Pcc-tuning: Breaking the Contrastive Learning Ceiling in Semantic Textual Similarity

• URL: http://arxiv.org/abs/2406.09790v2
• Date: Sun, 06 Oct 2024 12:41:47 GMT
• Title: Pcc-tuning: Breaking the Contrastive Learning Ceiling in Semantic Textual Similarity
• Abstract summary: Sentence representation methods have reached an average Spearman's correlation score of approximately 86 across seven STS benchmarks in SentEval. We propose Pcc-tuning, which employs Pearson's correlation coefficient as a loss function to refine model performance beyond contrastive learning. Experimental results demonstrate that Pcc-tuning can markedly surpass previous state-of-the-art strategies with only a minimal amount of fine-grained annotated samples.
• Score: 3.435381469869212
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Semantic Textual Similarity (STS) constitutes a critical research direction in computational linguistics and serves as a key indicator of the encoding capabilities of embedding models. Driven by advances in pre-trained language models and contrastive learning, leading sentence representation methods have reached an average Spearman's correlation score of approximately 86 across seven STS benchmarks in SentEval. However, further progress has become increasingly marginal, with no existing method attaining an average score higher than 86.5 on these tasks. This paper conducts an in-depth analysis of this phenomenon and concludes that the upper limit for Spearman's correlation scores under contrastive learning is 87.5. To transcend this ceiling, we propose an innovative approach termed Pcc-tuning, which employs Pearson's correlation coefficient as a loss function to refine model performance beyond contrastive learning. Experimental results demonstrate that Pcc-tuning can markedly surpass previous state-of-the-art strategies with only a minimal amount of fine-grained annotated samples.

Related papers

• Rethinking Entropy Minimization in Test-Time Adaptation for Autoregressive Models [52.18157855348584]
  Test-Time Adaptation (TTA) via entropy minimization (EM) has proven effective for classification tasks, yet its application remains theoretically fragmented.<n>In this work, we deriving a rigorous formulation of EM tailored to autoregressive models.<n>We show that the exact objective naturally decomposes into a token-level policy gradient loss and a token-level entropy loss, and we reinterpret prior methods as partial realizations of this unified formulation.<n>Using Whisper ASR as a testbed, we demonstrate that our approach consistently improves performance across more than 20 diverse domains, including acoustic noise, accents, and multilingual settings.
  arXiv  Detail & Related papers  (2026-05-05T12:00:06Z)
• AI Generated Text Detection [0.0]
  This paper presents an evaluation of AI text detection methods, including both traditional machine learning models and transformer-based architectures.<n>We utilize two datasets, HC3 and DAIGT v2, to build a unified benchmark and apply a topic-based data split to prevent information leakage.<n>Results indicate that contextual modeling is significantly superior to lexical features and highlight the importance of mitigating topic memorization.
  arXiv  Detail & Related papers  (2026-01-07T11:18:10Z)
• SASWISE-UE: Segmentation and Synthesis with Interpretable Scalable Ensembles for Uncertainty Estimation [6.082812294410541]
  This paper introduces an efficient sub-model ensemble framework aimed at enhancing the interpretability of medical deep learning models. By generating uncertainty maps, this framework enables end-users to evaluate the reliability of model outputs.
  arXiv  Detail & Related papers  (2024-11-08T04:37:55Z)
• Advancing Semantic Textual Similarity Modeling: A Regression Framework with Translated ReLU and Smooth K2 Loss [3.435381469869212]
  This paper presents an innovative regression framework for Sentence-BERT STS tasks. It proposes two simple yet effective loss functions: Translated ReLU and Smooth K2 Loss. Experimental results demonstrate that our method achieves convincing performance across seven established STS benchmarks.
  arXiv  Detail & Related papers  (2024-06-08T02:52:43Z)
• Can Perplexity Predict Fine-tuning Performance? An Investigation of Tokenization Effects on Sequential Language Models for Nepali [0.0]
  SentencePiece tokenization consistently yields superior results on understanding-based tasks for Nepali.<n>Our research specifically examines sequential transformer models, providing valuable insights for language model development in low-resource languages.
  arXiv  Detail & Related papers  (2024-04-28T05:26:12Z)
• A Probabilistic Approach for Alignment with Human Comparisons [7.6656660956453635]
  This paper studies the effective use of human comparisons to address limitations arising from noisy data and high-dimensional models. We propose a two-stage "Supervised Fine Tuning+Human Comparison" (SFT+HC) framework connecting machine learning with human feedback.
  arXiv  Detail & Related papers  (2024-03-16T02:19:21Z)
• The Languini Kitchen: Enabling Language Modelling Research at Different Scales of Compute [66.84421705029624]
  We introduce an experimental protocol that enables model comparisons based on equivalent compute, measured in accelerator hours. We pre-process an existing large, diverse, and high-quality dataset of books that surpasses existing academic benchmarks in quality, diversity, and document length. This work also provides two baseline models: a feed-forward model derived from the GPT-2 architecture and a recurrent model in the form of a novel LSTM with ten-fold throughput.
  arXiv  Detail & Related papers  (2023-09-20T10:31:17Z)
• ProBoost: a Boosting Method for Probabilistic Classifiers [55.970609838687864]
  ProBoost is a new boosting algorithm for probabilistic classifiers. It uses the uncertainty of each training sample to determine the most challenging/uncertain ones. It produces a sequence that progressively focuses on the samples found to have the highest uncertainty.
  arXiv  Detail & Related papers  (2022-09-04T12:49:20Z)
• The Concordance Index decomposition: A measure for a deeper understanding of survival prediction models [3.186455928607442]
  The Concordance Index (C-index) is a commonly used metric in Survival Analysis for evaluating the performance of a prediction model. We propose a decomposition of the C-index into a weighted harmonic mean of two quantities: one for ranking observed events versus other observed events, and the other for ranking observed events versus censored cases.
  arXiv  Detail & Related papers  (2022-02-28T23:50:47Z)
• Revisiting Consistency Regularization for Semi-Supervised Learning [80.28461584135967]
  We propose an improved consistency regularization framework by a simple yet effective technique, FeatDistLoss. Experimental results show that our model defines a new state of the art for various datasets and settings.
  arXiv  Detail & Related papers  (2021-12-10T20:46:13Z)
• NoiER: An Approach for Training more Reliable Fine-TunedDownstream Task Models [54.184609286094044]
  We propose noise entropy regularisation (NoiER) as an efficient learning paradigm that solves the problem without auxiliary models and additional data. The proposed approach improved traditional OOD detection evaluation metrics by 55% on average compared to the original fine-tuned models.
  arXiv  Detail & Related papers  (2021-08-29T06:58:28Z)
• A comprehensive comparative evaluation and analysis of Distributional Semantic Models [61.41800660636555]
  We perform a comprehensive evaluation of type distributional vectors, either produced by static DSMs or obtained by averaging the contextualized vectors generated by BERT. The results show that the alleged superiority of predict based models is more apparent than real, and surely not ubiquitous. We borrow from cognitive neuroscience the methodology of Representational Similarity Analysis (RSA) to inspect the semantic spaces generated by distributional models.
  arXiv  Detail & Related papers  (2021-05-20T15:18:06Z)
• An Improved Baseline for Sentence-level Relation Extraction [17.50856935207308]
  Sentence-level relation extraction (RE) aims at identifying the relationship between two entities in a sentence. In this paper, we revisit two aspects of RE models that are not thoroughly studied, namely entity representation and NA instance prediction.
  arXiv  Detail & Related papers  (2021-02-02T07:57:06Z)
• BERT Loses Patience: Fast and Robust Inference with Early Exit [91.26199404912019]
  We propose Patience-based Early Exit as a plug-and-play technique to improve the efficiency and robustness of a pretrained language model. Our approach improves inference efficiency as it allows the model to make a prediction with fewer layers.
  arXiv  Detail & Related papers  (2020-06-07T13:38:32Z)

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.