our News

November 15, 2017

Grafische vormgeving van jurisprudentie? Juribot doet het!

 

Emma Smitshuijzen, Legal Business Analyst, over de nieuwe hoge raad- interface:

Juribot, de kunstmatige intelligentie applicatie voor juristen, komt opnieuw met een innovatieve manier om jurisprudentie inzichtelijker en transparanter te maken: dit keer met een grafische interface voor referenties in Hoge Raad zaken (ook wel: de graaf). De graaf laat u de verwijzingen binnen uitspraken van de Hoge Raad zien in een interactieve grafische interface, en daarbij ook de mate van verwijzingen. Juribot™  belicht hiermee een nieuwe innovatieve kant van het gebruik van Artificiële Intelligentie (AI) binnen het juridisch vakgebied. Met het gebruik van de graaf is inzicht krijgen in de belangrijkste jurisprudentie over een bepaald onderwerp makkelijker dan ooit.

De graaf:

  • visualiseert de referenties tussen zaken van de Hoge Raad.

  • toont bij het invoeren van zoektermen alleen de zaken die matchen met uw termen.

  • geeft verschillende filtermogelijkheden om tot het beste resultaat te komen.

  • kan gezoomed en gesleept worden om naar uw wens referenties in beeld te brengen.

  • toont met verschil in grootte de mate waarin gerefereerd wordt naar een zaak.

    • hierdoor is snel in te zien wat wordt beschouwd als een kernzaak binnen een bepaald onderwerp

.

Een voorbeeld van snel inzicht is de  algemene top 5 van meest-gerefereerde strafzaken:

  1. Arrest Redelijke Termijn II (ECLI:NL:HR:2008:BD2578)

  2. Arrest Afvoerpijp (ECLI:NL:HR:2004:AM2533)

  3. Arrest Hennepkwekerij (ECLI:NL:HR:2006:AU9130)

  4. Arrest Redelijke Termijn I (ECLI:NL:HR:2000:AA7309)

  5. Arrest Post-Salduz (ECLI:NL:HR:2009:BH3079)

 

Op dit moment is de graaf in ontwikkeling op het gebied van strafrecht, maar zoals voor alle applicaties van Juribot™ geldt: ideeën en wensen van gebruikers staan voorop. Het is mogelijk om de graaf (en de andere applicaties) door te ontwikkelen tot een product dat volledig aansluit bij uw rechtsgebied of manier van werken. Denk hierbij aan het toevoegen van eigen data of het aanpassen van de filters.

 

Neemt u vooral contact met mij op bij ideeën, vragen of opmerkingen Emma Smitshuijzen, smitshuijzen@semlab.nl . Laat het me ook weten indien u geïnteresseerd bent in een vrijblijvende demonstratie van JuriBot

 

 

February 9, 2017

JuriBot – The Dutch Legal AI Predicting Criminal Trial Outcomes

Artificial Lawyer recently caught up with Bram Stalknecht, CEO of Dutch AI developer SemLab and founder of JuriBot, a legal AI litigation analysis application capable of criminal trial outcome prediction.

Stalknecht begins by explaining that JuriBot has been built by SemLab, a Dutch company that says of itself: ‘[We are] Europe’s main developers of semantic software applications. Today we have one of the largest groups of experts in Natural Language Processing (NLP), Computational Linguistics and Artificial Intelligence technologies.’

SemLab has around 45 full time staff working on AI. The company operates in several areas and has developed legal applications before, such as CrimiKaart, which allows people to track crimes committed in Holland at a very detailed level.

more

 

September 22, 2016

Who is the most successful lawyer or the most strict judge in the Netherlands?

LegalRobot ™: The First Intelligent Dutch case law machine is expected as Beta on www.semlab.nl/legalrobot this October. This web application uses Artificial Intelligence (AI) and will be offered free of charge to legal experts and lawyers. The application includes all public cases for criminal and related case law. Other case law is added in the course of this year.

The AI LegalRobot™ has analyzed the documents so you:

  • can filter out the defendant or perpetrator characteristics.
  • can search in specific sections of the document.
  • can filter by judge or lawyer.
  • can select acquittals or convictions.

This makes it possible to estimate which lawyer at which court for which type of offense is most likely to achieve an acquittal.
Legal robot mannetje v3 middel
LegalRobot ™ is registered as a trade mark in the Benelux by SemLab Ltd.

 

September 22, 2016

Wie is de beste advocaat of de strengste rechter van Nederland?

Legal Robot™: De eerste Nederlandse Intelligente jurisprudentiemachine wordt in oktober verwacht als Bèta op www.semlab.nl/legalrobot. De webapplicatie maakt gebruik van Artificiële Intelligentie (AI) en zal kosteloos worden aangeboden aan juristen en advocaten.
De applicatie bevat alle publieke jurisprudentie voor strafrecht en gerelateerde rechtsgebieden. Overige rechtsgebieden worden in het loop van dit jaar toegevoegd.
De AI van LegalRobot™ heeft de documenten geanalyseerd waardoor U:
• kan filteren op het gebruikte verweer of daderschap kenmerken.
• kan zoeken in specifieke secties van het document.
• kan filteren op rechter of advocaat.
• kan selecteren op vrijspraken of juist veroordelingen.
Hiermee wordt het mogelijk om in te schatten welke advocaat bij welke rechter voor welk soort delict de meeste kans maakt op een vrijspraak.
Legal Robot™ is als merk gedeponeerd in de Benelux door SemLab BVLegal robot mannetje v3 middel.

 

September 11, 2015

The Future of the Law: the impact of artificial intelligence and other advanced technologies on the search for truth and justice

LawTech Europe Congress is the leading annual law-, audit-, & technology conference taking place this year on October 26th-27th in Brussels. Innovation in law is one of the key drivers in this industry to change knowledge management and processes in law practices radically. One of the disruptive law-technology companies emerge in this field is SemLab from the Netherlands. SemLab
is the premium big data analytics companies using Artificial Intelligence and Semantic Analytics for predictive analytics and knowledge management in law practices. CEO Bram Stalknecht is delighted to be panelist in Big Data and Artificial Intelligence. In discussion with Ann Hemming & Alex Smith (LexisNexis) the topic is:

Making Connections With Legal Content

In the world of Big Data, there are new opportunities to implement smart systems and use intelligent linking of content to help users to find answers to legal problems, not only more quickly but also in new ways. Big Data analysis is helping us understand the DNA of the law from the creation of legislation through to interpretation in practice and in the court room. Find out how Big Data analytics has the potential to change the way we work with legal content.

Other conference topics include:

  • Data Privacy/Protection and Cross-Border ESI Requests
  • E-Discovery/E-Disclosure in a Big Data World
  • Competition Investigations and dawn raids
  • Mobile / Social Media / Cloud Discovery
  • Governance Risk and Compliance
  • Legal Efficiencies (Knowledge, Project, and Price Management)
  • Artificial Intelligence in Dispute Resolution
  • Digital Fraud Forensics
  • Data Analytics for Auditors
  • Digital Forensics Training

Come and learn and network with some of the best minds in audit, investigations, and technology.
The event website is www.lawtecheuropecongress.com

 

April 29, 2014

SemLab news analytics now available with event sentiment from non-attributed minutes of ECB governing council meetings

In a speech in Amsterdam on Thursday, the ECB president Mario Draghi said he is convinced that publishing an account of the main arguments raised in the central bank’s monthly policy meetings “would be useful” and “will on balance serve to strengthen the governing council’s collegiate decision making and communication”.
Bram Stalknecht, CEO SemLab said publishing non-attributed minutes of council meetings will open up the ECB’s decision making process, as an addition to ECB the monthly held press conferences, avoiding unexpected decisions.
With SemLab council meetings sentiment analytics, customers can react faster on ECB decisions, including conventional measures, eg liquidity operations and longer-term fixed rate operations. This provides at-a-glance insight in macro economic moving events, in a computer readable format.The resulting minute events are ranked according to their implicit sentiment on scale of -5 (negative) to 5 (positive).
Mario Draghi has backed plans for the European Central Bank to publish non-attributed minutes of its governing council meetings, a proposal that would move the central bank closer to its peers in the UK, US and Japan.

 

July 3, 2013

Ranking Luxury cars brands based on sentiment

SemLab’s semantic text processing platform enables the real-time monitoring of product and brand associated sentiments. In our showcase application AutoSentiment we continuously monitor the top ten most popular online automotive blog websites in The Netherlands and capture the sentiments expressed in the edited articles as well as in the readers’ comments.

In contrast to traditional sentiment tools, we determine the semantics of the expressed opinions by comparing the text to an automotive ontology of over 300 events. These events describe the most common concepts expressed in these types of text. For example the events range from “I like the car” to “the engine noise is barely audible”. Furthermore, the events are classified in the seven main quality parameters for luxury cars: Price, Looks, Driving experience, Comfort, Fuel consumption, Quality and Safety.

A live version of the AutoSentiment monitoring system is available here.

Results

The system is currently online and has processed about 145.000 text items resulting in 141.396 useful events. Excluding all car brands that yield 50 events or less, results in data on the 37 most popular car brands currently available in The Netherlands.

Ranking this data according to the defined parameters results in the following graphs:

Luxury car brands ranked on price sentiment

 

The graph above lists the car brands according to the percentage of positive sentiment about its purchasing cost. On the left hand side the brands are perceived as (too) expensive, the cars on the right are deemed affordable or to offer good value for money.

The overall results are not surprising: The top five expensive car brands include Ferrari, Land Rover and Cadillac, whereas the affordable brands are Skoda, Suzuki and Mitsubishi. More interesting is the position of Dacia and Renault. Renault is perceived as significantly more affordable than its low cost sister brand Dacia, which this data puts in the same range as the acclaimed luxury brand Lexus.

Luxury car brands ranked on driving experience sentiment

 

Regarding the driving experience, the top three consists of Porsche, Jaguar and Ferrari. The worst driving experience is expected from Chevrolet (In The Netherlands mostly marketing the former Daewoo models) and Dacia.

Luxury car brands ranked on appearance sentiment

 

The aesthetics associated with the car brands result in the graph above. The bottom section is the domain of most of the Japanese brands (with the exception of Suzuki and Mazda) and, more surprisingly Volkswagen. The top section is populated by the Italian design of Alfa Romeo and Lancia, but also Tesla whose limited model range has an almost unanimous appeal.
Value for money

Another way of examining this data is to plot one factor against the other. For instance when using price on the horizontal axis and the looks on the vertical axis results in the graph below.

Luxury car brands ranked on looks versus price sentiment

 

This graph clearly illustrates that for affordable good looking cast the Italian brands are in a league of their own. Fiat seems to be a bit out of contact with the other Italian brands, but still scores higher than most traditionally German brands.

The French brands are mostly associated with reasonably affordable and generally comfortable cars. This expectation can also be checked using our data since comfort was one of the main parameters included. The graph below plots the perceived comfort versus the price level of that brand.

Luxury car brands ranked on comfort versus price sentiment

 

The graph above illustrates that the Italian brands are perceived to offer less comfortable cars that the traditionally French brands. German brands score similarly but are generally in a higher price range. Surprisingly, Volkswagen scores higher than the luxury brands Mercedes and BMW. This may well result from the definition of Comfort used in this test, which included ergonomics, personal space and general practicality.
Conclusion

The conclusion that we draw from these results is that the data appears to be in agreement with most stereotypical preconceptions about the car brands. This is a good thing since the system is aimed at capturing the opinion of the general public, which by its nature can be expected to be sensitive to stereotyping.

A logical improvement in this study is to examine the various car models instead of the generic brands. In fact, the required data is available so if anyone is interested in these results or any other aspect of real time product sentiment monitoring, please don’t hesitate to contact us.

 

May 13, 2013

ViewerPro automatiseert verwerking Wet Openbaarheid van Bestuur (WOB) verzoeken

SemLab’s VIEWERPRO software wordt ingezet tegen het explosief stijgende aantal verzoeken van burgers, bedrijven en advocaten die beroep doen op de Wet openbaarheid van bestuur (WOB). “De reactietijd is thans zo verbeterd dat onze klanten, waaronder het Openbaar Ministerie, de stroom WOB verzoeken makkelijk aankunnen, en ruimschoots binnen de wettelijk gestelde termijn kunnen reageren” zegt Bram Stalknecht, SEMLAB te Alphen aan den Rijn. “Onze klanten vermoeden steeds vaker misbruik van deze wet, en hebben de stap genomen om onze taaltechnologie te gebruiken voor het detecteren van deze verzoeken. Door onze technologie in het informatieproces te integreren wordt de informatiestroom door een intelligent computersysteem gestuurd. Medewerkers worden nu ontlast en het systeem is zo ingeregeld dat het pieken makkelijk kan opvangen en flexibel voor elk WOB-onderwerp kan worden ingericht.”

Door middel van Natural Language Processing en Artificial Intelligence technieken detecteert VIEWERPRO met hoogste precisie en recall woorden en begrippen die relevant zijn uit de binnenkomende brieven en e-mails. Deze worden automatisch opgenomen in de reacties naar de verzoekers.

 

 

May 13, 2013

SemLab Internship Opportunities: Now open for international candidates

Internship Opportunities: Now open for international candidates:

1- Econometrics & Operations Research

2- Quantitative Modeling for Algorithmic Trading & Testing

We are looking for candidates for our fast growing work in our knowledge engineering developments in algorithmic trading.

Ad1-

Background of candidate is in Econometrics & Operations Research at a M.A. level university.

The candidate will be joining our Research & Development team in The Netherlands, near Amsterdam Airport. The thesis project is focusing on news analytics for multi asset class investments. The candidates should have an understanding of the implications and effects from news events on investments and risks. Macro economics and fixed income as well as equities and derivatives are subjects of interest of the internship work.

Duration: 6 month. After a successful completion of the thesis it is expected to be part of the growing development team.

Ad2-

Background of the candidate is in Quantitative Modeling and/or Financial Mathematics (M.Sc./PhD-thesis)

The candidate will be joining our Research & Development team in The Netherlands, near Amsterdam Airport. The thesis project is focusing on news analytics and market data for equity asset class algorithmic trading.

Candidates should have an understanding of risk/(multi) asset valuation modeling and an emphasis on financial service applications.

We require academic experience in the field of financial data analysis and research, with strong analytic solving skills, including tools like Matlab/R and experience of working with statistics and data sets for testing your algorithm and benchmark against indices.

Communication in English is essential to both of the intern positions as well as a valid EU working permit.

If you are interested in any of these positions please send your C.V. to stalknecht@semlab.nl

 

April 25, 2013

Filtering misinformation AP hacked twitter account; News analytics does work

 

4-format27ap-account-550x250

Recently a hacker took over the twitter account for the Associated Press (AP), creating momentary chaos across the world. The hacker posted a fake message claiming that US President Barack Obama was injured as a result of an explosion in the White House: AP Twitter

Immediately after the fake tweet went live, legacy news feed machines took up this message. This resulted in drastic nosedives of both the Dow Jones Industrial Average and the S&P 500 before quickly rebounding:  Machine in Control

“This is what happens if you don’t incorporated semantic cross referencing in your Machine Readable News (MRN) processing systems” says Bram Stalknecht, CEO of semantic analytics software vendor SemLab. “High frequency traders relying on social media only, without enhanced noise filtering  and cross referencing, risk taking decisions based on wrong news”.