Zero-training Sentence Embedding via Orthogonal Basis
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 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 its 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 representation. This approach requires zero training and zero parameters, along with efficient inference performance. We evaluate our approach on 11 downstream NLP tasks. Experimental results show that our model outperforms all existing zero-training alternatives in all the tasks and it is competitive to other approaches relying on either large amounts of labelled data or prolonged training time.
Code (1)
Tasks
SentenceSentence EmbeddingSentence-EmbeddingWord EmbeddingsSimilar Papers 제목 키워드 기반
Parameter-free Sentence Embedding via Orthogonal Basis
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 an…
SentenceSentence EmbeddingSentence-EmbeddingWord EmbeddingsTowards Continual Learning Desiderata via HSIC-Bottleneck Orthogonalization and Equiangular Embedding
Deep neural networks are susceptible to catastrophic forgetting when trained on sequential tasks. Various continual learning (CL) methods often rely on exemplar buffers or/and network expansion for balancing model stabil…
Continual LearningMitigating Semantic Leakage in Cross-lingual Embeddings via Orthogonality Constraint
Accurately aligning contextual representations in cross-lingual sentence embeddings is key for effective parallel data mining. A common strategy for achieving this alignment involves disentangling semantics and language …
DisentanglementRepresentation LearningSemantic Textual SimilaritySentence+1Inference-InfoGAN: Inference Independence via Embedding Orthogonal Basis Expansion
Disentanglement learning aims to construct independent and interpretable latent variables in which generative models are a popular strategy. InfoGAN is a classic method via maximizing Mutual Information (MI) to obtain in…
AttributeDisentanglementLinear Cross-Lingual Mapping of Sentence Embeddings
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