News & Events

2015

22 May 2015 - Release 1.2.3 of the EXCITEMENT Open Platform (EOP) is available at the following URL:

http://hltfbk.github.io/Excitement-Open-Platform/

The EOP is a generic multi-lingual platform for textual inference made available to the scientific and technological communities.

Major changes of release 1.2.3 compared to the previous release 1.2.1

New Features:

  • Scorer for multi-class classification problems
  • EDAs configuration files for Bulgarian.

Bug Fixes:

  • Some dependencies in the AdArte module were wrong.

10 March 2015 - The workshop on "Deep and Large-Scale Semantic Processing: The Way Ahead" will take place in FBK (Trento, Italy). This is an opportunity to discuss some of the major trends in Semantic Processing of Natural Language, with a specific focus on balancing the need of a deep analysis with the need to process big-data.

The workshop is a follow-up of two recent international initiatives: a "Shonan meeting", organized in Japan in November 2014, on "Towards Explanation Production Combining Natural Language Processing and Logical Reasoning” (http://shonan.nii.ac.jp/seminar/057/), and the EXCITEMENT EU project (https://sites.google.com/site/excitementproject/) on textual inferences, just concluded.

The program of the workshop includes invited seminars given by experts of Universities and Research Centers in Japan (NAIST, Tohoku, NII, JAIST), and Europe (Stuttgart, DFKI, University of Basque Country, FBK).

16 February 2015 - Release 1.2.1 of the EXCITEMENT Open Platform (EOP) is available at the following URL:

http://hltfbk.github.io/Excitement-Open-Platform/

The EOP is a generic multi-lingual platform for textual inference made available to the scientific and technological communities.

Major changes of release 1.2.1 compared to the previous release 1.2.0.

New features:

  • AdArte EDA (A Transformation-Driven Approach for Recognizing Textual Entailment) has been developed by FBK and is based on modelling entailment relations as a classification problem where the single T-H pairs are first represented by a sequence of edit operations (i.e., deleting, replacing and inserting pieces of text) called transformations needed to transform T into H, and then used as features to feed up a supervised learning classifier to classify the pairs as positive or negative examples.
  • Installation script for installing the EOP and also TreeTagger after you read and agree to its licence.

Bug fixes:

  • Wrong Italian part-of-speech mapping.
  • Script for installing TreeTagger.

Known bugs and limitations:

  • Scorer for evaluating binary-class classification problems only.

New available annotated data sets for the EOP

    • The EXCITEMENT data sets (Kotlerman et al, forthcoming) contain negative feedbacks from customers where they state reasons for dissatisfaction with a given company. The data sets are available for English and Italian. For each language, the release is composed of 4 data sets, structured along the two orthogonal dimensions of balanced-unbalanced and mixed-pure. Balanced-unbalanced refers to the fact that the data set contains a comparable number of positive and negative examples (balanced) or not (unbalanced), while mixed-pure regards the possibility to have the T-H pairs of a specific topic equally distributed between training and test set (mixed) or only in train or in test (i.e., pure).
  • RTE-3 for Bulgarian language (thanks to Iliana Simova)
  • SICK (Marelli et al, 2014) is the data set that was used at SemEval-2014 for the two subtasks of (i) Relatedness (i.e., predicting the degree of semantic similarity between two sentences), and (ii) Entailment (i.e., detecting the entailment relation holding between two sentences).

14 January 2015 - The Semantic Text Processing Symposium - Industrial Outlook was held at Bar-Ilan University in November 2014. The symposium included a broad range of talks about industrial activities and directions in this area, and several industry-related academic presentations.

The presentations and the videos of most of the talks are now available at the symposium's webpage: http://u.cs.biu.ac.il/~nlp/workshop14/program.html

An overview article about the symposium was published in the scientific section of the NRG online newspaper (the internet version of Maariv, in Hebrew): http://www.nrg.co.il/online/1/ART2/649/593.html

2014

24 December 2014 - Release 1.2.0 of the EXCITEMENT Open Platform (EOP) is available at the following URL:

http://hltfbk.github.io/Excitement-Open-Platform/

The EOP is a generic multi-lingual platform for textual inference made available to the scientific and technological communities.

Major changes of release 1.2.0 compared to the previous release 1.1.4:

  • P1EDA (alignment-based EDA) – this EDA tries to align T with H, according to different aspects of their representation: lexical, syntactic, etc. It eventually classifies whether or not T entails H by considering the plausibility of those alignments.
  • LAP for the Bulgarian language.

November 18-19, 2014 - The Symposium on Semantic Text Processing - Industrial Outlook will take place at Bar Ilan University.

The symposium is focused on an outlook towards the fast growing industrial activity in this area and it is organized by the EU-funded project EXCITEMENT (https://sites.google.com/site/excitementproject/).

More details can be found on the symposium web site.

17 October 2014 - Release 1.1.4 of the EXCITEMENT Open Platform (EOP) is available at the following URL:

http://hltfbk.github.io/Excitement-Open-Platform/

The EOP is a generic multi-lingual platform for textual inference made available to the scientific and technological communities.

Major changes of release 1.1.4 compared to the previous release 1.1.3:

  • New Features
    • MaltParser for Italian
  • Bug Fixes
    • English MaltParser pipeline made wrong results due to POS tag mismatch
    • Italian TreeTargger missed "canonical" POS tag
    • Util submodule used a wrong version of LAP

19 June 2014 - Release 1.1.3 of the EXCITEMENT Open Platform (EOP) is available at the following URL:

http://hltfbk.github.io/Excitement-Open-Platform/

The EOP is a generic multi-lingual platform for textual inference made available to the scientific and technological communities.

Major changes of release 1.1.3 compared to the previous release 1.1.2:

  • BIUTEE
      • tracer: support for researchers is provided by a visual tracing tool which visualizes every step of the inference.
      • pre-trained models
  • EDITS
    • different strategies for stop word removal
  • EOPRunner(i.e. EOP via command line interface)
    • better separation between processing steps: preprocessing,training,testing, scoring can each be done separately.
  • EOP wiki documentation:
    • Quick Start and Step by Step tutorial revised

The EXCITEMENT project will be present at the HLT Projects Village which will be held during LREC 2014, 26-31 May 2014, Reykjavik, Iceland.

In particular, the EXCITEMENT booth will present the EXCITEMENT Open Platform (EOP) .

26 March 2014 - Release 1.1.2 of the EXCITEMENT Open Platform (EOP) is available at the following URL:

http://hltfbk.github.io/Excitement-Open-Platform/

The EOP is a generic multi-lingual platform for textual inference made available to the scientific and technological communities.

The major changes of release 1.1.2 compared to the previous release 1.1.1 concern BIUTEE EDA that now is provided with a new command-line interface (for Linux) available through the BIUTEE environment. Then, the new release fix the EOP v1.1.1 issue about "Wrong version of artifact included" that could cause some strange errors when one uses EOP as a library from their own code.

2013

3 December 2013 - Bernardo Magnini gave an invited talk at the 2nd Workshop on Argumentation in Artificial Intelligence and Philosophy: computational and philosophical perspectives (ARGAIP 2013), Turin (Italy). The title of the talk was ``Semantic Inferences in Natural Language Processing''.

November 20-22, 2013 - The Joint Symposium on Semantic Processing (JSSP 2013) will take place at FBK in Trento (Italy). The Symposium is an event jointly organized by the EU-funded project EXCITEMENT (https://sites.google.com/site/excitementproject/) and by the B-CROCE project and it is endorsed by ACL SIGLEX and ACL SIGSEM. It aims at providing a stimulating and intriguing forum for mutual update and discussion of current research directions in semantic processing. To this end, it will accommodate a large number of keynote presentations by leading researchers in the field of semantic processing (among them Eneko Agirre, Johan Bos, Philipp Cimiano, Peter Clark, Mona Diab, Patrick Hanks, Mirella Lapata, Dan Roth, Sabine Schulte im Walde).

Further details can be found on the symposium web site: http://jssp2013.fbk.eu.

September 19-20, 2013 - DFKI and OMQ present the EXCITEMENT project at META-FORUM 2013 — Connecting Europe for New Horizons. META-FORUM is an international conference on powerful language technologies for the multilingual information society, the data value chain and the information market place.

This year's edition of the conference took place at the German Federal Ministry of Economics and Technology located in Berlin. Keynotes were presented by Daniel Marcu, Chief Science Officer at SDL, USA, and Wolfgang Wahlster, Chief Executive Office at DFKI, Germany. Talks were also given by members of the European Commission and stakeholders from language technology research and industry.

The EXCITEMENT project was presented as part of the META Exhibition, along with 27 other poster presentations and software demonstrations.

September 2-6, 2013 - A poster on the EXCITEMENT project was presented at MT Summit, which took place in Nice, France at the ACROPOLIS conference centre.

September 2013 - A course proposal on Textual Entailment at ESSLLI 2014 was accepted. The course will be delivered in August 2014 in Tübingen, Germany.

17 September 2013 - The following article has been accepted for publication on the Journal of Natural Language Engineering:

S. Pado, T.-G. Noh, A. Stern, R. Wang, R. Zanoli: Design and Realization of a Modular Architecture for Textual Entailment. Journal of Natural Language Engineering.

6 September 2013 - At the beginning of September, the final Call for papers of the Joint Symposium on Semantic Processing has been circulated. The symposium will take place in Trento in November 2013. The deadline for submitting papers is September 15, 2013. More details can be found on the symposium web site: http://jssp2013.fbk.eu.

14 August 2013 - The first public release of the EXCITEMENT Open Platform (EOP) is available at the following URL:

http://hltfbk.github.io/Excitement-Open-Platform/

The EOP is a generic multi-lingual platform for textual inference made available to the scientific and technological communities.

The EOP documentation is available here.

Please note that the current release is still preliminary (something in between an alpha and a beta release), particularly for what concerns the documentation. We are working hard to increase the usability of the platform improving the quality of the documentation.

The following book has been published by Morgan & Claypool:

Ido Dagan, Dan Roth, Mark Sammons, and Fabio Massimo Zanzotto

Recognizing Textual Entailment: Models and Applications.

Morgan & Claypool Publishers, July 2013.

July 2013 - At the end of June, the preliminary Call for papers of the Joint Symposium on Semantic Processing was circulated. The symposium will take place in Trento in November 2013. More details can be found on the symposium web site: http://jssp2013.fbk.eu.

18 April 2013 - The following paper has been accepted at the 2013 Conference of the Association for Computational Linguistics (ACL 2013), which will be held in August 2013 in Sofia, Bulgaria:

B. Zeller and J. Šnajder and S. Pado. DErivBase: Inducing and Evaluating a Derivational Morphology Resource for German.

March 2013 - The date of the tutorial on Textual Entailment at AAAI 2013 is now official. The tutorial will take place on Sunday, July 14 2013 from 2 PM to 6 PM in Bellevue, Washington, USA.

14 February 2013

EXCITEMENT Review Meeting, Saarbruecken

First Year Review Meeting at DFKI.

13 February 2013 - The following paper has been accepted at the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL 2013), which will be held in June 2013 in Atlanta, USA:

Amnon Lotan, Asher Stern, Ido Dagan. TruthTeller: Annotating Predicate Truth.

January 2013

Moshe Wasserblat was appointed as chairman of the Speech-Analytics workgroup in the Speech Processing Conference , 2-3 July 2013.

The focus of this workgroup will be on existing and potential future applications of speech analytics technologies; the challenges involved in speech analytics; how speech analytics can enhance customer service; new technological advances currently being implemented among them Textual Entailment platform; and a wish list for future capabilities.

January 2013 - The following paper has been accepted at the 10th International Conference on Computational Semantics (IWCS 2013), which will be held in March 2013 in Potsdam, Germany:

B. Zeller and S. Pado. A Textual Entailment Dataset from German Web Forum Text.

2012

December 2012 - A tutorial proposal on Textual Entailment at AAAI 2013 was accepted. The tutorial will be delivered in July 2013 in Bellevue, Washington, USA.

7-8 November 2012

EXCITEMENT Meeting, Rome

Consortium meeting at AlmavivA offices.

5 October 2012 - Bernardo Magnini gave a talk at isa-8 (the Eighth Joint ACL - ISO Workshop on Interoperable Semantic Annotation), talking about the EXCITEMENT project protocols.

5 September 2012 - Ido Dagan gave an invited talk at SEPLN 2012 (the Spanish NLP conference), talking about Textual Entailment in general and also specifically about the EXCITEMENT project.

July 2012 - Rui Wang gave a 6-hour course/tutorial on Textual Entailment with a focus on

EXCITEMENT at the 2012 HIT-MSRA Summer School on Human Language Technology.

22 June 2012 - NICE actively participated in the LT-Innovate Summit and META-Forum Language Technology events in Brussels.

NICE Analytics and EXCITEMENT presentation, as presented by Moshe in the LT-Innovate Summit conference, won an excellent award for innovation, collaboration and market potential.

See more details in http://www.lt-innovate.eu/.

20 June 2012 - Presentation of the EXCITEMENT project at AVIOS 2012

(the video of the presentation will be available soon)

Attachments:

9-10 May 2012

EXCITEMENT Meeting, Heidelberg

Consortium meeting at the University of Heidelberg.

CORDIS: EXCITEMENT - EXploring Customer Interactions through Textual EntailMENT

287923 – STREP

EXCITEMENT KickOff , Israel - Feb 7-9, 2012

[Slides of the presentation at AVIOS 2012]

1442 kB