Recently, there has been growing interest in the ability of Transformer-based models to produce meaningful embeddings of text with several applications, such as text similarity. Despite significant progress in the field, the explanations for similarity predictions remain challenging, especially in unsupervised settings. In this work, we present an unsupervised technique for explaining paragraph similarities inferred by pre-trained BERT models. By looking at a pair of paragraphs, our technique identifies important words that dictate each paragraph's semantics, matches between the words in both paragraphs, and retrieves the most important pairs that explain the similarity between the two. The method, which has been assessed by extensive human evaluations and demonstrated on datasets comprising long and complex paragraphs, has shown great promise, providing accurate interpretations that correlate better with human perceptions.
翻译:最近,人们对以变异器为基础的模型能否产生有意义的文字嵌入,并采用多种应用,例如文本相似性,的兴趣日益浓厚。尽管在实地取得了显著进展,但对相似性预测的解释仍然具有挑战性,特别是在无人监督的环境中。在这项工作中,我们提出了一个解释预先培训的BERT模型所推断的段落相似性的不受监督的技术。通过查看一对段落,我们的技术找出了决定每个段落语义的重要词句,两个段落的词词句相匹配,并检索了解释两个段落相似性的最重要对子。这种方法通过广泛的人类评价进行评估,并在包含长段落和复杂段落的数据集上展示,显示了巨大的希望,提供了与人类感知更好的准确解释。