Access the full text.
Sign up today, get DeepDyve free for 14 days.
C Dozier, R Kondadadi, M Light, A Vachher, S Veeramachaneni, R Wudali (2010)
Named entity recognition and resolution in legal text
K Greff, RK Srivastava, J Koutník, BR Steunebrink, J Schmidhuber (2017)
LSTM: A search space odysseyIEEE Trans Neural Netw Learn Syst, 28
XB Ngo, LM Nguyen, TO Tran, A Shimazu (2013)
A two-phase framework for learning logical structures of paragraphs in legal articlesACM Trans Asian Lang Inf Process (TALIP), 12
JL Elman (1990)
Finding structure in timeCognit Sci, 14
Y Bengio, P Simard, P Frasconi (1994)
Learning long-term dependencies with gradient descent is difficultIEEE Trans Neural Netw, 5
P Bojanowski, E Grave, A Joulin, T Mikolov (2017)
Enriching word vectors with subword informationTrans Assoc Comput Linguist, 5
N Srivastava, GE Hinton, A Krizhevsky, I Sutskever, R Salakhutdinov (2014)
Dropout: a simple way to prevent neural networks from overfittingJ Mach Learn Res, 15
S Hochreiter, J Schmidhuber (1997)
Long short-term memoryNeural Comput, 9
This paper proposes several recurrent neural network-based models for recognizing requisite and effectuation (RE) parts in Legal Texts. Firstly, we propose a modification of BiLSTM-CRF model that allows the use of external features to improve the performance of deep learning models in case large annotated corpora are not available. However, this model can only recognize RE parts which are not overlapped. Secondly, we propose two approaches for recognizing overlapping RE parts including the cascading approach which uses the sequence of BiLSTM-CRF models and the unified model approach with the multilayer BiLSTM-CRF model and the multilayer BiLSTM-MLP-CRF model. Experimental results on two Japan law RRE datasets demonstrated advantages of our proposed models. For the Japanese National Pension Law dataset, our approaches obtained an $$F_{1}$$ F 1 score of 93.27% and exhibited a significant improvement compared to previous approaches. For the Japan Civil Code RRE dataset which is written in English, our approaches produced an $$F_{1}$$ F 1 score of 78.24% in recognizing RE parts that exhibited a significant improvement over strong baselines. In addition, using external features and in-domain pre-trained word embeddings also improved the performance of RRE systems.
Artificial Intelligence and Law – Springer Journals
Published: Mar 24, 2018
Read and print from thousands of top scholarly journals.
Already have an account? Log in
Bookmark this article. You can see your Bookmarks on your DeepDyve Library.
To save an article, log in first, or sign up for a DeepDyve account if you don’t already have one.
Copy and paste the desired citation format or use the link below to download a file formatted for EndNote
Access the full text.
Sign up today, get DeepDyve free for 14 days.
All DeepDyve websites use cookies to improve your online experience. They were placed on your computer when you launched this website. You can change your cookie settings through your browser.