paper-with-me

홈 › Papers

A Little Linguistics Goes a Long Way: Unsupervised Segmentation with Limited Language Specific Guidance

2019-08-01 · WS 2019 8 · Alex Erdmann, er, Salam Khalifa, Mai Oudah, Nizar Habash, Houda Bouamor

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.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

A Little Confidence Goes a Long Way

2024-08-20 · John Scoville, Shang Gao, Devanshu Agrawal, Javed Qadrud-Din

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 Classification

Synthetic vascular structure generation for unsupervised pre-training in CTA segmentation tasks

2020-01-02 · Nil Stolt Ansó

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-training

Unsupervised object segmentation in video by efficient selection of highly probable positive features

2017-04-19 · ICCV 2017 10 · Emanuela Haller, Marius Leordeanu

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 Segmentation

U3DS$^3$: Unsupervised 3D Semantic Scene Segmentation

2023-11-10 · Jiaxu Liu, Zhengdi Yu, Toby P. Breckon, Hubert P. H. Shum

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 SegmentationSegmentation

DSP: Dual Soft-Paste for Unsupervised Domain Adaptive Semantic Segmentation

2021-07-20 · Li Gao, Jing Zhang, Lefei Zhang, DaCheng Tao

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