[Dbpedia-gsoc] Introduction

[Kunal Jha]

Hello everyone,

I would like to re-introduce myself. My name is Kunal. I am a masters
student in University of Bonn in CS. I had worked on the Lookup project for
GSoC 2016. I had a great experience with DBpedia last year and I would love
to participate  for GSoC 2017 and continue working for DBpedia.

I have been working in AKSW for more than a year now and I have been
researching and developing tools (full stack development)  in the filed of
resource and property ranking and benchmarking of NER and EL tools during
this course.  I believe I have good hand in Java ( more than 4 years
experience), Scala (more than 2 years of experience). I am relatively new
in python and have around 5 months of working experience in the same.

I am interested in working on the project of Holistic Ranking of Dbpedia
Resources
.
I have also played around with autoindex tool and am done with all the
warmup task.

I would really appreciate if anyone can direct me how can I proceed with
the project and proposal or if anything else is required from me.

Hope to work with Dbpedia again !!

Best Regards
Kunal Jha
--
Announcing the Oxford Dictionaries API! The API offers world-renowned
dictionary content that is easy and intuitive to access. Sign up for an
account today to start using our lexical data to power your apps and
projects. Get started today and enter our developer competition.
http://sdm.link/oxford___
Dbpedia-gsoc mailing list
Dbpedia-gsoc@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/dbpedia-gsoc

[Dbpedia-gsoc] Introduction

[Felix Conrads]

Hey ho,


I am Felix, a C.S. Student living in Berlin.
I recently finished my B.Sc. in Leipzig and starting my Master in April at
the FU Berlin. I am very much interested into the "Question Answering from
DBpedia to the whole LOD cloud" Topic.

I worked for almost 3 years at the AKSW and using DBpedia from the first
day on. I programmed the successor of the DBpedia SPARQL Benchmark (can be
found here: https://github.com/AKSW/IGUANA).
I started working on Gerbil and Gerbil QA, (as well as done some small
parts in NLIWOD) the last year.
Right now I am doing a SPARQL evaluation of Social Network graphs in
Triplestores with two of the Openlink SW guys.
I like to think that i have an understanding of NLP, QA, and DBpedia
(SPARQL in general).
As i am working now for 4 years with Java, i am high experienced in it.

If you have any further questions, just ask :)

Oh my warmup Task:
- Well i did start without any Problems and played a little bit around with
it.
- As there are not that many Open Source SRS (and like everyone had the
same) i simply share with you a paper i found over an interesting
evaluation of them (they used a few of the known open source srs and two
well known datasets) http://suendermann.com/su/pdf/oasis2014.pdf


If you could add me to the Slack channel that would be awesome :)

Best,
Felix
--
Announcing the Oxford Dictionaries API! The API offers world-renowned
dictionary content that is easy and intuitive to access. Sign up for an
account today to start using our lexical data to power your apps and
projects. Get started today and enter our developer competition.
http://sdm.link/oxford___
Dbpedia-gsoc mailing list
Dbpedia-gsoc@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/dbpedia-gsoc

Re: [Dbpedia-gsoc] Query regarding List_Extractor

[Krishanu Konar]

Hi,

I'll try to see if I can somehow include the JSONpedia framework in the
existing code, as it could indeed solve many problems.
Thanks!

Regards,
Krishanu

On Mon, Mar 6, 2017 at 7:09 AM, Marco Fossati  wrote:

> Hi guys,
>
> On 3/5/17 12:08, Federica Baiocchi wrote:
>
>> He told me that he was planning to implement an automatic restart sooner
>> or later
>>
> I fear he would have never done that, so I've just fixed it.
> The service now is scheduled to restart once a month.
> Please use it for low-traffic requests however.
>
>> look for a way to include the JSONpedia framework in the code to
>> use it offline.
>>
> Absolutely yes, it would be a much more efficient solution.
>
>> I did try to do it at first, but I encountered many
>> obstacles and compatibility problems with Python and Java and wasted a
>> lot of time.
>>
> Did you try with Jython with no success?
> Or maybe we should translate the current code from Python to Java.
> We could give a try with something like this:
> https://github.com/chrishumphreys/p2j
>
> What do you think?
> Best,
>
> Marco
>
--
Announcing the Oxford Dictionaries API! The API offers world-renowned
dictionary content that is easy and intuitive to access. Sign up for an
account today to start using our lexical data to power your apps and
projects. Get started today and enter our developer competition.
http://sdm.link/oxford___
Dbpedia-gsoc mailing list
Dbpedia-gsoc@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/dbpedia-gsoc

Re: [Dbpedia-gsoc] Introduction and question regarding chatbot

[Ricardo Usbeck]

Dear Daniel, all, 

first of all, thanks for interest in that topic.

1) You totally nailed. Additionally, the chat bot should keep track so we can 
answer questions based on the user’s history, e.g.. “When was Barack Obama 
born?” => “Does he have kids?” and resolve he to Barack Obama. 

2) For this GSoC project something more close to ELIZA than to neural nets is 
preferred since neural nets are not easy to control and overwatch. The dialogue 
benchmark is one option to learn the grammar for something ELIZA-like. 

Best regards
Ricardo 
> On 6 Mar 2017, at 14:53, Daniel Obraczka  wrote:
> 
> Hello,
> 
> I'm a Computer Science student living in Leipzig currently pursuing my 
> master degree. I'm very interested to work on the chatbot idea. My first 
> warmup task can be found here: 
> https://github.com/dobraczka/DBpedia_chatbot_warmup
> For the second task I wrote a Telegram bot utilizing openQA: 
> https://github.com/dobraczka/OpenQABot
> 
> I also have two questions regarding the DBpedia Chatbot idea:
> 
> 1) The chatbot should build on existing QA systems. Do I understand it 
> correctly, that the role of the chatbot should be on the one hand to 
> give responses where the user is not explicitly asking a question (in 
> which case the QA system cannot be used) and on the other hand ask the 
> user to provide more information if the question is incomplete/ambiguous ?
> 
> 2) The third warm-up task encourages the candidates to read about 
> grammar-based chatbots. Therefore I would assume the aim is to build a 
> closed domain chatbot (similar to e.g. ELIZA), rather than e.g. using 
> neural networks. Is this correct? Or should the dialogue benchmark 
> (mentioned in the project description) be used to train the bot 
> similarly to how e.g. the Ubuntu Corpus[1] was used to train machine 
> learning algorithms?
> 
> Best Regards,
> 
> Daniel Obraczka
> 
> [1] R. Lowe et al.,  The Ubuntu Dialogue Corpus: A Large Dataset for 
> Research in Unstructured Multi-Turn Dialogue Systems, 2015 
> https://arxiv.org/pdf/1506.08909.pdf
> 
> --
> Check out the vibrant tech community on one of the world's most
> engaging tech sites, SlashDot.org! http://sdm.link/slashdot
> ___
> Dbpedia-gsoc mailing list
> Dbpedia-gsoc@lists.sourceforge.net
> https://lists.sourceforge.net/lists/listinfo/dbpedia-gsoc

-- 
Ricardo Usbeck, M.Sc.
Augustusplatz 10
Room P905
04109 Leipzig

http://aksw.org/RicardoUsbeck

--
Announcing the Oxford Dictionaries API! The API offers world-renowned
dictionary content that is easy and intuitive to access. Sign up for an
account today to start using our lexical data to power your apps and
projects. Get started today and enter our developer competition.
http://sdm.link/oxford___
Dbpedia-gsoc mailing list
Dbpedia-gsoc@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/dbpedia-gsoc