# Symmetric Regularization based BERT for Pair-wise Semantic Reasoning

arXiv: https://arxiv.org/abs/1909.03405 · HTML: https://mlsanity.com/paper/1909.03405/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Sep 2019.

## Built on by (most cited first, 4 of 4)

- [FrameBERT: Conceptual Metaphor Detection with Frame Embedding Learning](https://mlsanity.com/paper/2302.04834/) (2023)
- [Multimodal Dialog Systems with Dual Knowledge-enhanced Generative Pretrained Language Model](https://mlsanity.com/paper/2207.07934/) (2022)
- [Dual-View Distilled BERT for Sentence Embedding](https://mlsanity.com/paper/2104.08675/) (2021)
- [Training self-supervised peptide sequence models on artificially chopped proteins](https://mlsanity.com/paper/2211.06428/) (2022)

## Abstract (arXiv)

The ability of semantic reasoning over the sentence pair is essential for many natural language understanding tasks, e.g., natural language inference and machine reading comprehension. A recent significant improvement in these tasks comes from BERT. As reported, the next sentence prediction (NSP) in BERT, which learns the contextual relationship between two sentences, is of great significance for downstream problems with sentence-pair input. Despite the effectiveness of NSP, we suggest that NSP still lacks the essential signal to distinguish between entailment and shallow correlation. To remedy this, we propose to augment the NSP task to a 3-class categorization task, which includes a category for previous sentence prediction (PSP). The involvement of PSP encourages the model to focus on the informative semantics to determine the sentence order, thereby improves the ability of semantic understanding. This simple modification yields remarkable improvement against vanilla BERT. To further incorporate the document-level information, the scope of NSP and PSP is expanded into a broader range, i.e., NSP and PSP also include close but nonsuccessive sentences, the noise of which is mitigated by the label-smoothing technique. Both qualitative and quantitative experimental results demonstrate the effectiveness of the proposed method. Our method consistently improves the performance on the NLI and MRC benchmarks, including the challenging HANS dataset citehans, suggesting that the document-level task is still promising for the pre-training.