Parameter-free Sentence Embedding via Orthogonal Basis

TL;DR

This paper introduces a parameter-free method for sentence embedding using orthogonal basis construction inspired by Gram-Schmidt, achieving competitive results across multiple NLP tasks without training.

Contribution

The paper presents a novel, non-parameterized orthogonal basis approach for sentence representation, eliminating the need for training while maintaining high performance.

Findings

Outperforms other non-parameterized methods on NLP tasks

Competitive with large-data or trained models

Efficient inference with zero parameters

Abstract

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.