mlsanityData to 7 Oct 2026

GAPX: Generalized Autoregressive Paraphrase-Identification X

arXiv 2210.01979 ↗First posted 5 Oct 2022cs.CL cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Paraphrase Identification is a fundamental task in Natural Language Processing. While much progress has been made in the field, the performance of many state-of-the-art models often suffer from distribution shift during inference time. We verify that a major source of this performance drop comes from biases introduced by negative examples. To overcome these biases, we propose in this paper to train two separate models, one that only utilizes the positive pairs and the other the negative pairs. This enables us the option of deciding how much to utilize the negative model, for which we introduce a perplexity based out-of-distribution metric that we show can effectively and automatically determine how much weight it should be given during inference. We support our findings with strong empirical results.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 45 of its 78 references that are in the map. First posted on arXiv 5 Oct 2022.

Builds on

45 of 78 references.

References · 45

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  4. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  5. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  6. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  7. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,462
  8. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  9. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  10. 2021Barlow Twins: Self-Supervised Learning via Redundancy Reductioncited by 1,818
  11. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
  12. 2020Energy-based Out-of-distribution Detectioncited by 1,296
33 more
  1. 2020BLEURT: Learning Robust Metrics for Text Generationcited by 1,196
  2. 2020COMET: A Neural Framework for MT Evaluationcited by 1,024
  3. 2017SemEval-2017 Task 1: Semantic Textual Similarity - Multilingual and Cross-lingual Focused Evaluationcited by 998
  4. 2018Deep Anomaly Detection with Outlier Exposurecited by 939
  5. 2021Generalized Out-of-Distribution Detection: A Surveycited by 796
  6. 2021BARTScore: Evaluating Generated Text as Text Generationcited by 719
  7. 2019Likelihood Ratios for Out-of-Distribution Detectioncited by 451
  8. 2019MoverScore: Text Generation Evaluating with Contextualized Embeddings and Earth Mover Distancecited by 415
  9. 2020Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Datacited by 408
  10. 2019PAWS: Paraphrase Adversaries from Word Scramblingcited by 395
  11. 2017Don't Just Assume; Look and Answer: Overcoming Priors for Visual Question Answeringcited by 337
  12. 2021Exploring the Limits of Out-of-Distribution Detectioncited by 283
  13. 2019Don't Take the Easy Way Out: Ensemble Based Methods for Avoiding Known Dataset Biasescited by 279
  14. 2019PAWS-X: A Cross-lingual Adversarial Dataset for Paraphrase Identificationcited by 262
  15. 2018Learning Confidence for Out-of-Distribution Detection in Neural Networkscited by 245
  16. 2020Classification-Based Anomaly Detection for General Datacited by 210
  17. 2019Learning De-biased Representations with Biased Representationscited by 199
  18. 2019RUBi: Reducing Unimodal Biases in Visual Question Answeringcited by 183
  19. 2018Latent Space Autoregression for Novelty Detectioncited by 149
  20. 2021Entailment as Few-Shot Learnercited by 122
  21. 2017Bilateral Multi-Perspective Matching for Natural Language Sentencescited by 120
  22. 2019Unlearn Dataset Bias in Natural Language Inference by Fitting the Residualcited by 119
  23. 2020Towards Debiasing NLU Models from Unknown Biasescited by 116
  24. 2020Automatic Machine Translation Evaluation in Many Languages via Zero-Shot Paraphrasingcited by 114
  25. 2016Deep Structured Energy Based Models for Anomaly Detectioncited by 113
  26. 2018Generative Probabilistic Novelty Detection with Adversarial Autoencoderscited by 99
  27. 2019Compositional Questions Do Not Necessitate Multi-hop Reasoningcited by 87
  28. 2021Contrastive Out-of-Distribution Detection for Pretrained Transformerscited by 70
  29. 2018Neural Network Models for Paraphrase Identification, Semantic Textual Similarity, Natural Language Inference, and Question Answeringcited by 23
  30. 2020FarsTail: A Persian Natural Language Inference Datasetcited by 23
  31. 2016Sentence Similarity Learning by Lexical Decomposition and Compositioncited by 16
  32. 2018Blindfold Baselines for Embodied QAcited by 13
  33. 2017Neural Paraphrase Identification of Questions with Noisy Pretrainingcited by 9

Built on by

Not cited yet.