Related papers: Sentence Representations via Gaussian Embedding

Current work in lexical distributed representations maps each word to a point vector in low-dimensional space. Mapping instead to a density provides many interesting advantages, including better capturing uncertainty about a representation…

Sentence embedding methods have made remarkable progress, yet they still struggle to capture the implicit semantics within sentences. This can be attributed to the inherent limitations of conventional sentence embedding methods that assign…

Compared with word embedding based on point representation, distribution-based word embedding shows more flexibility in expressing uncertainty and therefore embeds richer semantic information when representing words. The Wasserstein…

Learning semantically meaningful sentence embeddings is an open problem in natural language processing. In this work, we propose a sentence embedding learning approach that exploits both visual and textual information via a multimodal…

Generic sentence embeddings provide a coarse-grained approximation of semantic textual similarity but ignore specific aspects that make texts similar. Conversely, aspect-based sentence embeddings provide similarities between texts based on…

Dense vector representations for sentences made significant progress in recent years as can be seen on sentence similarity tasks. Real-world phrase retrieval applications, on the other hand, still encounter challenges for effective use of…

Contrastive learning has been extensively studied in sentence embedding learning, which assumes that the embeddings of different views of the same sentence are closer. The constraint brought by this assumption is weak, and a good sentence…

Recently, word representation has been increasingly focused on for its excellent properties in representing the word semantics. Previous works mainly suffer from the problem of polysemy phenomenon. To address this problem, most of previous…

We present an introductory investigation into continuous-space vector representations of sentences. We acquire pairs of very similar sentences differing only by a small alterations (such as change of a noun, adding an adjective, noun or…

We propose new static word embeddings optimised for sentence semantic representation. We first extract word embeddings from a pre-trained Sentence Transformer, and improve them with sentence-level principal component analysis, followed by…

Transformer models learn to encode and decode an input text, and produce contextual token embeddings as a side-effect. The mapping from language into the embedding space maps words expressing similar concepts onto points that are close in…

Traditional sentence embedding models encode sentences into vector representations to capture useful properties such as the semantic similarity between sentences. However, in addition to similarity, sentence semantics can also be…

Unsupervised sentence representation learning is one of the fundamental problems in natural language processing with various downstream applications. Recently, contrastive learning has been widely adopted which derives high-quality sentence…

A novel sentence embedding method built upon semantic subspace analysis, called semantic subspace sentence embedding (S3E), is proposed in this work. Given the fact that word embeddings can capture semantic relationship while semantically…

We present Relational Sentence Embedding (RSE), a new paradigm to further discover the potential of sentence embeddings. Prior work mainly models the similarity between sentences based on their embedding distance. Because of the complex…

Sentence embedding is a significant research topic in the field of natural language processing (NLP). Generating sentence embedding vectors reflecting the intrinsic meaning of a sentence is a key factor to achieve an enhanced performance in…

We present UNSEE: Unsupervised Non-Contrastive Sentence Embeddings, a novel approach that outperforms SimCSE in the Massive Text Embedding benchmark. Our exploration begins by addressing the challenge of representation collapse, a…

Learning sentence embeddings from dialogues has drawn increasing attention due to its low annotation cost and high domain adaptability. Conventional approaches employ the siamese-network for this task, which obtains the sentence embeddings…

While important properties of word vector representations have been studied extensively, far less is known about the properties of sentence vector representations. Word vectors are often evaluated by assessing to what degree they exhibit…

We present a novel approach to learn representations for sentence-level semantic similarity using conversational data. Our method trains an unsupervised model to predict conversational input-response pairs. The resulting sentence embeddings…