Connect with us


Chatbots Transforming Legal Industry




How chatbots can enhance law firm’s productivity?

KLoBot — the Best AI-Chatbot builder platform


Chatbots, currently are the hot tech-topic in the legal industry and law firms need to leverage the power of chatbots for managing their existing and potential customers.

Advancements in AI and ML have led towards the emergence of AI-enabled chatbots, which can hold human-like conversations through auditory and textual methods. These AI-based chatbots are gaining popularity and are helping several companies across various verticals with customer engagement, workforce productivity, reduced expenses, and a lot more.

Given its history of relying on paper-based documents, the legal industry has always been alleged of falling behind other industries in terms of accepting and deploying emerging technologies. However, over the past few years, the legal industry has been witness to large investments on automation and cloud technology, which has started to take root and is now becoming mainstream.

Several law firms are exploring advanced technologies, and hence the deployment of chatbots is in the initial stages. However, the industry holds huge potential to transform the legal sector. Chatbot vendors and service providers are showcasing several ways in which chatbots can help legal firms, lawyers, and customers to gain better insights about their cases.

Pain points in the legal industry that automation can address

• Onboarding new legal talent often becomes challenging especially when introducing them to legal team-members and clients

• Legal teams deal with hundreds of documents every day making their task more challenging and time-consuming

• With clients becoming tech-savvy and digitally advanced, law firms are under pressure to meet client’s expectations by offering enhanced levels of customer experience

Why legal firms should invest in chatbots?

Legal firms are trying to identify ways to better manage their workflow with lawyers and associates struggling to bridge the digital gap between the legal industry and their clientele. Chatbot vendors are positioning solutions and services that cater across a wide array of services right from automating mundane tasks to narrowing down to specific laws and policies to support their client case. Depending on the size and nature of the law firm, the following areas make top use-cases for collaboration platforms.

Currently, the industry is witnessing demand for chatbots that can help:

• Generate legal agreements, non-disclosure agreements (NDA’s), privacy policy, and other legal-related organizational policies

  • Enable legal firms to increase visibility for clients to find legal resources and search lawyers, and mediators
  • Assist lawyers in interviewing clients, generating legal documents and contracts instantly.

Employee onboarding and management: In any legal organization, chatbots can be used for handling administrative and HR-related tasks. Chatbots can help internal employees to solve trivial issues without any extensive support from the HR department. Employees can leverage chatbots for simpler tasks including setting up reminders, managing leave applications, and ensuring a seamless onboarding process.

1. Conversational AI: Code/No Code

2. Chatbots 2.0: Simplifying Customer Service with RPA and AI

3. Question Answering on Medical conversation

4. Automating WhatsApp with NLP: Complete guide

Ease in accessing and managing information: Paralegals and attorneys need to go through large volumes of information in the form of case studies, laws and policies, and other related information related to the case at hand. Chatbots can help lawyers in analyzing data as well as assisting them in finding the relevant information they are looking for. These high levels of automation reduce the information collection time, offering a hassle-free experience to paralegals and attorneys.

Enhanced customer experience: Some chatbots use NLP to better understand colloquial human language by detecting synonyms, wider terminology, and long phrases. By providing more precise and accurate legal terms and responses, chatbots offer better user experiences. Chatbots act as the legal advisor designed for helping individuals to deal with legal issues and streamlining the process of new queries.

Legal chatbots for internal businesses and consumers

Although chatbots are more focused on providing services for consumers, several companies are designing and developing solutions specifically for lawyers. By automating legal services, Chatbots are positioned to offer value-add for customers and enable law firms with incremental revenues. Chatbots are addressing the high expectations of digital-age customers and are expediting solutions for legal issues.

Chatbots are being used by legal firms to promote interactive and user-friendly communication with their customers so that lawyers can shift their focus to important legal work.

By offering enhanced customer support, law firms establish and strengthen trust with existing as well as new customers.

Chatbots are handling law firms’ internal repetitive tasks and are helping marketing teams to focus on new clients. Law firms are also using chatbots for website visitor engagement and have now become an important part of marketing strategy. Chatbots are being designated to answer the questions of website visitors and help generate qualified leads.

Legal firms can integrate the chatbot in three ways

Future impact of legal chatbots

AI-based chatbots hold the potential to enhance the firm’s efficiency by reducing expenses and boosting ROI.

Chatbots can reduce the burden of report generation and documentation to vastly improve productivity.

Providing free legal advice to existing and potential customers is one of the major use cases of chatbots in the legal industry.

Present-day chatbots are aimed at offering services to customers seeking legal services as well as legal professionals including lawyers, paralegals, judges, prosecutors, and notaries, which is transforming the legal industry. Legal chatbots are now being used by several legal firms for improving their internal as well as external legal operations and providing better client experience.

KLoBot Approach

KLoBot is a provider of no-code chatbot builder platform, helping businesses to build their own chatbots, either based on text or voice. While the platform can be used to build and deploy chatbots for any use case, the legal industry is aptly suited to leverage the full potential of the offerings. Riddled with complex legal terminologies and jargons, clients of law firms are often at a disadvantage to understand the underlying context and relevant firms to represent them.

Developers at KLoBot understand such intricacies of the legal industry as well as challenges faced by law firms resulting in an intuitive platform with capabilities to handle complex customer queries. By automating routine tasks and streamlining business processes, chatbots can be customized to respond to queries from internal firm partners, attorneys as well as customers.

KLoBot helps law firms in creating an automated client response system where clients can ask specific details about their cases, billing history, upcoming events, and much more.

Questions like: What are the recent private equity matters? Which lawyer is handling ACME Railroad Acquisition matter? and other similar questions for connecting with attorneys can be answered by the chatbot.

The platform enables secured access to on-demand organizational intelligence, resulting in faster response based on existing organizational data. KLoBot helps in creating chatbots that can double down as personal assistants for searching client and matter-related information, scheduling meetings, setting reminders, and finding colleagues among others.

KLoBot and the team are dedicated towards continuous research resulting in innovative solutions making them an innovator in delivering AI-powered chatbots.



Graph Convolutional Networks (GCN)

In this post, we’re gonna take a close look at one of the well-known graph neural networks named Graph Convolutional Network (GCN). First, we’ll get the intuition to see how it works, then we’ll go deeper into the maths behind it. Why Graphs? Many problems are graphs in true nature. In our world, we see many data are graphs, […]

The post Graph Convolutional Networks (GCN) appeared first on TOPBOTS.



graph convolutional networks

In this post, we’re gonna take a close look at one of the well-known graph neural networks named Graph Convolutional Network (GCN). First, we’ll get the intuition to see how it works, then we’ll go deeper into the maths behind it.

Why Graphs?

Many problems are graphs in true nature. In our world, we see many data are graphs, such as molecules, social networks, and paper citations networks.

Tasks on Graphs

  • Node classification: Predict a type of a given node
  • Link prediction: Predict whether two nodes are linked
  • Community detection: Identify densely linked clusters of nodes
  • Network similarity: How similar are two (sub)networks

Machine Learning Lifecycle

In the graph, we have node features (the data of nodes) and the structure of the graph (how nodes are connected).

For the former, we can easily get the data from each node. But when it comes to the structure, it is not trivial to extract useful information from it. For example, if 2 nodes are close to one another, should we treat them differently to other pairs? How about high and low degree nodes? In fact, each specific task can consume a lot of time and effort just for Feature Engineering, i.e., to distill the structure into our features.

graph convolutional network
Feature engineering on graphs. (Picture from [1])

It would be much better to somehow get both the node features and the structure as the input, and let the machine to figure out what information is useful by itself.

That’s why we need Graph Representation Learning.

graph convolutional network
We want the graph can learn the “feature engineering” by itself. (Picture from [1])

If this in-depth educational content on convolutional neural networks is useful for you, you can subscribe to our AI research mailing list to be alerted when we release new material. 

Graph Convolutional Networks (GCNs)

Paper: Semi-supervised Classification with Graph Convolutional Networks (2017) [3]

GCN is a type of convolutional neural network that can work directly on graphs and take advantage of their structural information.

it solves the problem of classifying nodes (such as documents) in a graph (such as a citation network), where labels are only available for a small subset of nodes (semi-supervised learning).

graph convolutional network
Example of Semi-supervised learning on Graphs. Some nodes dont have labels (unknown nodes).

Main Ideas

As the name “Convolutional” suggests, the idea was from Images and then brought to Graphs. However, when Images have a fixed structure, Graphs are much more complex.

graph convolutional network
Convolution idea from images to graphs. (Picture from [1])

The general idea of GCN: For each node, we get the feature information from all its neighbors and of course, the feature of itself. Assume we use the average() function. We will do the same for all the nodes. Finally, we feed these average values into a neural network.

In the following figure, we have a simple example with a citation network. Each node represents a research paper, while edges are the citations. We have a pre-process step here. Instead of using the raw papers as features, we convert the papers into vectors (by using NLP embedding, e.g., tf–idf).

Let’s consider the green node. First off, we get all the feature values of its neighbors, including itself, then take the average. The result will be passed through a neural network to return a resulting vector.

graph convolutional network
The main idea of GCN. Consider the green node. First, we take the average of all its neighbors, including itself. After that, the average value is passed through a neural network. Note that, in GCN, we simply use a fully connected layer. In this example, we get 2-dimension vectors as the output (2 nodes at the fully connected layer).

In practice, we can use more sophisticated aggregate functions rather than the average function. We can also stack more layers on top of each other to get a deeper GCN. The output of a layer will be treated as the input for the next layer.

graph convolutional network
Example of 2-layer GCN: The output of the first layer is the input of the second layer. Again, note that the neural network in GCN is simply a fully connected layer (Picture from [2])

Let’s take a closer look at the maths to see how it really works.

Intuition and the Maths behind

First, we need some notations

Let’s consider a graph G as below.

graph convolutional network
From the graph G, we have an adjacency matrix A and a Degree matrix D. We also have feature matrix X.

How can we get all the feature values from neighbors for each node? The solution lies in the multiplication of A and X.

Take a look at the first row of the adjacency matrix, we see that node A has a connection to E. The first row of the resulting matrix is the feature vector of E, which A connects to (Figure below). Similarly, the second row of the resulting matrix is the sum of feature vectors of D and E. By doing this, we can get the sum of all neighbors’ vectors.

graph convolutional network
Calculate the first row of the “sum vector matrix” AX
  • There are still some things that need to improve here.
  1. We miss the feature of the node itself. For example, the first row of the result matrix should contain features of node A too.
  2. Instead of sum() function, we need to take the average, or even better, the weighted average of neighbors’ feature vectors. Why don’t we use the sum() function? The reason is that when using the sum() function, high-degree nodes are likely to have huge v vectors, while low-degree nodes tend to get small aggregate vectors, which may later cause exploding or vanishing gradients (e.g., when using sigmoid). Besides, Neural networks seem to be sensitive to the scale of input data. Thus, we need to normalize these vectors to get rid of the potential issues.

In Problem (1), we can fix by adding an Identity matrix I to A to get a new adjacency matrix Ã.

Pick lambda = 1 (the feature of the node itself is just important as its neighbors), we have Ã = A + I. Note that we can treat lambda as a trainable parameter, but for now, just assign the lambda to 1, and even in the paper, lambda is just simply assigned to 1.

By adding a self-loop to each node, we have the new adjacency matrix

Problem (2)For matrix scaling, we usually multiply the matrix by a diagonal matrix. In this case, we want to take the average of the sum feature, or mathematically, to scale the sum vector matrix ÃX according to the node degrees. The gut feeling tells us that our diagonal matrix used to scale here is something related to the Degree matrix D̃ (Why , not D? Because we’re considering Degree matrix  of new adjacency matrix Ã, not A anymore).

The problem now becomes how we want to scale/normalize the sum vectors? In other words:

How we pass the information from neighbors to a specific node?

We would start with our old friend average. In this case, D̃ inverse (i.e., D̃^{-1}) comes into play. Basically, each element in D̃ inverse is the reciprocal of its corresponding term of the diagonal matrix D.

For example, node A has a degree of 2, so we multiple the sum vectors of node A by 1/2, while node E has a degree of 5, we should multiple the sum vector of E by 1/5, and so on.

Thus, by taking the multiplication of D̃ inverse and X, we can take the average of all neighbors’ feature vectors (including itself).

So far so good. But you may ask How about the weighted average()?. Intuitively, it should be better if we treat high and low degree nodes differently.

We’re just scaling by rows, but ignoring their corresponding columns (dash boxes)
Add a new scaler for columns.

The new scaler gives us the “weighted” average. What are we doing here is to put more weights on the nodes that have low-degree and reduce the impact of high-degree nodes. The idea of this weighted average is that we assume low-degree nodes would have bigger impacts on their neighbors, whereas high-degree nodes generate lower impacts as they scatter their influence at too many neighbors.

graph convolutional network
When aggregating feature at node B, we assign the biggest weight for node B itself (degree of 3), and the lowest weight for node E (degree of 5)
Because we normalize twice, we change “-1” to “-1/2”

For example, we have a multi-classification problem with 10 classes, F will be set to 10. After having the 10-dimension vectors at layer 2, we pass these vectors through a softmax function for the prediction.

The Loss function is simply calculated by the cross-entropy error over all labeled examples, where Y_{l} is the set of node indices that have labels.

The number of layers

The meaning of #layers

The number of layers is the farthest distance that node features can travel. For example, with 1 layer GCN, each node can only get the information from its neighbors. The gathering information process takes place independentlyat the same time for all the nodes.

When stacking another layer on top of the first one, we repeat the gathering info process, but this time, the neighbors already have information about their own neighbors (from the previous step). It makes the number of layers as the maximum number of hops that each node can travel. So, depends on how far we think a node should get information from the networks, we can config a proper number for #layers. But again, in the graph, normally we don’t want to go too far. With 6–7 hops, we almost get the entire graph which makes the aggregation less meaningful.

graph convolutional network
Example: Gathering info process with 2 layers of target node i

How many layers should we stack the GCN?

In the paper, the authors also conducted some experiments with shallow and deep GCNs. From the figure below, we see that the best results are obtained with a 2- or 3-layer model. Besides, with a deep GCN (more than 7 layers), it tends to get bad performances (dashed blue line). One solution is to use the residual connections between hidden layers (purple line).

graph convolutional network
Performance over #layers. Picture from the paper [3]

Take home notes

  • GCNs are used for semi-supervised learning on the graph.
  • GCNs use both node features and the structure for the training
  • The main idea of the GCN is to take the weighted average of all neighbors’ node features (including itself): Lower-degree nodes get larger weights. Then, we pass the resulting feature vectors through a neural network for training.
  • We can stack more layers to make GCNs deeper. Consider residual connections for deep GCNs. Normally, we go for 2 or 3-layer GCN.
  • Maths Note: When seeing a diagonal matrix, think of matrix scaling.
  • A demo for GCN with StellarGraph library here [5]. The library also provides many other algorithms for GNNs.

Note from the authors of the paper: The framework is currently limited to undirected graphs (weighted or unweighted). However, it is possible to handle both directed edges and edge features by representing the original directed graph as an undirected bipartite graph with additional nodes that represent edges in the original graph.

What’s next?

With GCNs, it seems we can make use of both the node features and the structure of the graph. However, what if the edges have different types? Should we treat each relationship differently? How to aggregate neighbors in this case? What are the advanced approaches recently?

In the next post of the graph topic, we will look into some more sophisticated methods.

graph convolutional network
How to deal with different relationships on the edges (brother, friend,….)?


[1] Excellent slides on Graph Representation Learning by Jure Leskovec (Stanford):

[2] Video Graph Convolutional Networks (GCNs) made simple:

[3] Paper Semi-supervised Classification with Graph Convolutional Networks (2017):

[4] GCN source code:

[5] Demo with StellarGraph library:

This article was originally published on Medium and re-published to TOPBOTS with permission from the author.

Enjoy this article? Sign up for more computer vision updates.

We’ll let you know when we release more technical education.

Continue Reading


Microsoft BOT Framework — Loops



Loops is one of the basic programming structure in any programming language. In this article, I would demonstrate Loops within Microsoft BOT framework.

To follow this article clearly, please have a quick read on the basics of the Microsoft BOT framework. I wrote a couple of articles sometime back and the links are below:

Let’s Get Started.

I would be using the example of a TaxiBot described in one of my previous article. The BOT asks some general questions and books a Taxi for the user. In this article, I would be providing an option to the user to choose there preferred cars for the ride. The flow will look like below:

Create a new Dialog Class for Loops

We would need 2 Dialog classes to be able to achieve this task:

  1. SuperTaxiBotDialog.cs: This would be the main dialog class. The waterfall will contains all the steps as defined in the previous article.
  2. ChooseCarDialog.cs: A new dialog class will be created which would allow the user to pick preferred cars. The loop will be defined in this class.

The water fall steps for both the classes could be visualized as:

The complete code base is present on the Github page.

Important Technical Aspects

  • Link between the Dialogs: In the constructor initialization of SuperTaxiBotDialog, add a dialog for ChooseCarDialog by adding the line:
AddDialog(new ChooseCarDialog());

1. 8 Proven Ways to Use Chatbots for Marketing (with Real Examples)

2. How to Use Texthero to Prepare a Text-based Dataset for Your NLP Project

3. 5 Top Tips For Human-Centred Chatbot Design

4. Chatbot Conference Online

  • Call ChooseCarDialog from SuperTaxiBotDialog: SuperTaxiBotDialog calls ChooseCarDialog from the step SetPreferredCars, hence the return statement of the step should be like:
await stepContext.BeginDialogAsync(nameof(ChooseCarDialog), null, cancellationToken);
  • Return the flow back from ChooseCarDialog to SuperTaxiBotDialog: Once the user has selected 2 cars, the flow has to be sent back to SuperTaxiBotDialog from the step LoopCarAsync. This should be achieved by ending the ChooseCarDialog in the step LoopCarAsync.
return await stepContext.EndDialogAsync(carsSelected, cancellationToken);

The complete code base is present on the Github page.

Once the project is executed using BOT Framework Emulator, the output would look like:

Hopefully, this article will help the readers in implementing a loop with Microsoft BOT framework. For questions: Hit me.




Continue Reading


The Bleeding Edge of Voice

This fall, a little known event is starting to make waves. As COVID dominates the headlines, an event called “Voice Launch” is pulling…



Tapaan Chauhan

This fall, a little known event is starting to make waves. As COVID dominates the headlines, an event called “Voice Launch” is pulling together an impressive roster of start-ups and voice tech companies intending to uncover the next big ideas and start-ups in voice.

While voice tech has been around for a while, as the accuracy of speech recognition improves, it moves into its prime. “As speech recognition moves from 85% to 95% accuracy, who will use a keyboard anymore?” says Voice Launch organizer Eric Sauve. “And that new, more natural way to interact with our devices will usher in a series of technological advances,” he added.

Voice technology is something that has been dreamt of and worked on for decades all over the world. Why? Well, the answer is very straightforward. Voice recognition allows consumers to multitask by merely speaking to their Google Home, Amazon Alexa, Siri, etc. Digital voice recording works by recording a voice sample of a person’s speech and quickly converting it into written texts using machine language and sophisticated algorithms. Voice input is just the more efficient form of computing, says Mary Meeker in her ‘Annual Internet Trends Report.’ As a matter of fact, according to ComScore, 50% of all searches will be done by voice by 2020, and 30% of searches will be done without even a screen, according to Gartner. As voice becomes a part of things we use every day like our cars, phones, etc. it will become the new “norm.”

The event includes a number of inspiration sessions meant to help start-ups and founders pick the best strategies. Companies presenting here include industry leaders like Google and Amazon and less known hyper-growth voice tech companies like Deepgram and Balto and VCs like OMERS Ventures and Techstars.

But the focus of the event is the voice tech start-ups themselves, and this year’s event has some interesting participants. Start-ups will pitch their ideas, and the audience will vote to select the winners. The event is a cross between a standard pitchfest and Britain’s Got Talent.


Continue Reading
AI3 hours ago

Graph Convolutional Networks (GCN)

AI4 hours ago

Microsoft BOT Framework — Loops

AI5 hours ago

The Bleeding Edge of Voice

AI20 hours ago

Using Amazon SageMaker inference pipelines with multi-model endpoints

AI20 hours ago

Using Amazon SageMaker inference pipelines with multi-model endpoints

AI20 hours ago

Using Amazon SageMaker inference pipelines with multi-model endpoints

AI20 hours ago

Using Amazon SageMaker inference pipelines with multi-model endpoints

AI20 hours ago

Using Amazon SageMaker inference pipelines with multi-model endpoints

AI20 hours ago

Using Amazon SageMaker inference pipelines with multi-model endpoints

AI20 hours ago

Using Amazon SageMaker inference pipelines with multi-model endpoints

AI20 hours ago

Using Amazon SageMaker inference pipelines with multi-model endpoints

AI20 hours ago

Using Amazon SageMaker inference pipelines with multi-model endpoints

AI20 hours ago

Using Amazon SageMaker inference pipelines with multi-model endpoints

AI20 hours ago

Using Amazon SageMaker inference pipelines with multi-model endpoints

AI20 hours ago

Using Amazon SageMaker inference pipelines with multi-model endpoints

AI20 hours ago

Using Amazon SageMaker inference pipelines with multi-model endpoints

AI20 hours ago

Using Amazon SageMaker inference pipelines with multi-model endpoints

AI20 hours ago

Using Amazon SageMaker inference pipelines with multi-model endpoints

AI20 hours ago

Using Amazon SageMaker inference pipelines with multi-model endpoints

AI20 hours ago

Using Amazon SageMaker inference pipelines with multi-model endpoints