Transformer-based pre-trained models have achieved great improvements in
semantic matching. However, existing models still suffer from insufficient
ability to capture subtle differences. The modification, addition and deletion
of words in sentence pairs may make it difficult for the model to predict their
relationship. To alleviate this problem, we propose a novel Dual Path Modeling
Framework to enhance the model's ability to perceive subtle differences in
sentence pairs by separately modeling affinity and difference semantics. Based
on dual-path modeling framework we design the Dual Path Modeling Network
(DPM-Net) to recognize semantic relations. And we conduct extensive experiments
on 10 well-studied semantic matching and robustness test datasets, and the
experimental results show that our proposed method achieves consistent
improvements over baselines.

提出一种基于双路径建模框架的 Transformer 模型，分别对语义关系的相似性和差异性进行建模，以增强模型感知句对中微妙差异的能力，实验结果表明，该模型与基线相比表现出更加一致的提升。

感知微妙冲突的双路径语义匹配建模

Dual Path Modeling for Semantic Matching by Perceiving Subtle Conflicts

This paper describes the LIAAD system that was ranked second place in the
Word-in-Context challenge (WiC) featured in SemDeep-5. Our solution is based on
a novel system for Word Sense Disambiguation (WSD) using contextual embeddings
and full-inventory sense embeddings. We adapt this WSD system, in a
straightforward manner, for the present task of detecting whether the same
sense occurs in a pair of sentences. Additionally, we show that our solution is
able to achieve competitive performance even without using the provided
training or development sets, mitigating potential concerns related to task
overfitting

本文描述了 LIAAD 系统，该系统在 SemDeep-5 中的 Word-in-Context 挑战赛中排名第二。我们的解决方案基于一种使用上下文嵌入和完整库存感知嵌入的新型词义消歧系统。此外，我们展示了我们的解决方案即使不使用提供的训练或开发集，也能够实现有竞争力的性能，从而缓解了与任务过度拟合相关的潜在问题。

LIAAD 在 SemDeep-5 挑战赛中：上下文中的单词（WiC）

LIAAD at SemDeep-5 Challenge: Word-in-Context (WiC)

Convolutional neural networks (CNNs) have recently emerged as a popular
building block for natural language processing (NLP). Despite their success,
most existing CNN models employed in NLP share the same learned (and static)
set of filters for all input sentences. In this paper, we consider an approach
of using a small meta network to learn context-sensitive convolutional filters
for text processing. The role of meta network is to abstract the contextual
information of a sentence or document into a set of input-aware filters. We
further generalize this framework to model sentence pairs, where a
bidirectional filter generation mechanism is introduced to encapsulate
co-dependent sentence representations. In our benchmarks on four different
tasks, including ontology classification, sentiment analysis, answer sentence
selection, and paraphrase identification, our proposed model, a modified CNN
with context-sensitive filters, consistently outperforms the standard CNN and
attention-based CNN baselines. By visualizing the learned context-sensitive
filters, we further validate and rationalize the effectiveness of proposed
framework.

本研究中提出一种使用小型元网络学习文本处理的上下文敏感卷积滤波器的方法，并将该框架进一步推广到模拟句子对，通过可视化学习的上下文敏感滤波器验证了所提出的框架的有效性。