Data By the Bay

Overview of recent legal developments affecting Big Data, including the recent Federal Trade Commission Report on Big Data

For young law firms in particular, the challenge of finding and retaining new clients is won by responding to inbound calls and intakes more quickly than the competition. However, an effective lawyer cannot spend his/her entire day on mobile messaging.  Furthermore, the high cost and diversity of channels available for reaching the online audience continues to add complexity.

We present our system for systematically acquiring new clients, which focused on integrating data across the "full funnel" User Experience. Using precision-based advertising, and 24/7 mobile messaging APIs, we show how we bridge together the online and offline interactions, to create a near-frictionless and ethically sound connection between law firms and potential new clients.  We show how these techniques may be generalized to small and mid-sized businesses looking take advantage of data to fuel their growth.

The law has traditionally considered itself as “art not science”, but what value can be created by rethinking that art/science divide, and what would law as part science look like? Industries like sports, politics, and journalism provide recent and powerful comparisons, “moneyball” and Obama’s data-driven 2012 election campaign being the most famous examples of transformation. In the law, questions that can be answered with better data abound: how has a judge ruled on a defined type of case before? What is the likely outcome of filing a specific motion? How successful has a lawyer or firm been in representing certain kinds of cases, or before certain judges? This presentation will focus on the technology that Ravel Law uses to extract and classify such information, and on how it has built a business that harnesses the results.

Summarization remains one of the most conspicuously unsolved problems in NLP today. There is plenty of active research, and the best available is reasonably capable of capturing the information contained in a body of text, but the output is often clumsy compared to what might be written by a human. More importantly for those of us working in legal informatics, the law is a notoriously conservative profession. Lawyers will justifiably be more comfortable relying on summaries written by fellow members of the bar. Fortunately, judges provide high quality, detailed summarization of the cases they cite to in their opinions, and a rich body of this data exists throughout the body of historical case law. We present a technique for enriching the display of judicial opinions with high quality summary data extracted from subsequent opinions, using a variety of state of the art open-source software tools. FOSS tools used include Antlr, for recognition of deterministic sequences using formal grammars, and Apache UIMA for construction of multi-layered indexes of recognized entities, such that their various juxtapositions can be used for further inference.

Apache Spark powers Ravel’s case law dissecting backend. This talk will cover the motivation for migrating to Spark, the benefits, pain points and experiences running on a legal corpus. Over a year ago, Ravel Law’s batch processing moved from Apache Pig to Apache Spark. Spark eliminated many Pig and Hadoop related pain points and has enabled rapid development of our case law processing pipeline to include running many NER, clustering and machine learning models, building search indexes and constructing the legal citation graph with case law, statutes and judges as nodes. Spark helps accelerate Ravel Law’s processing, development and integration of machine learning systems. Learn how we use Spark to prep our data and some of the building blocks we use to create our legal research and analytics products.

While work in natural language processing in the legal domain has primarily focused on case law and e-discovery, the domain of contracts and agreements has received comparatively little attention. Our work focuses on the potential for errors and oversights in such documents, a common problem with consequences ranging from professional embarrassment to litigation in the worst case. The American Bar Association estimates that administrative and substantive errors account for some 75% of all legal malpractice claims; our own small-scale analysis suggests that some one in five civil cases involve disputes over ambiguous contract language. We present our work applying computational linguistics techniques to automatically detecting such errors, focusing particularly on inconsistencies, ambiguities and style issues.  Our evolving pipeline for contract analysis builds on augmenting corpora of contracts with manual annotations including judgments of ambiguity.

Big Data processing is dominating several business applications. Businesses are realizing the benefits of Big Data and analyzing large volumes of data to gain insights about their customers. This causes more data to be collected and stored centrally. Much of the storage occurs in the Cloud. This attracts hackers since they could gain access to large volumes of data about people. Accessing this type of data results in disastrous consequences to individuals whose privacy is violated. In this talk we will look at five of the major data breaches within the recent past and look at ways to protect people's privacy by considering several Best Practices approach. Many in the IT field have realized that it would be very difficult to secure all data that is accessible from the cloud and so better mechanisms should be developed to protect such public data.