Skip to toolbar

Community & Business Groups

Natural Language Interfaces for the Web of Data Community Group

The Natural Language Interfaces for the Web of Data Community Group aims at analyzing, modelling, unifying and enhancing natural language interfaces for the Web of Data. The core goal is to improve the reusability of systems and to increase their quality and performance. The group will develop diverse modules as well as an unified data vocabulary and ontology to foster a growing interface landscape. This includes question answering, information retrieval, keyword search, answer verbalisation and so on. Furthermore, the Natural-Language Interfaces for the Web of Data CG will incubate a wide and collaborative environment for researchers, industrials and practitioners. We hope, that research as well as industry projects will support and benefit of this community group’s activity.

Note: Community Groups are proposed and run by the community. Although W3C hosts these conversations, the groups do not necessarily represent the views of the W3C Membership or staff.

No Reports Yet Published

Learn more about publishing.

Chairs, when logged in, may publish draft and final reports. Please see report requirements.

Publish Reports

Call for Systems QALD2017 CHALLENGE @ ESWC 2017

ESWC 2017, May 28th, 2016 to June 1st, 2017 Portoroz, Slovenia.
https://project-hobbit.eu/challenges/qald2017/

The key challenge for Question Answering over Linked Data is to translate a user’s information need into a form such that it can be evaluated using standard Semantic Web query processing and inferencing techniques.

The main task of QALD therefore is the following: Given one or several RDF dataset(s) as well as additional knowledge sources and natural language questions or keywords, return the correct answers or a SPARQL query that retrieves these answers.

In order to focus on specific aspects and challenges, we propose the following three tasks:

Task 1: Multilingual question answering over DBpedia
Task 2: Hybrid question answering
Task 3: Large-Scale question answering over RDF
Task 4: Wikidata-based question answering

Submission

The QALD challenge provides an automatic evaluation tool (GERBIL QA integrated into the HOBBIT platform) that is open source and available for everyone to re-use. This tool is accessible online, so that participants can simply upload the answers produced by their system or even check their system via a web service.

Each experiment will have a citable, time-stable and archivable URI which is both human- and machine-readable. It is mandatory for each system to provide an endpoint URL wrapped inside a provided Docker container after the submission in order to be evaluated with GERBIL QA.

We are accepting papers (up to 5 pages) describing the submitted approach and evaluation results. Submissions must be in English and in PDF, formatted in the style of the Springer Publications format for Lecture Notes in Computer Science (LNCS).

Papers should be submitted through the EasyChair system (https://easychair.org/conferences/?conf=qald2017) no later than midnight Friday March 10th, 2017, Hawaii Time. Submissions will be reviewed by members of the challenge program committee. Papers will be evaluated according to their significance, originality, technical content, style, clarity, and relevance to the challenge. The complete set of papers will be published with the CEUR Workshop Proceedings (CEUR-WS.org), listed by the DBLP.

For any questions, please write an email to Ricardo Usbeck (usbeck AT informatik.uni-leipzig.de).

Preliminary Schedule

Release of training data and instructions: Friday January 13th, 2017
Release of test dataset: Friday April 7th, 2017
Paper submission deadline: Friday March 10th, 2017
Challenge paper reviews: Tuesday April 5th, 2017
Paper Notifications and invitation to task: Friday April 7th, 2017
Camera ready papers (5 pages document): Sunday April 23rd, 2017
Submission of camera-ready papers: April 24, 2014

First online meeting – Tuesday, October 4th, 1pm (GMT+2 , Berlin time zone)

Dear all,

according to the doodle poll we will have our first telco on Tuesday, October 4th, 1pm (GMT+2 , Berlin time zone).

Please use the following gotomeeting link: https://global.gotomeeting.com/join/727443869 . Notes can be taken here: https://pad.okfn.org/p/W3C_CG_NLIWOD_-_First_telco

Topics include but can be extended:

  • Should we adapt the charter in terms of goals, meeting times?
  • Which efforts will be done towards the first milestones? Who wants to participate?
    • Milestone 1 (Q4/2016)
      • Draft for a first test suite including various datasets as well as benchmark queries
      • Draft for a first specification of benchmarking methods
      • Collection of existing interfaces for NLI systems on the Web
    • Milestone 2 (Q2/2017)
      • Requirements for NLI Benchmarks
      • First test suite including various datasets as well as benchmark queries
      • First specification of benchmarking methods
      • Draft for best practices for publishing natural language interfaces (and modules) on the web which unifies different approaches

Best regards,

Ricardo

Recap on the first face-to-face meeting @SEMANTiCS 2016

The goal of this meeting was to discuss the charter and first milestone of the W3C community group for Natural Language Interfaces on the Web of Data. Around 20 people joined and presented their systems, requirements towards test, benchmarks, data and APIs as well as brainstormed about reusability of existing approaches. 

You can find all talks and links including the protocol of the discussion here [1].

[1] https://docs.google.com/document/d/12ElVLD2NXEAOpVE52aguRwKc9Cx96YFfMWZCyEwo1nU 

TL;DR

Join the group! And help decide about the time and date of our monthly telcos by taking part in the doodle poll [2].

[2] http://doodle.com/poll/6qcvgncrwwc2zpvd 

Open Knowledge Base and Question Answering Workshop at COLING

The main goal of this workshop is to join forces in the collaborative development of open frameworks for knowledge extraction and question answering, to share standards, and to foster the creation of an ecosystem of tools and benchmarks. The workshop will therefore not only comprise short and long paper presentations but also a hands-on session on already existing frameworks, standards, and benchmarking campaigns, as well as a social meet-up.

Continue reading

Call for Contributions – Natural Language Interfaces for the Web of Data

Dear all!

We would like to invite contributions related to this meeting:

  • Presentations and demonstrations of state-of-the-art systems, communication protocols, benchmark datasets
  • Position presentations about the future development of NLI
  • Ideas sparking discussion all around this group.

This meet-up should serve as an open discussion ground for the future scope of the W3C Community group. A protocol of the meeting with links to resources will be published in this blog.

The first face-to-face meeting will take place in Leipzig on Monday, September 12, 2016 – 13:30 to 17:00.

All tutorials and workshops at the SEMANTiCS conference are free of charge.

More information can be found here: http://2016.semantics.cc/satellite-events/w3c-community-group-natural-language-interfaces-web-data 

 

All the best,

Ricardo

Charter for the NLIWoD Community Group

Natural Language Interfaces for the Web of Data (NLIWoD) Community Group Charter (V1.0.0)

The mission of the NLIWoD Community Group is to provide standards to analyze, model, unify, test, benchmark and enhance natural language interfaces for the Web of Data. The core goal is to improve the reusability of systems as well as benchmark datasets and to increase as well as measure their quality and performance in an effective and efficient way.

The group will develop at developing modules, benchmarks and test standards as well as unified data vocabularies and ontologies to foster a growing interface landscape. Topics relevant to the community group include all topics related to question answering, information retrieval, keyword search, answer verbalisation.

Furthermore, the NLIWoD CG will incubate a wide and collaborative environment for researchers, companies and practitioners. The group hopes that research as well as industry projects will support and benefit from this community group’s activity.

Join the NLIWoD Working Group.

  • Start date : 17th November 2015
  • End date : Unlimited
  • Chairs : Ricardo Usbeck
  • Public mailing list

Meeting Schedule

  • Teleconferences: bi-monthly telcos to align work
  • Face-to-face: TBA; additional face-to-face meetings may be scheduled by consent of the participants, no more than 3 ordinary per year.

Scope

The scope of this CG is threefold:

  1. It seeks consensus for best practices pertaining to the publication of natural language interfaces in the Web of Data.
  2. The CG will collaborate to enhance testing and benchmarking environments for natural language interfaces for the Web of Data.
  3. The core goal is to improve the reusability as well as quality and efficieny of NLIWoD systems by introducing best practices.

Out of Scope

The following features are out of scope, and will not be addressed by this working group.

  • The CG will not develop new NLIWoD systems.

Criteria towards Recommendation Proposals

In order to advance to Proposed Recommendation, each specification is expected to have at least two independent implementations of each of feature defined in the specification.

Each specification should contain a section detailing any known security or privacy implications for implementers, Web authors, and end users.

Deliverables

More detailed milestones and updated publication schedules are available on the group publication status page.

  • Milestone 1 (Q4/2016)
    • Draft for a first test suite including various datasets as well as benchmark queries
    • Draft for a first specification of benchmarking methods
    • Collection of existing interfaces for NLI systems on the Web
  • Milestone 2 (Q2/2017)
    • Requirements for NLI Benchmarks
    • First test suite including various datasets as well as benchmark queries
    • First specification of benchmarking methods
    • Draft for best practices for publishing natural language interfaces (and modules) on the web which unifies different approaches
  • Milestone 3 (Q4/2017)
    • Best practices for publishing natural language interfaces (and modules) on the web to tackle heterogeneous machine-interfaces
    • Second test suite extending datasets and benchmark queries
    • Improved specification of benchmarking methods

Coordination

The elicitation will follow the group discussions (telcos) and external input from research projects as well as industry statements.

External Organizations and Projects

External organizations can enhance the work of this CG by providing input via the mailing list, participation in telcos and face-to-face meetings. They are also invited to join the CG directly.

Organizations

Projects

Mailinglists

  • Question Answering Interest Group qaig@googlegroups.com, founded in 2014 to accomplish a unification of German QA research

Participation

The group encourages questions, comments and issues on its public mailing lists and document repositories, as described in Communication.

The group also welcomes non-Members to contribute technical submissions for consideration, with the agreement from each participant to Royalty-Free licensing of those submissions under the W3C Patent Policy.

Communication

Meeting minutes from teleconference and face-to-face meetings will be archived for public review, and technical discussions and issue tracking will be conducted in a manner that can be both read and written to by the general public. Working Drafts and Editor’s Drafts of specifications will be developed on a public repository, and may permit direct public contribution requests.

Information about the group (including details about deliverables, issues, actions, status, participants, and meetings) will be available from the NLIWoD Community Group home page.

Most NLIWoD Community Group teleconferences will focus on discussion of particular specifications, and will be conducted on an as-needed basis.

This group primarily conducts its technical work on the public mailing list public-nli@w3.org (archive). The public is invited to post messages to this list.

The group may use a Member-confidential mailing list for administrative purposes and, at the discretion of the Chairs and members of the group, for member-only discussions in special cases when a participant requests such a discussion.

Decision Policy

This group will seek to make decisions through consensus and due process, per the W3C Process Document (section 3.3). Typically, an editor or other participant makes an initial proposal, which is then refined in discussion with members of the group and other reviewers, and consensus emerges with little formal voting being required.

However, if a decision is necessary for timely progress, but consensus is not achieved after careful consideration of the range of views presented, the Chairs may call for a group vote, and record a decision along with any objections.

To afford asynchronous decisions and organizational deliberation, any resolution (including publication decisions) taken in a face-to-face meeting or teleconference will be considered provisional. A call for consensus (CfC) will be issued for all resolutions (for example, via email and/or web-based survey), with a response period from one week to 10 working days, depending on the chair’s evaluation of the group consensus on the issue. If no objections are raised on the mailing list by the end of the response period, the resolution will be considered to have consensus as a resolution of the Working Group.

All decisions made by the group should be considered resolved unless and until new information becomes available, or unless reopened at the discretion of the Chairs or the Director.

This charter is written in accordance with the W3C Process Document (Section 3.4, Votes), and includes no voting procedures beyond what the Process Document requires.

Patent Policy

This Community Group operates under the W3C Patent Policy (5 February 2004 Version). To promote the widest adoption of Web standards, the group seeks to issue Recommendations that can be implemented, according to this policy, on a Royalty-Free basis. For more information about disclosure obligations for this group, please see the W3C Patent Policy Implementation.

Licensing

This Community Group will use the W3C Software and Document license for all its deliverables.

About this Charter

This charter has been created according to section 5.2 of the Process Document. In the event of a conflict between this document or the provisions of any charter and the W3C Process, the W3C Process shall take precedence.

First Face-to-Face Meeting of the Natural Language Interfaces CG

Hi all!

It is a pleasure to announce the first face-to-face meeting of the Natural Language Interfaces for the Web of Data.

This meeting will take place in Leipzig on Monday, September 12, 2016 – 13:30 to 17:00.

More information can be found here: http://2016.semantics.cc/satellite-events/w3c-community-group-natural-language-interfaces-web-data

I am looking forward to meet you there!

Ricardo

Call for Participation in Natural Language Interfaces for the Web of Data Community Group

The Natural Language Interfaces for the Web of Data Community Group has been launched:


The Natural Language Interfaces for the Web of Data Community Group aims at analyzing, modelling, unifying and enhancing natural language interfaces for the Web of Data. The core goal is to improve the reusability of systems and to increase their quality and performance. The group will develop diverse modules as well as an unified data vocabulary and ontology to foster a growing interface landscape. This includes question answering, information retrieval, keyword search, answer verbalisation and so on. Furthermore, the Natural-Language Interfaces for the Web of Data CG will incubate a wide and collaborative environment for researchers, industrials and practitioners. We hope, that research as well as industry projects will support and benefit of this community group’s activity.


In order to join the group, you will need a W3C account. Please note, however, that W3C Membership is not required to join a Community Group.

This is a community initiative. This group was originally proposed on 2015-11-16 by Ricardo Usbeck. The following people supported its creation: Ricardo Usbeck, Martin Voigt, Elena Cabrio, Christina Unger, Sebastian Walter, Liubov Kovriguina. W3C’s hosting of this group does not imply endorsement of the activities.

The group must now choose a chair. Read more about how to get started in a new group and good practice for running a group.

We invite you to share news of this new group in social media and other channels.

If you believe that there is an issue with this group that requires the attention of the W3C staff, please email us at site-comments@w3.org

Thank you,
W3C Community Development Team