相关论文: UNSEE: Unsupervised Non-contrastive Sentence Embed…

Semantic representation learning for sentences is an important and well-studied problem in NLP. The current trend for this task involves training a Transformer-based sentence encoder through a contrastive objective with text, i.e.,…

We propose Medical Entity Definition-based Sentence Embedding (MED-SE), a novel unsupervised contrastive learning framework designed for clinical texts, which exploits the definitions of medical entities. To this end, we conduct an…

We explore semantic correspondence estimation through the lens of unsupervised learning. We thoroughly evaluate several recently proposed unsupervised methods across multiple challenging datasets using a standardized evaluation protocol…

Contrastive learning has been studied for improving the performance of learning sentence embeddings. The current state-of-the-art method is the SimCSE, which takes dropout as the data augmentation method and feeds a pre-trained transformer…

We present EASE, a novel method for learning sentence embeddings via contrastive learning between sentences and their related entities. The advantage of using entity supervision is twofold: (1) entities have been shown to be a strong…

This paper improves contrastive learning for sentence embeddings from two perspectives: handling dropout noise and addressing feature corruption. Specifically, for the first perspective, we identify that the dropout noise from negative…

We propose Unified Visual-Semantic Embeddings (UniVSE) for learning a joint space of visual and textual concepts. The space unifies the concepts at different levels, including objects, attributes, relations, and full scenes. A contrastive…

Taking inspiration from Set Theory, we introduce SetCSE, an innovative information retrieval framework. SetCSE employs sets to represent complex semantics and incorporates well-defined operations for structured information querying under…

The lack of labeled data is a major obstacle to learning high-quality sentence embeddings. Recently, self-supervised contrastive learning (SCL) is regarded as a promising way to address this problem. However, the existing works mainly rely…

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…

Contrastive learning has been demonstrated to be effective in enhancing pre-trained language models (PLMs) to derive superior universal sentence embeddings. However, existing contrastive methods still have two limitations. Firstly, previous…

This paper presents miCSE, a mutual information-based contrastive learning framework that significantly advances the state-of-the-art in few-shot sentence embedding. The proposed approach imposes alignment between the attention pattern of…

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…

We propose reCSE, a self supervised contrastive learning sentence representation framework based on feature reshaping. This framework is different from the current advanced models that use discrete data augmentation methods, but instead…

Recent progress in sentence embedding, which represents the meaning of a sentence as a point in a vector space, has achieved high performance on tasks such as a semantic textual similarity (STS) task. However, sentence representations as a…

Data augmentation techniques have been proven useful in many applications in NLP fields. Most augmentations are task-specific, and cannot be used as a general-purpose tool. In our work, we present AugCSE, a unified framework to utilize…

Learning high quality sentence embeddings from dialogues has drawn increasing attentions as it is essential to solve a variety of dialogue-oriented tasks with low annotation cost. Annotating and gathering utterance relationships in…

We introduce SemCSE, an unsupervised method for learning semantic embeddings of scientific texts. Building on recent advances in contrastive learning for text embeddings, our approach leverages LLM-generated summaries of scientific…

Traditional comparative learning sentence embedding directly uses the encoder to extract sentence features, and then passes in the comparative loss function for learning. However, this method pays too much attention to the sentence body and…

Large-scale network embedding is to learn a latent representation for each node in an unsupervised manner, which captures inherent properties and structural information of the underlying graph. In this field, many popular approaches are…