Understanding nuanced meaning in legal documents

Why is semantics important?

Semantics is described as the root meaning of text within any given document or speech. A complex document such as a contract will be open to misinterpretation where the meaning could be obfuscated within layers of overlapping clauses.

For any layperson attempting to appreciate a contract’s content fully, a specialist or lawyer will be essential to decipher meaning at every level. Once meaning has been identified, applying a viewpoint to that meaning can also be open to misinterpretation.

The role of semantics in the legal profession 

When presented with a legal contract, most of us will read and re-read each clause to understand the ‘meaning’ behind the text. Often described as ‘legalese’, contractual clauses can seem overly complex to the layman, consisting of overriding sentences that frame the clause and define boundaries within which the contractually obligated parties can operate.

Whenever a contract is created or amended, all relevant parties should evaluate the text – often at a granular level – to fully understand the document’s implications. This evaluation can take a lot of time and expense for lawyers or your legal specialists.

Although many firms will have qualified professionals supporting their people with analysis, comparison, and investigation services, they can often miss the ‘meaning’ behind a phrase. This meaning and how it relates to the client are at stake. Usually, only the client can interpret the true essence within a contractual term – but only if they have the facts (and meanings) clearly laid out in front of them, and this can take a considerable amount of time, cost and effort.

How automation has attempted to improve contract analysis

Since the early 1980s, firms have attempted to introduce automation to detect and understand the meanings within contract documents. These systems mainly use rules-based workflows alongside large libraries to identify and alert users to pre-defined issues within documents. These systems can be cumbersome and complex, demanding constant updates and manual intervention to guarantee any measure of success. Additionally, these systems often fail when multiple languages and regional variations in law are applied.

However, the need for a solution to the problem of document analysis and semantic recognition continues to grow.

The considerable volume of documents created in the legal domain demands more sophisticated tools supporting efficient and intelligent information gathering. Document research and management systems are now using strategies based on machine learning to classify, filter and extract context-based content. These systems help users identify relevant structured portions of legal text semi-automatically – such as contract clauses.

However, while knowledge management systems can deliver automated detection of matching text sections, they often fail to identify meaning – or the change of purpose.

From Machine Learning to AI – the solution to rapid semantic text analysis

The application of artificial intelligence (AI) to the problem of identifying and comparing semantic meaning has, at last, started to gain ground. Companies such as ThingsTHINKING from Karlsruhe have developed technologies over the previous 14 years that can already identify and compare semantic meanings within complex legal documentation.

The Semantha platform from ThingsTHINKING delivers fully automated semantic processing for legal, contractual, and complex documents. It can be applied to many use cases such as CV matching, NDA analysis, contract review, contract renewals, international contract translation and more.

The team at ThingsTHINKING describe their Semantha platform as ideal in situations where there is “too much text and not enough time”, – which sums up the situation most lawyers and legal teams find themselves in every day.

The Semantha interface allows users to upload multiple documents (such as contracts) to an interface for analysis. These documents can be in different formats (Word or PDF) and various languages. The user can then run a comparison or search against the records to find and identify matching sections of text that imply similar (or the same) meaning.

During a recent webinar by the Semantha team with automation integrations specialists UiPath, a search was conducted for the phrase “All genders have equal rights and obligations” across a selection of constitutions from countries such as Canada, India, China, Mexico, the USA and Europe. Semantha instantly identified clauses within each constitution that matched the same meaning – irrespective of language.

The Semantha platform can easily compare the matching phrases for similarity matches with adjustable thresholds. It makes these comparisons and identifies matches in semantic meaning despite different wording and terms in each document.

Perhaps just as importantly, the Semantha platform quickly identifies if a close match is not available between documents – helping users to discover if an expected intention in meaning is missing from within a document.

ThingsTHINKING is packaging the Semantha platform for firms to apply to their internal systems either as a stand-alone tool – or as an integration to other document management solutions using their extensive API. Semantha works ‘out of the box’ with learning required, thanks to the AI engine behind the solution.

Identifying meaning vs application of viewpoint

Although the Semantha platform can quickly identify the presence of an expected item of text with specific meaning, this is not enough for most organisations. We might already know that a phrase or clause is essential – and it is significant that the platform identifies the presence of this phrase – but what about a client’s specific viewpoint of that phrase? For example, a clause specified within a contract may stipulate a penalty. Our client might believe that this penalty is unacceptable – and we need the AI to help us identify and highlight the inclusion of this unacceptable condition. In this case, the user can tell Semantha via a simple interface that a particular phrase is ‘Bad’. In addition, the user can apply a ‘Good’ phrase – so anytime Semantha finds an item of text similar to the ‘Bad’ phrase, it will suggest or use the ‘Good’ alternative.

By applying your alternative phrases to a document, the Semantha platform will learn the user’s viewpoint and apply these learnings to any records available to the platform.

Semantic analysis automation in document management

Working with automation tools such as UiPath, users can integrate the Semantha platform to their document libraries such as SharePoint and any gateways where documents are arriving at the organisation (such as email). Semantha can automatically scan incoming documents looking for semantic meanings that it knows to highlight – triggering an alert and actions that the user can easily manage.

Users can decide on the level of integration they want within their document management workflows – and they can maintain human intervention where specialists need to evaluate semantic changes in contracts. As they become more confident in the accuracy of the Semantha platform, they can rely increasingly on automation and AI to deliver accurate results far more quickly.

Getting Semantha on board

For anyone dealing with many legal documents such as contract renewals, having a system like Semantha onboard could save the organisation many hundreds of hours in analysis. Although Semantha is easy to install and test within your environment, a demonstration is recommended to appreciate the platform’s advantages and features.

Channel Partnerships, working in partnership with Tech Data is here to help organisations evaluate the technology.

Channel Partnerships can set up a meaningful and tailored demonstration that will show the Semantha platform working to provide you a real-world evaluation.

Contact Channel Partnerships directly by calling: 01923 618099

Or, email: info@channel-tools.biz

https://channel-partnerships.com