P2P

93 I L T A N E T . O R G Figure 3 above demonstrates the average recall curve for test cases utilizing the new algorithm (blue line) and how far it deviates from the results (green line). The lines are closely matched for most of the graph, indicating that the algorithm is highly accurate at predicting the number of documents required for review before that review even takes place. This shows that KIBIT technology is capable of significantly alleviating the headaches of litigation logistics planning for document review projects by enabling legal operations teams to accurately estimate the extent of their document review burden before it takes place. Automatic Sentence Highlighting The new algorithm not only improves the document ranking process but can also score individual words within those documents and automatically highlight high-value sentences. Figure 4 above shows an example. Sentences most relevant to a particular subject matter are highlighted in red, and those with moderate evidentiary value are highlighted in yellow. Word Weights and Keyword Suggestions To help with Early Case Assessment and Review phases of the EDRM model, FRONTEO is introducing several features in the immediate future that will help with identifying key concepts and words in document sets. Word weights show and visualize word distribution in the target data set, enabling attorneys to easily identify outlier words and concepts. Keyword Suggestion will enhance the searching process by enabling KIBIT to automatically suggest additional keywords relevant to a particular query or a particular content type. F I G U R E 4 . E X A M P L E O F A I - D R I V E N H I G H L I G H T I N G I N N E W A L G O R I T H M . F I G U R E 5 : O N E O F T H E F E AT U R E S T O B E R E L E A S E D I N T H E N E X T V E R S I O N O F K A M T H AT I S D E S I G N E D T O H E L P I D E N T I F Y K E Y W O R D S A N D R E V I E W D O C U M E N T S

• Cover