetic and natural-language data.
The Stanford CoreNLP Natural Language Processing Toolkit
7,238 Citations2014Christopher D. Manning, Mihai Surdeanu +4 more
The design and use of the Stanford CoreNLP toolkit is described, an extensible pipeline that provides core natural language analysis, and it is suggested that this follows from a simple, approachable design, straightforward interfaces, the inclusion of robust and good quality analysis components, and not requiring use of a large amount of associated baggage.
Semi-supervised learning using Gaussian fields and harmonic functions
3,377 Citations2003Xiaojin Zhu, Zoubin Ghahramani +1 more
Class-based n -gram models of natural language
2,893 Citations1992Peter F. Brown, P.V. deSouza +3 more
This work addresses the problem of predicting a word from previous words in a sample of text and discusses n-gram models based on classes of words, finding that these models are able to extract classes that have the flavor of either syntactically based groupings or semanticallybased groupings, depending on the nature of the underlying statistics.
Word Representations: A Simple and General Method for Semi-Supervised Learning
1,944 Citations2010Joseph Turian, Lev-Arie Ratinov +1 more
This work evaluates Brown clusters, Collobert and Weston (2008) embeddings, and HLBL (Mnih & Hinton, 2009) embeds of words on both NER and chunking, and finds that each of the three word representations improves the accuracy of these baselines.
Artificial IntelligenceBabelNet: The automatic construction, evaluation and application of a wide-coverage multilingual semantic network
1,461 Citations2012Roberto Navigli, Simone Paolo Ponzetto
arXiv (Cornell University)A Universal Part-of-Speech Tagset
731 Citations2011Slav Petrov, Dipanjan Das +1 more
This work proposes a tagset that consists of twelve universal part-of-speech categories and develops a mapping from 25 different treebank tagsets to this universal set, which when combined with the original treebank data produces a dataset consisting of common parts- of-speech for 22 different languages.
Inducing multilingual text analysis tools via robust projection across aligned corpora
497 Citations2001David Yarowsky, Grace Ngai +1 more
Noise-robust tagger, bracketer and lemmatizer training procedures capable of accurate system bootstrapping from noisy and incomplete initial projections are presented, which significantly exceeds that obtained by direct annotation projection.
Smart innovation, systems and technologiesA Survey on Transfer Learning
365 Citations2020Santisudha Panigrahi, Anuja Nanda +1 more
Empirical Methods in Natural Language ProcessingMulti-Source Transfer of Delexicalized Dependency Parsers
314 Citations2011Ryan McDonald, Slav Petrov +1 more
This work demonstrates that delexicalized parsers can be directly transferred between languages, producing significantly higher accuracies than unsupervised parsers and shows that simple methods for introducing multiple source languages can significantly improve the overall quality of the resulting parsers.
Unsupervised Part-of-Speech Tagging with Bilingual Graph-Based Projections
247 Citations2011Dipanjan Das, Slav Petrov
A novel approach for inducing unsupervised part-of-speech taggers for languages that have no labeled training data, but have translated text in a resource-rich language, using graph-based label propagation for cross-lingual knowledge transfer.
Cross-lingual Word Clusters for Direct Transfer of Linguistic Structure
239 Citations2012Oscar Täckström, Ryan McDonald +1 more
It is shown that by augmenting direct-transfer systems with cross-lingual cluster features, the relative error of delexicalized dependency parsers, trained on English treebanks and transferred to foreign languages, can be reduced by up to 13%.
Cross-Language Parser Adaptation between Related Languages
160 Citations2008Daniel Zeman, Philip Resnik
An approach to adapting a parser to a new language using existing annotations in the source language achieves performance equivalent to that obtained by training on 1546 trees in the target language.
Target Language Adaptation of Discriminative Transfer Parsers
122 Citations2013Oscar Täckström, Ryan McDonald +1 more
This work shows how recent insights on selective parameter sharing can be applied to a discriminative parser by carefully decomposing its model features, and shows how the parser can be relexicalized and adapted using unlabeled target language data and a learning method that can incorporate diverse knowledge sources through ambiguous labelings.
Transactions of the Association for Computational LinguisticsCross-lingual Projected Expectation Regularization for Weakly Supervised Learning
81 Citations2014Mengqiu Wang, Christopher D. Manning
This work proposes a new method that projects model expectations rather than labels, which facilities transfer of model uncertainty across language boundaries, and encode expectations as constraints and train a discriminative CRF model using Generalized Expectation Criteria.
Syntactic Transfer Using a Bilingual Lexicon
57 Citations2012Greg Durrett, Adam Pauls +1 more
This work uses features to transfer the behavior of words at a type level to produce gains across a range of target languages, using two different low-resource training methodologies and two different dictionary sources.
Data-Driven Graph Construction for Semi-Supervised Graph-Based Learning in NLP
28 Citations2007Andrei T. Alexandrescu, Katrin Kirchhoff
This paper introduces a data-driven method that optimizes the representation of the initial feature space for graph construction by means of a supervised classier and demonstrates improvements over both label propagation and state-of-the-art supervised classiers.