Self-Adaptive Reconstruction with Contrastive Learning for Unsupervised Sentence Embeddings

• URL: http://arxiv.org/abs/2402.15153v1
• Date: Fri, 23 Feb 2024 07:28:31 GMT
• Title: Self-Adaptive Reconstruction with Contrastive Learning for Unsupervised Sentence Embeddings
• Authors: Junlong Liu, Xichen Shang, Huawen Feng, Junhao Zheng, Qianli Ma
• Abstract summary: Unsupervised sentence embeddings task aims to convert sentences to semantic vector representations. Due to the token bias in pretrained language models, the models can not capture the fine-grained semantics in sentences. We propose a novel Self-Adaptive Reconstruction Contrastive Sentence Embeddings framework.
• Score: 24.255946996327104
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Unsupervised sentence embeddings task aims to convert sentences to semantic vector representations. Most previous works directly use the sentence representations derived from pretrained language models. However, due to the token bias in pretrained language models, the models can not capture the fine-grained semantics in sentences, which leads to poor predictions. To address this issue, we propose a novel Self-Adaptive Reconstruction Contrastive Sentence Embeddings (SARCSE) framework, which reconstructs all tokens in sentences with an AutoEncoder to help the model to preserve more fine-grained semantics during tokens aggregating. In addition, we proposed a self-adaptive reconstruction loss to alleviate the token bias towards frequency. Experimental results show that SARCSE gains significant improvements compared with the strong baseline SimCSE on the 7 STS tasks.

Related papers

• Bipartite Graph Pre-training for Unsupervised Extractive Summarization with Graph Convolutional Auto-Encoders [24.13261636386226]
  We argue that utilizing pre-trained embeddings derived from a process specifically designed to optimize cohensive and distinctive sentence representations helps rank significant sentences. We propose a novel graph pre-training auto-encoder to obtain sentence embeddings by explicitly modelling intra-sentential distinctive features and inter-sentential cohesive features.
  arXiv  Detail & Related papers  (2023-10-29T12:27:18Z)
• Wiki-En-ASR-Adapt: Large-scale synthetic dataset for English ASR Customization [66.22007368434633]
  We present a first large-scale public synthetic dataset for contextual spellchecking customization of automatic speech recognition (ASR) The proposed approach allows creating millions of realistic examples of corrupted ASR hypotheses and simulate non-trivial biasing lists for the customization task. We report experiments with training an open-source customization model on the proposed dataset and show that the injection of hard negative biasing phrases decreases WER and the number of false alarms.
  arXiv  Detail & Related papers  (2023-09-29T14:18:59Z)
• Sentence Embedding Leaks More Information than You Expect: Generative Embedding Inversion Attack to Recover the Whole Sentence [37.63047048491312]
  We propose a generative embedding inversion attack (GEIA) that aims to reconstruct input sequences based only on their sentence embeddings. Given the black-box access to a language model, we treat sentence embeddings as initial tokens' representations and train or fine-tune a powerful decoder model to decode the whole sequences directly.
  arXiv  Detail & Related papers  (2023-05-04T17:31:41Z)
• Context-aware Fine-tuning of Self-supervised Speech Models [56.95389222319555]
  We study the use of context, i.e., surrounding segments, during fine-tuning. We propose a new approach called context-aware fine-tuning. We evaluate the proposed approach using the SLUE and Libri-light benchmarks for several downstream tasks.
  arXiv  Detail & Related papers  (2022-12-16T15:46:15Z)
• Sentence Representation Learning with Generative Objective rather than Contrastive Objective [86.01683892956144]
  We propose a novel generative self-supervised learning objective based on phrase reconstruction. Our generative learning achieves powerful enough performance improvement and outperforms the current state-of-the-art contrastive methods.
  arXiv  Detail & Related papers  (2022-10-16T07:47:46Z)
• A Sentence is Worth 128 Pseudo Tokens: A Semantic-Aware Contrastive Learning Framework for Sentence Embeddings [28.046786376565123]
  We propose a semantics-aware contrastive learning framework for sentence embeddings, termed Pseudo-Token BERT (PT-BERT) We exploit the pseudo-token space (i.e., latent semantic space) representation of a sentence while eliminating the impact of superficial features such as sentence length and syntax. Our model outperforms the state-of-the-art baselines on six standard semantic textual similarity (STS) tasks.
  arXiv  Detail & Related papers  (2022-03-11T12:29:22Z)
• SimCSE: Simple Contrastive Learning of Sentence Embeddings [10.33373737281907]
  This paper presents SimCSE, a contrastive learning framework for embeddings. We first describe an unsupervised approach, which takes an input sentence and predicts itself in a contrastive objective. We then incorporate annotated pairs from NLI datasets into contrastive learning by using "entailment" pairs as positives and "contradiction" pairs as hard negatives.
  arXiv  Detail & Related papers  (2021-04-18T11:27:08Z)
• COCO-LM: Correcting and Contrasting Text Sequences for Language Model Pretraining [59.169836983883656]
  COCO-LM is a new self-supervised learning framework that pretrains Language Models by COrrecting challenging errors and COntrasting text sequences. COCO-LM employs an auxiliary language model to mask-and-predict tokens in original text sequences. Our analyses reveal that COCO-LM's advantages come from its challenging training signals, more contextualized token representations, and regularized sequence representations.
  arXiv  Detail & Related papers  (2021-02-16T22:24:29Z)
• Autoencoding Variational Autoencoder [56.05008520271406]
  We study the implications of this behaviour on the learned representations and also the consequences of fixing it by introducing a notion of self consistency. We show that encoders trained with our self-consistency approach lead to representations that are robust (insensitive) to perturbations in the input introduced by adversarial attacks.
  arXiv  Detail & Related papers  (2020-12-07T14:16:14Z)
• Semi-Supervised Models via Data Augmentationfor Classifying Interactive Affective Responses [85.04362095899656]
  We present semi-supervised models with data augmentation (SMDA), a semi-supervised text classification system to classify interactive affective responses. For labeled sentences, we performed data augmentations to uniform the label distributions and computed supervised loss during training process. For unlabeled sentences, we explored self-training by regarding low-entropy predictions over unlabeled sentences as pseudo labels.
  arXiv  Detail & Related papers  (2020-04-23T05:02:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.