paper-with-me

홈 › Papers

Representing Sentences as Low-Rank Subspaces

2017-04-18 · ACL 2017 7 · Jiaqi Mu, Suma Bhat, Pramod Viswanath

Sentences are important semantic units of natural language. A generic, distributional representation of sentences that can capture the latent semantics is beneficial to multiple downstream applications. We observe a simple geometry of sentences -- the word representations of a given sentence (on average 10.23 words in all SemEval datasets with a standard deviation 4.84) roughly lie in a low-rank subspace (roughly, rank 4). Motivated by this observation, we represent a sentence by the low-rank subspace spanned by its word vectors. Such an unsupervised representation is empirically validated via semantic textual similarity tasks on 19 different datasets, where it outperforms the sophisticated neural network models, including skip-thought vectors, by 15% on average.

📄 PDF Abstract BibTeX arXiv:1704.05358

Code (0)

등록된 구현이 없습니다.

Tasks

Semantic Textual SimilaritySentence

Similar Papers 제목 키워드 기반

Sample, computation vs storage tradeoffs for classification using tensor subspace models

2017-06-18 · Mohammadhossein Chaghazardi, Shuchin Aeron

In this paper, we exhibit the tradeoffs between the (training) sample, computation and storage complexity for the problem of supervised classification using signal subspace estimation. Our main tool is the use of tensor …

General Classification

Bags of Affine Subspaces for Robust Object Tracking

2014-08-11 · Sareh Shirazi, Conrad Sanderson, Chris McCool, Mehrtash T. Harandi

We propose an adaptive tracking algorithm where the object is modelled as a continuously updated bag of affine subspaces, with each subspace constructed from the object's appearance over several consecutive frames. In co…

ObjectObject Tracking

Coherent Source Enumeration with Compact ULAs

2025-04-27 · Dibakar Sil, Sunder Ram Krishnan, Kumar Vijay Mishra

Source enumeration typically relies on subspace-based techniques that require accurate separation of signal and noise subspaces. However, prior works do not address coherent sources in small uniform linear arrays, where …

Low-Rank Subspaces in GANs

2021-06-08 · NeurIPS 2021 12 · Jiapeng Zhu, Ruili Feng, Yujun Shen, Deli Zhao 외

The latent space of a Generative Adversarial Network (GAN) has been shown to encode rich semantics within some subspaces. To identify these subspaces, researchers typically analyze the statistical information from a coll…

AttributeGenerative Adversarial Network

Learning Robust Subspace Clustering

2013-08-01 · Qiang Qiu, Guillermo Sapiro

We propose a low-rank transformation-learning framework to robustify subspace clustering. Many high-dimensional data, such as face images and motion sequences, lie in a union of low-dimensional subspaces. The subspace cl…

Clustering