Mentor at TiU: Francesco Lelli 

Mentors at Talpa: Anca Dumitrache and/or Ricardo Fabian Guevara

There are some internships opportunities available at Talpa. You will have the opportunity to develop your master’s thesis in collaboration with the AI division of one of the most innovative media companies in the Netherlands .

If you have a go-get attitude with the desire to expand your knowledge and expertise in the area of big data and artificial intelligence, this is probably the internship that you are looking for.

Topics for this thesis include Natural Language Processing (NLP), Machine Learning and Predictors. At the same time you are encouraged to propose your own idea as well.

Knowledge and Skills:

Programming, preferably Python, and/or statistical skills.

Interested in Joining Talpa?

Here you can find a short presentation of the company:

Where to Read More:

The following ideas are possible internship opportunities and related topic for your thesis. You may want to use them for forming an idea of the kind of jobs that you will be doing at Talpa as well as for developing your research proposal (here you can find a few tips for that).

Swimlane for Trending on Social Media

Both KIJK (video streaming platform) and JUKE (audio streaming platform) present their content separated into swimlanes on the front page. For instance, one swimlane contains a list of TV shows that were popular in the previous days. We would like to create a new swimlane that contains items that were trending on social media. Taking Twitter as a data source, the project will go through the following steps:

• (1) extract tweets about popular TV shows and/or radio shows,
• (2) perform entity linking to match them to the shows in our database,
• (3) aggregate the results to get the most popular shows in one swimlane.

Project: KIJK and/or JUKE

Automatic Teaser Tweet Creation

Starting with a (textual) description of a TV show episode or radio program, we would like to generate teaser tweets about the show that are meant to generate anticipation on social media. The underlying task would be a summarization problem, where the program description is mapped to a short tweet about it. The tweet should contain relevant information about the program, but not reveal any spoilers. Either an extractive (entity + relation extraction) or abstractive method could be applied.

Source: https://www.aclweb.org/anthology/N19-1398/

Project: KIJK and/or JUKE

Exploring Pair-wise Learning-to-Rank

Talpa current recommender system uses ALS, a point-wise learning-to-rank approach, where the learning objective is based on modeling the score of a given item (i.e. similarly to how regression works). Alternative methods of doing learning-to-rank are pair-wise (learning objective is to model the ranking of a pair of items relative to each other) and list-wise learning to rank (learning objective is calculated over the entire list of items). The project goal is to investigate different learning objectives and find out:

• (1) how they perform relatively to the point-wise method,
• (2) if there are subsets of data where this method works better/worse.

Source:https://medium.com/@nikhilbd/pointwise-vs-pairwise-vs-listwise-learning-to-rank-80a8fe8fadfd

Project: KIJK and/or JUKE

Automatic Playlist Generation

JUKE music player features a lot of non-stop music playlists that are manually created by an editor, usually selecting music from a given genre (e.g. hard rock non-stop radio). We would like to see whether these playlists can be generated by AI and what the quality is. This can be approached as a song clustering problem, where the feature space could contain the genre, artist, as well as other audio features.

Project: JUKE

Google AdWords for Video

Advertisers can buy Google search keywords to show their ad in conjunction with them. We would like to see whether it is possible to do something similar within videos, too. In this way, contextual advertising in different medias becomes feasible. The steps involved in this project are:

• (1) generate textual metadata of video (either based on transcript, or other features of the video; there might be some existing video metadata as well),
• (2) match video textual metadata with ad keywords.

Exploring Seasonal Trends as RecSys Features

Our domain experts know that both video and audio streaming trends are highly influenced by seasonality (e.g. Sky Radio becomes very popular over Christmas). The goal of this project is to:

• (1) identify these trends by studying user listening data, then
• (2) incorporating these trends into our prediction model (e.g. recommend Sky Radio to fans of Christmas music, but only over the Christmas holidays).

Challenge: a lot of data may be needed to accomplish this.

Project: KIJK and/or JUKE

Radio Station Embeddings

Goal: produce embedding with various sizes similar to Glove but for radio stations that reflect radio station similarity with euclidean distance.

Value: many of Talpa challenges, like radio to radio similarity, could be tackled with this approach. Our RecSys can also use the radio embedding as a feature to determine if a radio channel is a good match for a user. This could also greatly alleviate the cold start problem when we introduce new radio stations.

Approach: this is an unexplored problem but there has been previous research and practical work done on audio embeddings. In the simplest form, a radio station embedding could be just a bag of features like genre frequencies, languages and origins of artists, but also properties from the target audience like age range. Going beyond that, it could use an average of the embeddings of representative songs on it in a given past period. Another valuable asset of Talpa is its understanding of usage behavior, so radio station features could also be calculated based on the type of person who listens to it, the frequency of listening and other seasonal behavior.

At the same time, there is a temporal aspect to take into consideration when analyzing user preference of radio stations. Therefore, we cannot expect the embeddings to remain the same forever. Consequently a refresh period is to be expected (even word embeddings need to account for word semantic drifting, only their refresh window is larger).

Project: Juke

Podcast Embeddings for JUKE

Similar to the radio embeddings project, Talpa is interested in creating embeddings for the podcasts available on JUKE. Podcast recommendations suffer from cold start problem even more than radio, since there is usually a high volume of items that are published continuously. The features that can be used for podcast embeddings are also slightly different than typical audio embedding features based on e.g. musical genre.

Project: Juke

Interested in a Talpa internship? Check also the Following:

Webinar about Talpa Internship Opportunities (Available for Tilburg Student Only)

Interested in Applying?

Send an email to Francesco Lelli with CV, Short motivation letter, project(s) that interest you and (optional) draft research proposal. In the case you would like to propose a particular project please put extra attention to your research proposal.

A selected list of candidates will be interviewed by TALPA that has the ultimate saying on accepting you for an internship. Succes, Good luck, In Bocca al Lupo!

The post Master Thesis Plus Talpa Internship Opportunities in Big Data and Artificial Intelligence appeared first on Francesco Lelli.

Web 2.0 communities emerge regularly with the growing need for domain-specific programming over Web APIs. Even though Web mashups provide access to Web APIs, they ignore domain-specific programming needs. On the other hand, developing domain-specific languages (DSLs) is costly and not feasible for such ad hoc communities. We propose User Language Domain (ULD): an intermediate Web based architecture using a domain-specific embedded languages approach that reduces the cost of DSL development to plugging the Web APIs into a host end user programming language. We have implemented the proposed architecture in the context of smart devices, where we plug the functionality of different Lego Mindstorms devices into a Web-based visual programming language. We expect that several domains, such as smart homes or wearable computers can use the ULD architecture to reduce development effort.

Some relevant Key words: domain specific languages, Web 2.0 communities, end user programming, plugin architecture, smart devices, ubiquitous computing.

Our case study of smart devices helps to show the promise of separating functionality from the end user programming language in end user programming. Currently, web based artifacts are released together with a set of open APIs that can be used by their customers for building extensions. Our solution allows an efficient way of embedding these APIs into a customizable wed based end user programming environment. Based on this case study we note that:

• The idea of adopting a plugin architecture introduces a tradeoff between (i) having a standardized and uniform access to different APIs and (ii) having a completely free set of methods. In the first case the realization of the Application Domains Library is simpler and portable. However, the introduction of domain dedicated features is more complex.
• In the realized prototype we have considered the possibility of separating the functionality from the visualization. However, we could also embed in the APIs a set of metadata for the visualization of the instructions and this will result in a more uniform adoption across possible domain languages.
• The end user programming language developed in this case study runs completely on the client side of the Web browser. By using JavaScript as the assembly language of the Web, the underlying compiler of the programming language compiles the visual language into the complete JavaScript application. Since JavaScript is an event-based programming language, the compiler is forced to map the visual programming language to an event-based language.
• In our case study, the provided visual language consists of methods that can be treated as events and be triggered upon calling them; hence it is straightforward to map this language to an event-based language. However, in case of need for other programming paradigms, such as functional programming or data-flow programming, the mapping to an event-based language is more complex.
• Server-side execution of end user developed applications creates a trade-off between flexibility and interactivity. Although server-side compilation and execution increases the flexibility on possible technologies and methods to be used for compilation and execution, it hampers interactivity during application execution, which is important in domains such as scientific simulations and games. A hybrid solution between client and server-side execution has to be chosen according to the domain.

In this paper we propose ULD, a Web-based architecture to separate the domain functionality from the programming language to support programming in the highly dynamic ecosystem of Web 2.0 communities. We devise a plugin architecture for an end user programming language to be used as a host language into which the functionality of multiple domains can be plugged. We apply our architecture in the context of smart devices. As a result, end users are provided with a visual programming environment to program different Lego Mindstorms devices. The visual programming interface is automatically generated from the device functionality and embedded into the programming environment. The adoption of the Web for end user programming opens new frontiers for collaborative developments. The developed case study will serve as a testbed where we will evaluate different collaborative end user programming tools and methods in order to assess the potential of end user programming in online social environments and understanding their challenges.

Full article available at the following link:

Supporting Domain-Specific Programming in Web 2.0: a Case Study of Smart Devices: https://doi.org/10.1109/ASWEC.2010.36

Read the paper at this link

Your help in sharing the idea is very welcome!

Cite this paper as:

N. Ahmadi, F. Lelli and M. Jazayeri Supporting Domain-Specific Programming in Web 2.0: a Case Study of Smart Devices, In proc of 21st Australian Software Engineering Conference (ASWEC), Auckland, New Zealand, April 2010

Related Article:

• The Many Faces of the Integration of Instruments and the Grid

Supporting #domain Specific #programming in #Web 2.0: a #casestudy of #Smart Devices ( #IoT ).
Share on X

• Full list of Articles
• Full list of Journal Publications
• Full list of Conference Publications

The post Supporting Domain-Specific Programming in Web 2.0: a Case Study of Smart Devices appeared first on Francesco Lelli.

Mentor: Francesco Lelli 

In the coming 10 years not only computers will be connected to the Internet but also small and heterogeneous devices will be part of the web too. These devices will support people in carrying their everyday life activities. This trends is known as Internet of Things.

Toward this idea in this project the candidate will design and implement a generic controller for an embedded device i.e he/she will produce Web APIs for Instruments and Devices. Moreover this control system should expose its APIs in the web in order to allow remote access to the resource. The device that will be targeted in this project is the Lego Mindstorm robot [1] and at the end of the project a working prototype is expected.

In the past year libraries and framework have been proposed for the control of the Lego chip. The purpose of this work is to evaluate the status of the art of these developments proposing new architecture and design guidelines. In addition the candidate will contribute to existing open source project in order to improve the present tools. 

The candidate will use: 

• A Lego Mindstorm [1]
• The Lejos [2] library in order to access and control of the robot using java APIs.
• The Instrument Element [3] tools for exposing Web Service APIs.
• Any tool that she knows for the realization of a user interface.

The candidate can choose any configuration of the robot that she prefer such as car, arm, walking robot etc. She also will choose the User Interface according to the selected configuration. 

In this video an example of prototype is presented: 
http://www.youtube.com/watch?v=I8VvTENzPGI 
This is just an example; the candidate is encouraged to propose a different prototype. 

Knowledge and Skills:

Web Programming, Java Programming and basic knowledge of Distribute Applications and Embedded Devices. 

References:

[1] Lego Mindstorm NXT: https://shop.lego.com/en-US/category/mindstorms
[2] Lejos Project: http://lejos.sourceforge.net/ 
[3] Instrument Element Project: http://instrumentelem.sourceforge.net/ 

The post Web APIs for Instruments and Devices appeared first on Francesco Lelli.

Mentor: Francesco Lelli 

Grid/ Cloud computing offers to their users a virtually unlimited computational infrastructure. Users usually interact with this system using a command line interface thus limiting its use to people that are familiar with computers. The goal of the thesis is to expose similar functionality using Web based APIs thus exposing Grid functionalities to a larger audience. 
The candidate will design and implement this APIs offering functionality like: (i) user authentication; (ii) job submission; (iii) data transfer; (iv) job monitoring and notification. Moreover it will validate the quality of his design choices implementing a Facebook or a WordPress plug-in. 

During this thesis the candidate will have the opportunity to contribute to existing open source projects in order to improve the present tools and enable them with interfaces for Web 2.0 APIs for Grid Computing

Knowledge and Skills:

Web Programming, Java Programming and basic knowledge of Distributed Systems. 

Where to know more:

Read this introduction about cloud computing and looks at the following references:

[1] GridComputing:http://en.wikipedia.org/wiki/Grid_computing
[2] REST: http://en.wikipedia.org/wiki/Representational_State_Transfer 
[3] Facebook APIs http://developers.facebook.com/ 
[4] WordPress plugin http://codex.wordpress.org/Writing_a_Plugin 

The post Web 2.0 APIs for Grid Computing: Thesis Proposal appeared first on Francesco Lelli.