Similar Philippine Supreme Court Case Decisions Retrieval System Using Doc2Vec

From Iskomunidad
Revision as of 20:40, 15 December 2019 by Lbranera (talk | contribs) (Created page with " '''Abstract''' Ranera, Lorenz Timothy Barco. (2019). Similar Philippine Supreme Court Case Decisions Retrieval System using Doc2Vec. Drafting a case decision is an intensiv...")
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)

Abstract

Ranera, Lorenz Timothy Barco. (2019). Similar Philippine Supreme Court Case Decisions Retrieval System using Doc2Vec.

Drafting a case decision is an intensive task for lower court judges which may be a factor in the case backlog problem of the Philippine judiciary. The search for similar Philippine Supreme Court case decisions is a common task done manually in the trial setting in order to support the decision of the judge. Doc2Vec, a common document embedding technique in NLP, and cosine similarity are implemented in order to determine semantically similar case decisions automatically. The model shows to have an accuracy of 76% and exhibits a moderate positive association with the similarity scores of a legal domain expert.

Keywords: Document Embedding, Document Retrieval, Document Similarity, Similarity score, Doc2Vec, Natural Language Processing, Philippine Supreme Court, Case decisions


View Manuscript