A Little Linguistics Goes a Long Way: Unsupervised Segmentation with Limited Language Specific Guidance
We present de-lexical segmentation, a linguistically motivated alternative to greedy or other unsupervised methods, requiring only minimal language specific input. Our technique involves creating a small grammar of closed-class affixes which can be written in a few hours. The grammar over generates analyses for word forms attested in a raw corpus which are disambiguated based on features of the linguistic base proposed for each form. Extending the grammar to cover orthographic, morpho-syntactic or lexical variation is simple, making it an ideal solution for challenging corpora with noisy, dialect-inconsistent, or otherwise non-standard content. In two evaluations, we consistently outperform competitive unsupervised baselines and approach the performance of state-of-the-art supervised models trained on large amounts of data, providing evidence for the value of linguistic input during preprocessing.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
A Little Confidence Goes a Long Way
We introduce a group of related methods for binary classification tasks using probes of the hidden state activations in large language models (LLMs). Performance is on par with the largest and most advanced LLMs currentl…
Binary ClassificationSynthetic vascular structure generation for unsupervised pre-training in CTA segmentation tasks
Large enough computed tomography (CT) data sets to train supervised deep models are often hard to come by. One contributing issue is the amount of manual labor that goes into creating ground truth labels, specially for v…
Computed Tomography (CT)SegmentationUnsupervised Pre-trainingUnsupervised object segmentation in video by efficient selection of highly probable positive features
We address an essential problem in computer vision, that of unsupervised object segmentation in video, where a main object of interest in a video sequence should be automatically separated from its background. An efficie…
ObjectSemantic SegmentationUnsupervised Object SegmentationU3DS$^3$: Unsupervised 3D Semantic Scene Segmentation
Contemporary point cloud segmentation approaches largely rely on richly annotated 3D training data. However, it is both time-consuming and challenging to obtain consistently accurate annotations for such 3D scene data. M…
Point Cloud SegmentationRepresentation LearningScene SegmentationSegmentationDSP: Dual Soft-Paste for Unsupervised Domain Adaptive Semantic Segmentation
Unsupervised domain adaptation (UDA) for semantic segmentation aims to adapt a segmentation model trained on the labeled source domain to the unlabeled target domain. Existing methods try to learn domain invariant featur…
Domain AdaptationSemantic SegmentationSynthetic-to-Real TranslationUnsupervised Domain Adaptation