paper-with-me

홈 › Papers

Parameter-free Sentence Embedding via Orthogonal Basis

2018-09-30 · IJCNLP 2019 11 · Ziyi Yang, Chenguang Zhu, Weizhu Chen

We propose a simple and robust non-parameterized approach for building sentence representations. Inspired by the Gram-Schmidt Process in geometric theory, we build an orthogonal basis of the subspace spanned by a word and its surrounding context in a sentence. We model the semantic meaning of a word in a sentence based on two aspects. One is its relatedness to the word vector subspace already spanned by its contextual words. The other is the word's novel semantic meaning which shall be introduced as a new basis vector perpendicular to this existing subspace. Following this motivation, we develop an innovative method based on orthogonal basis to combine pre-trained word embeddings into sentence representations. This approach requires zero parameters, along with efficient inference performance. We evaluate our approach on 11 downstream NLP tasks. Our model shows superior performance compared with non-parameterized alternatives and it is competitive to other approaches relying on either large amounts of labelled data or prolonged training time.

📄 PDF Abstract BibTeX arXiv:1810.00438

Code (1)

ziyi-yang/GEM 공식 구현

Tasks

SentenceSentence EmbeddingSentence-EmbeddingWord Embeddings

Similar Papers 제목 키워드 기반

Zero-training Sentence Embedding via Orthogonal Basis

2019-05-01 · ICLR 2019 5 · Ziyi Yang, Chenguang Zhu, Weizhu Chen

We propose a simple and robust training-free approach for building sentence representations. Inspired by the Gram-Schmidt Process in geometric theory, we build an orthogonal basis of the subspace spanned by a word and it…

SentenceSentence EmbeddingSentence-EmbeddingWord Embeddings

Basis-Oriented Low-rank Transfer for Few-Shot and Test-Time Adaptation

2025-12-02 · Junghwan Park, Woojin Cho, Junhyuk Heo, Darongsae Kwon 외 arxiv

Adapting large pre-trained models to unseen tasks under tight data and compute budgets remains challenging. Meta-learning approaches explicitly learn good initializations, but they require an additional meta-training pha…

parameter-efficient fine-tuningTest-time Adaptation

CORA: Per-Slice Coherent Orthogonal Rotation for SVD-based Low-Rank Adaptation

2026-06-30 · Pengcheng Wang, Ziran Liu, Wei Wang, Wei Jiang arxiv

Parameter-Efficient Fine-Tuning (PEFT) commonly adapts pretrained weights through low-rank updates, and recent methods further exploit the singular value decomposition (SVD) of the base weight for initialization or subsp…

parameter-efficient fine-tuningCode Generation

Linear Cross-Lingual Mapping of Sentence Embeddings

2023-05-23 · Oleg Vasilyev, Fumika Isono, John Bohannon

Semantics of a sentence is defined with much less ambiguity than semantics of a single word, and we assume that it should be better preserved by translation to another language. If multilingual sentence embeddings intend…

SentenceSentence EmbeddingsTranslation

OPE-SR: Orthogonal Position Encoding for Designing a Parameter-free Upsampling Module in Arbitrary-scale Image Super-Resolution

2023-03-02 · CVPR 2023 1 · Gaochao Song, Luo Zhang, Ran Su, Jianfeng Shi 외

Implicit neural representation (INR) is a popular approach for arbitrary-scale image super-resolution (SR), as a key component of INR, position encoding improves its representation ability. Motivated by position encoding…

Image ReconstructionImage Super-ResolutionPositionSuper-Resolution