Sunday, March 12, 2017

Alexa socialbot testers wanted!

We are finishing the last details, of the Alquist social bot.  Today we are opening the first preview for testers.  If you are interested, leave your email. We will send you instructions. The total number of testers is limited. Hurry up!

If you do not own Echo or other Alexa appliance, install the Echosim.io or Reverb on your cell, and you are ready to start. Upon signing up, we will email you all required details. We are interested in your feedback.

The chatbot is not perfect but, it is the time to start learning how users interact and collect the feedback. We need real users who are not familiar with the system. Amazon is helping us with their internal testing system, and it is a unique opportunity. Help us!

What can you expect?  We have trained Alquist to carry a simple dialog, it knows how to answer factoid questions using the Wikidata DB, and how to give help. Recently, we have made advances in creating a simple dialog within limited domains with frequently changing data.

All is still under development with a lot of quirks and twists, but your feedback will help us to improve. Thanks!

Sunday, March 5, 2017

New projects - join us

eClub will again organize the Summer Camp (ESC). The ESC 2016 was incredibly successful. Five eClubbers worked on a question answering system YodaQA. At the end of summer, they have entered the Amazon Alexa Prize competition and got in between top twelve selected for development of a social bot. They received $100k scholarship for a social bot development. Currently, they are busy working on the first version of Alquist.

We would like to continue in the direction of developing dialog applications in ESC 2017. The social bot task is very challenging, and many required technologies are still in development. While developing YodaQA, we have looked at the well known classical NLP algorithms as well as to new mainly neural networks based ones, such as LSTM, GRU, etc. to process text in many different ways.

It is beginning of March, but we are already prepared to incubate new, eager students interested joining us on this journey toward smarter systems. We have strong support not only from Amazon but also from the local company Seznam. Seznam is one of the few competing successfully with Google on the domestic market. They are 100% Machine Learning company with a lot of problems of mutual interest.

Here is a sneak preview of the projects for this year. Join us, and work with us tomorrow, if you are interested. We are offering scholarship equivalent to what you would earn working for a company. We are moving to the new CVUT building, it is gorgeous, as soon as it opens, it is just a matter of weeks. Join us! You can start any time.

Automatic email reply generation
In this project, we want to research methods for automatic generation of short responses to emails or social networks messages. Specifically, on a cell phone, it can be a great advantage to select from a selection of semantically diverse replies. We want first cover few words long messages. The initial steps will include a review of Recurrent Neural Networks architectures and a meaningful training set construction.

Amazon Echo conversational application
We have a set of tasks we would like to cover as a spoken dialog. We want to design interactive conversational bots for Amazon Echo. We want the application to be engaging, entertaining and informative, bringing the user latest news from specific areas, such as sports, celebrities, movies, etc. This project is OK for students who are only entering the field with no or small experience.
   
Knowledge extraction
There is vast of information on the Internet. A lot of the information is in the form of a text; the information is unstructured. In this project, we want to review the methods for retrieving and extracting the information, learning the dependencies of statements in the texts. We want to create ontologies from a selected, limited content and store the knowledge for further use. These are very challenging problems but do not hesitate to join. We have students currently working on these topics. We know what the first steps are.

Text summarization
Journalists write the Internet news in a particular language, frequently using idioms, slang or infrequent expressions. In this project, we want to extract what is important and create a summary in a clear language. Initially, we want to summarize long sentences. Next, select a suitable method, implement and test it on a chosen domain.

Events Extraction from Text
This project is only an extension of the previous one. We want to design and implement a system for extracting events from the Internet. The primary goal is selecting news messages based on identified topics (or events). Extraction of economic events like mergers & acquisitions, stock splits, dividend announcements, etc., play an essential role in decision making, in risk analysis applications and monitoring systems.


Tuesday, November 22, 2016

eClub Prague received the Amazon Alexa Prize!

eClub Prague students got one of their best opportunities by being selected as one of 12 teams from world leading universities to compete in the inaugural Amazon Alexa Prize with their very own Alquist chatbot. The eClub team has been selected by Amazon and it has been given the challenge to build a social bot that can converse on popular topics for 20 minutes. By being selected among such names as Princeton University, Berkeley, Carnegie Mellon and as only one of three universities in Europe this is a unique and exciting opportunity to put us on the map as one of the thought leaders on social bots. eClub Prague was awarded a $100,000 stipend, Alexa-enabled devices, free AWS services, and support from Amazon’s Alexa Skills Kit (ASK) team. All this to help us make the final three, who will be announced in August 2017. Also as part of the judging process, Alexa customers will have the opportunity to try out the Alquist chatbot themselves and their feedback will have an instrumental impact on the team making the final. The winners will be announced in November 2017 with a $1,5 million up for grabs. I am the academic advisor for a team consisting of Long Hoang Nguyen, Honza Pichl, Martin Matulík, Jakub Konrád and Petr Marek. the team is very excited about the opportunity that Amazon has given us and we hope to make the final three. Although this is a great achievement for the Prague-based team the work only starts. From now until April they will be working on developing conversational AIs such as knowledge acquisition, natural language understanding, natural language generation, context modeling, commonsense reasoning and dialog planning.

Thursday, October 13, 2016

Thursday, September 22, 2016

Do not look for part time job work for the university

eClub is extending the Summer Camp for the whole academic year. This is an early information.

The eClub Summer Camp is in its third month. This year we have more than twenty members. It is a little less than last year but the projects are much more focused. The mentors are more effective, they have learned how to lead. Overall we have accomplished much more. The success and the high quality of projects has ignited an idea to extend the eClub throughout the whole academic year.

We will offer students scholarships starting from the October 1st for the winter and extend for the summer semester. We are preparing joined labs with our partners Seznam, Jablotron, and many others. We are in the process of signing the contracts. Our joined labs are located in the new CVUT building in the Dejvice campus, everybody will get a seat and table. You will save the commute time. eClub and the partners too, are looking for innovative ideas and interesting projects. We also want to make the projects semestral works or final thesis to let you earn credits. Working with leading companies is a great entry to CVs. eClub will provide scholarships and we also will offer a complete infrastructure including large computer clusters. Each student will have a mentor helping to get over the usual problems no to get stucked.

We will offer similar projects as during the Summer Camp. Mainly from the field of artificial Intelligence, IoT Industry 4.0 and BigData. We do not wnat to limit our activities to this fields only, come and ask. We are inviting students from all Czech Universities. We also will support startups. Work for the leading companies in an university joined lab.

Work on great projects. Follow our FB, eClub web pages and blog, stay tuned for further information.

Wednesday, September 7, 2016

Bots, Home control and many more projects, eClub

The students in the eClub Summer Camp are for more than two months working on new projects in IoT and Bots. Here is the first status report describing the projects under development.

The presentation has two major parts the IoT and conversational applications projects. The IoT team has built a proof of concept application allowing intelligent control of light including the cloud infrastructure. The sensors are wirelessly connected. A cloud application offers a simple dashboard. In conversational applications, we have built several modules, services running in Docker. Combining them we can implement simple conversational bots as well as a factoid answering machine.

In the presentation, you can find a basic information and links to websites, demos or gitHub with the code. Some of the projects are in progress some of them are already finished. Some students will extend the projects to theses in the following academic year. Let us know what you think.

Friday, September 2, 2016

Bots and question answering in ESC 2016

a team of talented students formed around conversational applications in the eClub Summer Camp 2016. They continue developing the YodaQA and a simple Alquist bot. Both systems are built on top of a set of services including dialog managers up to NLP services.

We have started with the YodaQA factoid question answering system inspired by the IBM Watson. It is a fairly sophisticated engine, which builds on many NLP algorithms, Lucene search, RDF databases etc. The architecture and technology description is available on GitHub along with a test website and Android application.

The latest work is concentrated on teaching YodaQA Czech. This requires replacing some of the components with Czech versions. The most important are the Stanford syntactic parser, the Named Entity Recognition and finally the answer classifier. For syntactic parser, we use the Google Tensor Flow, the Syntaxnet and the Czech dependencies dataset. We get similar accuracy as the classical top of the line algorithms. Currently, we are developing the basic version of the entity recognition algorithm based on Conditional Random Fields (CRF). We have plans to implement NER also using Neural Nets.

The biggest problem in machine learning are the training sets. For the initial answer scoring algorithm, we have put together a set of questions-answer pairs. To make the set as rich as possible we have been enriching the set using variables for entities and synonyms, which is allowing us to algorithmically generate a large number of questions. The real system is logging questions and answers helping us creating better training sets. The sets still require some manual processing, but it is worth doing it.

The emergence of the conversational bots caught our attention too. Initially, we have tested the Wit.ai, Microsoft Luise, Meya, and Amazon Echo for English. Soon we have found many different limitations. Because the YodaQA is put together from a set of independent services, NLU processors, we have decided to use the same services to build simpler conversational bots. The bots use two essential parts intent and the entities recognizers. The bot processes the input users query and the extracted intent and entities are saved to a context object. Dialog manager (DM) uses the context to control the dialog flow.

Since we do not use the DM in YodaQA, we had to develop it. During our experiments with commercially available bots, we liked very much the Meya DM because of the simple dialog declaration in YAML. We have decided to go in a similar direction and created our own version called Alquist. It allows us writing even complicated dialogs. The implementation was fast and today we are running our first version of Alquist DM.

All this work is done by about ten students and the team grows. During the last weeks, we have made a considerable progress. We have at work several applications, stay tuned to be the first to test them.