About  the EXCITEMENT project 

There are two interleaved high-level goals for this project. The first is to set up, for the first time, a generic architecture and a comprehensive implementation for a multilingual textual inference platform and to make it available to the scientific and technological communities.

The second goal of the project is to develop a new generation of inference-based industrial text exploration applications for customer interactions, which will enable businesses to better analyze and make sense of their diverse and often unpredicted client content. These goals will be achieved for three languages – English, German and Italian, and for three customer interaction channels – speech (transcriptions), email and social media.

   

 

  • 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
     
     
  • 2015

     
  • 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.
     
  • 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
     

Additional information