Sensicon is a sensorial lexicon that associates English words with senses: Sight, Hearing, Taste, Smell, Touch. This resource assigns five sensorial values to each lemma-part of speech tuple. Sensicon is created as the results of the studies [1] and [2].

DPC Sensorial Lexicon

An additional sensorial lexicon is created as a part of the study in [3]. This resource contains a sensorial lexicon that assigns five sensorial values (sight, hearing, taste, smell, and touch) to noun and adjective lemmas. The sensorial values are extracted from a corpus of dependency-parsed sentences by using the hypothesis that nouns frequently acting as a direct object of a verb representing a human sense are highly associated to that sense. The associations for adjectives are obtained in a similar vein by using the adjective complement syntactic relations.

While Sensicon yields indirect sensorial associations by modeling distributional properties of the lexicon, DPC attempts to directly model these associations independently of the context.

How To Use

Each line in the lexicon has the following format: "lemma__POS<tab>sightAssociation<tab>hearingAssociation<tab>tasteAssociation <tab>smellAssociation<tab>touchAssociation" . The columns are tab separated. The first column in the lexicon file consists of a lemma and its part of speech(POS) tag with the format "LEMMA__POS".

The rest of the columns denote the sensorial associations Sight, Hearing, Taste, Smell, Touch, respectively. Each sensorial association is a float value in the range of -1 and 1.

Refer to our publications below for more details.

How to obtain it

SENSICON and DPC Sensorial Lexicon are freely available for research purposes.

Whenever making reference to the lexicons, please cite the papers in the reference section as follows:

1. Sensicon: [1]

2. DPC Sensorial Lexicon: [3]

A research licence is granted through the following online form to scholars working for academic and research institutions. Please give us clear evidence about your affiliation (for instance the e-mail account and home-page).

If you are an undergraduate or master student the licence should be submitted by a professor of your University.

Agreement terms:

LICENCE AGREEMENT

FONDAZIONE BRUNO KESSLER (FBK)

SENSICON (Lexicon)

1) Grant:

The Fondazione Bruno Kessler (FBK) hereby grants to you a non-exclusive, non-transferable, perpetual, royalty-free and worldwide license (the “License”) to use Sensicon (the “Lexicon”) solely for educational and research purposes, in accordance with Paragraph 2 below and subject to the terms and conditions of this License Agreement (the “Agreement”).

2) Limitations on Use:

The License is limited to non-commercial use. Non-commercial use relates only to educational and research purposes. Any other use is commercial

use. You may not use the Lexicon in connection with any business activities. You may distribute and/or allow others to use a) the Lexicon or b) the applications you create with the Lexicon only if each new user is bound by the provisions of this Agreement.

3) Copies:

You may copy FBK material only as reasonably necessary for your licensed use.

4) Ownership:

The Lexicon and the accompanying documentation are licensed, not sold, to you. The Lexicon is a proprietary product of FBK. FBK retains all rights not specifically granted to you hereunder, including ownership of the Lexicon and all copyrights, trade secrets, or other intellectual property rights in the Lexicon and any accompanying information.

5) Publication Credit:

You agree to acknowledge FBK (“FBK”, Fondazione Bruno Kessler) with appropriate citations in any publication or presentation containing research results obtained in whole or in part through the use of the Lexicon. The following publications have to be cited:

Sensicon: An Automatically Constructed Sensorial Lexicon, Serra Sinem Tekiroğlu, Gözde Özbal, Carlo Strapparava. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 1511–1521, Doha, Qatar, October. Association for Computational Linguistics.

A Computational Approach to Generate a Sensorial Lexicon, Serra Sinem Tekiroğlu, Gözde Özbal and Carlo Strapparava. In Proceedings of the COLING 2014 Workshop on Cognitive Aspects of the Lexicon (CogALex), August 2014, Dublin, Ireland.

Exploring Sensorial Features for Metaphor Identification, Serra Sinem Tekiroğlu, Gözde Özbal, and Carlo Strapparava. In Proceedings of the NAACL HLT 2015 (2015) on The Third Workshop on Metaphor in NLP: 31, June 2015 Denver, Colorado, USA.

6) Term of License:

The License is effective upon receipt by you of the Lexicon and shall continue until terminated. The License will terminate immediately without notice by FBK if you fail to comply with the terms and conditions of this Agreement. Upon termination of this License, you shall immediately discontinue all use of the Lexicon provided hereunder, and return to FBK or destroy the original and all copies of all such Lexicon. All of your obligations under this Agreement shall survive the termination of the License.

7) Warranty:

FBK MAKES NO REPRESENTATIONS ABOUT THE SUITABILITY, USE, OR PERFORMANCE OF THIS DATABASE OR ABOUT ANY CONTENT OR INFORMATION MADE ACCESSIBLE BY THE DATABASE, FOR ANY PURPOSE. THE DATABASE IS

PROVIDED “AS IS,” WITHOUT EXPRESS OR IMPLIED WARRANTIES INCLUDING, BUT NOT LIMITED TO, ANY IMPLIED WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE, OR NONINFRINGEMENT WITH RESPECT

TO THE DATABASE. FBK IS NOT OBLIGED TO SUPPORT OR ISSUE UPDATES TO THE DATABASE.

8) Limitation on Liability:

This Lexicon is provided free of charge and, accordingly, FBK shall not be liable under any theory for any damages suffered by you or any user of the Lexicon. UNDER NO CIRCUMSTANCES SHALL FBK BE LIABLE TO YOU OR ANY OTHER PERSON FOR ANY DIRECT, INDIRECT, SPECIAL, INCIDENTAL, OR CONSEQUENTIAL DAMAGES OF ANY CHARACTER INCLUDING, WITHOUT LIMITATION, DAMAGES FOR LOSS OF GOODWILL, WORK STOPPAGE, COMPUTER FAILURE OR MALFUNCTION, OR ANY AND ALL OTHER ECONOMIC LOSS OR COMMERCIAL DAMAGES ARISING OUT OF THE USE OR INABILITY TO USE THIS DATABASE, EVEN IF FBK SHALL HAVE

BEEN INFORMED OF THE POSSIBILITY OF SUCH DAMAGES, OR FOR ANY THIRD-PARTY CLAIMS.

9) Indemnification:

You agree to hold harmless, indemnify, and defend FBK, its Trustees, officers, employees, and agents from and against any loss, damage, liability, claim of loss, lawsuit, cause of

action, or other claim asserted against them or any of them arising out of, or in any way connected with, your performance of any activity hereunder.

10) Export Controls:

You agree that the Lexicon will not be shipped, transferred, or exported into any country or used in any manner prohibited by the Italian export laws, restrictions, or regulations.

11) Disputes/Arbitration:

This Agreement shall be governed under the laws of Italy. Any dispute between the parties arising out of or relating to this Agreement will be submitted to binding

arbitration in Trento, (Italy), pursuant to the Commercial Arbitration Rules of the Italian Arbitration Association, and judgment on the award may be entered in any court of competent

jurisdiction; provided, however, that either party may seek preliminary injunctive or other equitable relief pending arbitration to prevent irreparable harm. The prevailing party in

any arbitration or litigation shall be entitled to recover all reasonable expenses thereof, including attorney’s fees in connection with such proceedings or any appeal thereof.

12) Entire Agreement:

This Agreement contains the entire agreement between the parties with respect to the subject matter hereof, and it shall not be modified or amended except by an instrument in writing signed by both parties hereto.

SUBMIT REQUEST

References:

[1] Sensicon: An Automatically Constructed Sensorial Lexicon, Serra Sinem Tekiroğlu, Gözde Özbal, Carlo Strapparava. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 1511–1521, Doha, Qatar, October. Association for Computational Linguistics.

[2] A Computational Approach to Generate a Sensorial Lexicon, Serra Sinem Tekiroğlu, Gözde Özbal and Carlo Strapparava. In Proceedings of the COLING 2014 Workshop on Cognitive Aspects of the Lexicon (CogALex), August 2014, Dublin, Ireland.

[3] Exploring Sensorial Features for Metaphor Identification, Serra Sinem Tekiroğlu, Gözde Özbal, and Carlo Strapparava. In Proceedings of the NAACL HLT 2015 (2015) on The Third Workshop on Metaphor in NLP: 31, June 2015 Denver, Colorado, USA.

Contact: Serra Sinem Tekiroglu and Carlo Strapparava