Keras vs. Litera Kira vs. Theano

Keras is quite perfect, if the aim is to build the standard Deep Learning model, and materialize it to serve the real business use case, while it is not suitable if the purpose is for research and a lot of non-standard try out and customization are required, in that case either directly goes to low level TensorFlow API or Pytorch

Incentivized

Kira is a great due diligence tool and can be well utilised on both large and small transactions. It also has good application if you are looking to compare multiple documents against a model form document or market standard templates. Kira is less useful if you are looking to review emails (e.g. as part of a disclosure exercise); or if your review involves non-Latin based script languages.

• One of the reason to use Keras is that it is easy to use. Implementing neural network is very easy in this, with just one line of code we can add one layer in the neural network with all it's configurations.
• It provides lot of inbuilt thing like cov2d, conv2D, maxPooling layers. So it makes fast development as you don't need to write everything on your own. It comes with lot of data processing libraries in it like one hot encoder which also makes your development easy and fast.
• It also provides functionality to develop models on mobile device.

Incentivized

• UI/UX - tagging and naming feels much easier than you'd expect machine learning to feel
• Accuracy - Kira's built-in models perform well out of the box
• Assistance - Kira's support team gets back to me same day if I have a question

Incentivized

• As it is a kind of wrapper library it won't allow you to modify everything of its backend
• Unlike other deep learning libraries, it lacks a pre-defined trained model to use
• Errors thrown are not always very useful for debugging. Sometimes it is difficult to know the root cause just with the logs

Incentivized

• Inability to relabel smart fields to suit the review process means it is hard to align it to particular projects (e.g. it would be useful to relabel the "Assignment" smart field as "Is the contract assignable?")
• Not enough non-English smart fields.
• Needs the ability to resell user-trained smart fields in a marketplace.
• Output is not customizable enough.
• Built-in analysis tools are useful but a little basic.

Incentivized

I am giving this rating depending on my experience so far with Keras, I didn't face any issue far. I would like to recommend it to the new developers.

If our firm had more contracts in English, the usability of Kira would be rated higher. However, since we have to train clauses in Portuguese in order to use Kira, it makes its usability lower. We still are not able to fully use Kira for reading contracts in Portuguese. It takes a long time and many associate hours to make Kira usable in other languages.

Incentivized

Keras have really good support along with the strong community over the internet. So in case you stuck, It won't so hard to get out from it.

Customer Support is excellent. The online help portal is probably the best I have ever seen. Great videos with content easily found. The HelpLine is staffed by knowledgeable people. The videos have saved us providing a lot of in-house training, which we would struggle to resource. The account managers really know the product and their law firm clients and share best practices and trends.

Incentivized

Keras is good to develop deep learning models. As compared to TensorFlow, it's easy to write code in Keras. You have more power with TensorFlow but also have a high error rate because you have to configure everything by your own. And as compared to MATLAB, I will always prefer Keras as it is easy and powerful as well.

Incentivized

Kira offers a lot more out of the box than other providers and is also more flexible around integrations. This, plus the clear pricing structure, is why we went for it instead of (or as well as) others. Diligen, RAVN, Leverton, Della, Seal not in list.

Incentivized

• Easy and faster way to develop neural network.
• It would be much better if it is available in Java.
• It doesn't allow you to modify the internal things.

Incentivized

• Positive ROI: Increased comfort level of attorneys and use of tech
• Neutral ROI: It has not significantly change how we handle projects, since there still is a need for manual review
• Negative ROI: It has been cost prohibitive to scale it

Incentivized