rufimelo commited on
Commit
9c98c1a
1 Parent(s): ece17ba

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +18 -3
README.md CHANGED
@@ -126,11 +126,26 @@ SentenceTransformer(
126
  If you use this work, please cite:
127
 
128
  ```bibtex
129
- @inproceedings{MeloSemantic,
130
- author = {Melo, Rui and Santos, Professor Pedro Alexandre and Dias, Professor Jo{\~ a}o},
131
- title = {A {Semantic} {Search} {System} for {Supremo} {Tribunal} de {Justi}{\c c}a},
 
 
 
 
 
 
 
 
 
 
 
 
 
 
132
  }
133
 
 
134
  @inproceedings{souza2020bertimbau,
135
  author = {F{\'a}bio Souza and
136
  Rodrigo Nogueira and
 
126
  If you use this work, please cite:
127
 
128
  ```bibtex
129
+ @InProceedings{MeloSemantic,
130
+ author="Melo, Rui
131
+ and Santos, Pedro A.
132
+ and Dias, Jo{\~a}o",
133
+ editor="Moniz, Nuno
134
+ and Vale, Zita
135
+ and Cascalho, Jos{\'e}
136
+ and Silva, Catarina
137
+ and Sebasti{\~a}o, Raquel",
138
+ title="A Semantic Search System for the Supremo Tribunal de Justi{\c{c}}a",
139
+ booktitle="Progress in Artificial Intelligence",
140
+ year="2023",
141
+ publisher="Springer Nature Switzerland",
142
+ address="Cham",
143
+ pages="142--154",
144
+ abstract="Many information retrieval systems use lexical approaches to retrieve information. Such approaches have multiple limitations, and these constraints are exacerbated when tied to specific domains, such as the legal one. Large language models, such as BERT, deeply understand a language and may overcome the limitations of older methodologies, such as BM25. This work investigated and developed a prototype of a Semantic Search System to assist the Supremo Tribunal de Justi{\c{c}}a (Portuguese Supreme Court of Justice) in its decision-making process. We built a Semantic Search System that uses specially trained BERT models (Legal-BERTimbau variants) and a Hybrid Search System that incorporates both lexical and semantic techniques by combining the capabilities of BM25 and the potential of Legal-BERTimbau. In this context, we obtained a {\$}{\$}335{\backslash}{\%}{\$}{\$}335{\%}increase on the discovery metric when compared to BM25 for the first query result. This work also provides information on the most relevant techniques for training a Large Language Model adapted to Portuguese jurisprudence and introduces a new technique of Metadata Knowledge Distillation.",
145
+ isbn="978-3-031-49011-8"
146
  }
147
 
148
+
149
  @inproceedings{souza2020bertimbau,
150
  author = {F{\'a}bio Souza and
151
  Rodrigo Nogueira and