Sentence Representation Learning with Generative Objective rather than Contrastive Objective

• URL: http://arxiv.org/abs/2210.08474v1
• Date: Sun, 16 Oct 2022 07:47:46 GMT
• Title: Sentence Representation Learning with Generative Objective rather than Contrastive Objective
• Authors: Bohong Wu, Hai Zhao
• Abstract summary: 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.
• Score: 86.01683892956144
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Though offering amazing contextualized token-level representations, current pre-trained language models take less attention on accurately acquiring sentence-level representation during their self-supervised pre-training. However, contrastive objectives which dominate the current sentence representation learning bring little linguistic interpretability and no performance guarantee on downstream semantic tasks. We instead propose a novel generative self-supervised learning objective based on phrase reconstruction. To overcome the drawbacks of previous generative methods, we carefully model intra-sentence structure by breaking down one sentence into pieces of important phrases. Empirical studies show that our generative learning achieves powerful enough performance improvement and outperforms the current state-of-the-art contrastive methods not only on the STS benchmarks, but also on downstream semantic retrieval and reranking tasks. Our code is available at https://github.com/chengzhipanpan/PaSeR.

Related papers

• Manual Verbalizer Enrichment for Few-Shot Text Classification [1.860409237919611]
  acrshortmave is an approach for verbalizer construction by enrichment of class labels. Our model achieves state-of-the-art results while using significantly fewer resources.
  arXiv  Detail & Related papers  (2024-10-08T16:16:47Z)
• Pixel Sentence Representation Learning [67.4775296225521]
  In this work, we conceptualize the learning of sentence-level textual semantics as a visual representation learning process. We employ visually-grounded text perturbation methods like typos and word order shuffling, resonating with human cognitive patterns, and enabling perturbation to be perceived as continuous. Our approach is further bolstered by large-scale unsupervised topical alignment training and natural language inference supervision.
  arXiv  Detail & Related papers  (2024-02-13T02:46:45Z)
• DenoSent: A Denoising Objective for Self-Supervised Sentence Representation Learning [59.4644086610381]
  We propose a novel denoising objective that inherits from another perspective, i.e., the intra-sentence perspective. By introducing both discrete and continuous noise, we generate noisy sentences and then train our model to restore them to their original form. Our empirical evaluations demonstrate that this approach delivers competitive results on both semantic textual similarity (STS) and a wide range of transfer tasks.
  arXiv  Detail & Related papers  (2024-01-24T17:48:45Z)
• Alleviating Over-smoothing for Unsupervised Sentence Representation [96.19497378628594]
  We present a Simple method named Self-Contrastive Learning (SSCL) to alleviate this issue. Our proposed method is quite simple and can be easily extended to various state-of-the-art models for performance boosting.
  arXiv  Detail & Related papers  (2023-05-09T11:00:02Z)
• Generative or Contrastive? Phrase Reconstruction for Better Sentence Representation Learning [86.01683892956144]
  We propose a novel generative self-supervised learning objective based on phrase reconstruction. Our generative learning may yield powerful enough sentence representation and achieve performance in Sentence Textual Similarity tasks on par with contrastive learning.
  arXiv  Detail & Related papers  (2022-04-20T10:00:46Z)
• CLEAR: Contrastive Learning for Sentence Representation [41.867438597420346]
  We propose Contrastive LEArning for sentence Representation (CLEAR), which employs multiple sentence-level augmentation strategies. These augmentations include word and span deletion, reordering, and substitution. Our approach is shown to outperform multiple existing methods on both SentEval and GLUE benchmarks.
  arXiv  Detail & Related papers  (2020-12-31T06:40:13Z)
• SLM: Learning a Discourse Language Representation with Sentence Unshuffling [53.42814722621715]
  We introduce Sentence-level Language Modeling, a new pre-training objective for learning a discourse language representation. We show that this feature of our model improves the performance of the original BERT by large margins.
  arXiv  Detail & Related papers  (2020-10-30T13:33:41Z)

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.