DELTA: Pre-train a Discriminative Encoder for Legal Case Retrieval via Structural Word Alignment

arXiv:2403.18435v1 Announce Type: cross
Abstract: Recent research demonstrates the effectiveness of using pre-trained language models for legal case retrieval. Most of the existing works focus on improving the representation ability for the contextualized embedding of the [CLS] token and calculate relevance using textual semantic similarity. However, in the legal domain, textual semantic similarity does not always imply that the cases are relevant enough. Instead, relevance in legal cases primarily depends on the similarity of key facts that impact the final …

abstract alignment arxiv case cs.cl cs.ir delta embedding encoder focus however improving language language models legal representation research retrieval semantic textual token train type via word