Projects
We are interested in several broad areas where technologies are helping explore, support and advance understanding of legal reasoning, the delivery of legal services and access to justice and legal information.
These include, but are not limited to:
Natural Language Processing
Natural language processing (NLP) is a subfield of linguistics, computer science, and artificial intelligence concerned with the interactions between computers and human language. The goal is a computer capable of “understanding” the contents of documents, including the contextual nuances of the language within them.
Language Models
Language modelling (LM) is the use of various statistical and probabilistic techniques to determine the probability of a given sequence of words occurring in a sentence. We are interested in exploring the behaviour and performance of state-of-the-art models.
Language Benchmarks
With the increasing availability of textual data and improved model capabilities, Natural Language Processing (NLP) is gaining wider adoption in industry.
However, the field is mainly guided by research-motivated benchmarks which, due to their research-oriented nature, can fail to adequately measure real-world utility of NLP applications.
At Mishcon de Reya we envision that, in addition to existing benchmarks, more application-driven benchmarks can also help guide us towards improved Natural Language Understanding and inform the regulatory landscape.
To facilitate this, we have introduced the RAIN benchmark – a collection of NLP tasks and corresponding datasets with broad practical application.
Graph Databases
In computing, a graph database (GDB) is a database that uses graph structures for semantic queries with nodes, edges, and properties to represent and store data. A key concept of the system is the graph (or edge or relationship). The graph relates the data items in the store to a collection of nodes and edges, the edges representing the relationships between the nodes. They could store information related to anything from legal citations, to counter parties, to company structures.
Temporal graph analysis
Graph analytics is pivotal in understanding the modern world, especially for business and logistics planning. However, capturing and telling a story with data can be time-consuming and often requires the user to manually refresh the output for an update. As we collect more and more information it is increasingly useful to understand the order and timing of information so you can better understand its context.
Raphtory
Raphtory is an open source distributed real-time temporal graph analytics platform funded by The Alan Turing Institute. Raphtory is the answer to creating dynamic temporal graphs that could be used anywhere at any time. The goal is to make it easy for you to access accurate, time-sensitive graphs without the burden of reloading the results when you want the latest information. We are working with Raphtory on several projects and contributing code to this open source project.
Legal analytics
Analysing sources of legal data can help us understand better how a legal system has worked, is working, or might be made to work better.
Calls for Evidence
We use data science expertise to confirm and rebut assumptions about how the legal system works. Our responses to calls for evidence demonstrate that adopting a holistic approach to legal problems can provide a novel perspective with meaningful results. Mishcon’s wealth of legal experience and targeted use of data analytics allows us to shed a different light on assumed truths.
Law as a complex system
In recent years, a growing body of research understands the interaction of law and society as a complex adaptive system. There has been growth in social, political and economic complexity which has in turn manifested in legal complexity. In support of this view, we leverage techniques and tools from statistical physics, complexity and computational social science to both characterise and predict the behaviour of various parts of legal systems.
DLT, Blockchain and Smart contracts
The term DLT refers to a broad umbrella of technologies that seek to store, synchronise and maintain digital records across a network of computers. Each computer on the network updates the ledger as new data (i.e. transactions) arises, and propagate the updated ledger to the network. The first and most famous application of DLT remains the cryptoasset-based blockchain, Bitcoin.
On-chain conveyancing
The term “conveyance” refers to the legal process of transferring property from one owner to another. We have explored several different aspects of using DLT systems to conduct real estate transactions.
Smart regulatory instruments
The first DLT system to enable the deployment of blockchain-based smart contracts was the Ethereum blockchain. We are working on projects using DLT for auditing data flows and encoding system governance mechanisms.
Environmental, Sustainability and Governance
We are involved in several projects that are interested in measuring, auditing, tracking the environmental and sustainability properties of systems. DLT systems might be used to record carbon emissions and offsets and link them to real estate titles, providing an immutable and auditable history of a real estate asset’s carbon footprint. DLT would provide much needed transparency and trust to an area that has high incidences of inaccuracy, misreporting and fraud.
Accord Project
The Accord Project is an open ecosystem enabling you to build smart agreements and documents on a technology neutral platform. We are working with the Accord framework on several projects and contributing code to this open-source project.
