Statute recommendation: Re-ranking statutes by modeling case-statute relation with interpretable hand-crafted features
نویسندگان
چکیده
In the continental law system, it is appropriate for judges to find relevant laws and consider rules defined in them when dealing with legal cases. Therefore, recommending quickly accurately based on case content crucial improving efficiency of processing. There have been researched works recommender systems various fields, but few lucubrates that recommend statutes To best our knowledge, there no research by modeling relationship between interpretable hand-crafted features. this paper, we define five novel types features calculating relevance a statute resorting all retrieved through collaborative filtering input case. Both pair-wise list-wise ranking models are trained these re-ranking list. Besides, also test combinations different learning algorithms popular pre-trained language models. Experimental results show adopting proposed achieves performance. It improves recommendation recall Top 1 almost 5% compared approach.
منابع مشابه
A Plea for a Statute
The well-known tendency of the lawyer engaged in the drafting of conveyances is to adhere as closely as possible to the beaten paths; to follow the forms handed down from the fathers; to view with suspicion and close scrutiny any departure therefrom, and to insert new clauses and covenants only when convinced that they are demanded by the necessities engendered by tonditions and enterprises unk...
متن کاملThe slayer statute and insanity.
It is common law that persons cannot benefit from their crimes. For this reason, most states have enacted slayer rules that prevent a killer from sharing in the victim's estate. However, terms in the slayer rules, such as willful and unlawful, can be difficult to apply, as illustrated by the situation in which a slayer is found not guilty by reason of insanity. The Washington Supreme Court has ...
متن کاملPerson re-identification with fusion of hand-crafted and deep pose-based body region features
Person re-identification (re-ID) aims to accurately retrieve a person from a large-scale database of images captured across multiple cameras. Existing works learn deep representations using a large training subset of unique persons. However, identifying unseen persons is critical for a good re-ID algorithm. Moreover, the misalignment between person crops to detection errors or pose variations l...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Information Sciences
سال: 2022
ISSN: ['0020-0255', '1872-6291']
DOI: https://doi.org/10.1016/j.ins.2022.06.042