SpanAlign: Efficient Sequence Tagging Annotation Projection into Translated Data applied to Cross-Lingual Opinion Mining
Following the increasing performance of neural machine translation systems, the paradigm of using automatically translated data for cross-lingual adaptation is now studied in several applicative domains. The capacity to accurately project annotations remains however an issue for sequence tagging tasks where annotation must be projected with correct spans. Additionally, when the task implies noisy user-generated text, the quality of translation and annotation projection can be affected. In this paper we propose to tackle multilingual sequence tagging with a new span alignment method and apply it to opinion target extraction from customer reviews. We show that provided suitable heuristics, translated data with automatic span-level annotation projection can yield improvements both for cross-lingual adaptation compared to zero-shot transfer, and data augmentation compared to a multilingual baseline.
Code (0)
등록된 구현이 없습니다.
Tasks
Data AugmentationMachine TranslationOpinion MiningTranslationSimilar Papers 제목 키워드 기반
Learning when to trust distant supervision: An application to low-resource POS tagging using cross-lingual projection
Cross lingual projection of linguistic annotation suffers from many sources of bias and noise, leading to unreliable annotations that cannot be used directly. In this paper, we introduce a novel approach to sequence tagg…
POSPOS TaggingCross-lingual Annotation Projection Is Effective for Neural Part-of-Speech Tagging
We tackle the important task of part-of-speech tagging using a neural model in the zero-resource scenario, where we have no access to gold-standard POS training data. We compare this scenario with the low-resource scenar…
Part-Of-Speech TaggingPOSPOS TaggingTranslation via Annotation: A Computational Study of Translating Classical Chinese into Japanese
Ancient people translated classical Chinese into Japanese using a system of annotations placed around characters. We abstract this process as sequence tagging tasks and fit them into modern language technologies. The res…
Machine TranslationMultilingual Projection for Parsing Truly Low-Resource Languages
We propose a novel approach to cross-lingual part-of-speech tagging and dependency parsing for truly low-resource languages. Our annotation projection-based approach yields tagging and parsing models for over 100 languag…
Cross-Lingual TransferDependency ParsingPart-Of-Speech TaggingTransfer LearningT-Projection: High Quality Annotation Projection for Sequence Labeling Tasks
In the absence of readily available labeled data for a given sequence labeling task and language, annotation projection has been proposed as one of the possible strategies to automatically generate annotated data. Annota…
Cross-Lingual NERMachine TranslationTranslationVocal Bursts Intensity Prediction