The Creative Language System Group

Idiom Savant

Tony Veale — Tue, 13 Apr 2010 00:33:36 GMT

You can find a colorful description for almost anything in the texts of the world-wide-web. Of course, you can also find a great deal of nonsense and irrelevance too.Idiom Savant is a linguistic magnet for finding the sharpest needles in the haystacks of the internet. Enter a term of interest, such as priest or politician or critic or movie and Idiom Savant will show you two lists of resonant descriptions, divided acording to the perceived affect of the words employed: one list for positive descriptions, and another for negative descriptions. A sensible measure of pragmatic comparability (not just semantic similarity) is used to find the most comparable terms for your input, and to show you the positive and negative descriptions pertaining to those other terms also. For instance, enter the term critic and you will find apt descriptions for judge and monster also.

Dorian: Analogical Portraiture

Tony Veale — Mon, 14 Sep 2009 20:48:50 GMT

Hand-crafted formal ontologies have many practical uses. So too do lightweight lexical ontologies like WordNet, since each offers a semantic picture of the world than can be leveraged by a machine to achieve intelligent behaviour.

But such ontologies typically offer a reduced picture of the world, in which objects have a single correct categorization, or, at any rate, a small number of acceptable categorizations. But the real world is not so rigid, and everyday objects and entities can have very many different categorizations, depending on time, place and categorizing agent. In one context, Bill Gates may be an example of a powerful billionaire, in another an example of a software genius or business tycoon, and in another Microsoft’s CEO (or chairman, or chief architect, and so on).

This multiplicity of categorization is perhaps easiest to observe when talking about people, especially well-known people, since our categories tend to convey our subjective opinions just as much as objective facts.

Dorian is a knowledge-base that explores this multiplicity of categorization when dealing with proper-named entities. Dorian’s knowledge-base of proper-named entities is harvested from the Google n-grams, and associates entities with the categories that speakers most commonly attribute to them. Dorian’s knowledge-base is supplemented by the category-system in Wikipedia, which adopts a less subjective, curated approach to categorization.

Dorian uses these categories to perform analogical reasoning. It learns its analogical transfer rules from large text corpora (such as the Google n-grams again) by first identifying cliques of concepts that it considers comparable and interchangeable (such as London and Paris, or Java and Perl, or DC and Marvel, or Playboy and Penthouse) and generalizing these cliques to the category-level (so that e.g., Java_inventor is analogous to Perl_inventor, implying that James_Gosling is analogous to Larry_Wall, and so on).

Dorian also identifies cliques of proper-named entities in corpora (such as Roger_Federer and Rafael_Nadal) and attempts to establish analogical transfer rules that will make these clique-members analogous at the category-level.

Click here to explore Dorian’s world for yourself …

The Lex-Ecologist

Tony Veale — Mon, 25 Sep 2006 17:45:56 GMT

Ecologists study the natural environment of plants and animals. Our plants and animals are words and concepts, and our environments are large text corpora. The Lex-Ecologist allows you to explore the rich textual environment for words provided by the text of the on-line encyclopaedia Wikipedia. Observe the behaviour of concepts in this environment: observe what they do, what is done to them, what they act upon, and how they congregrate into groups.

Jigsaw Bard

Tony Veale — Tue, 16 Jun 2009 10:47:18 GMT

When we think about poetry, we tend to think about rhythm and rhyme, but these just provide the packaging of poetry. You don’t have to look in poetry books to find poetry, because poetry isn’t limited to poems. Poetry is all about finding the most resonant phrase to communicate a certain idea. A resonant phrase is one that suggests a lot more than it actually says, one that sticks in the memory by painting a mental picture of something that may not have a literal visual dimension.

The Jigsaw Bard is an online application that allows you to find resonant phrases for a large range of simple properties, like quiet, or for an even larger range of complex blended properties, like quiet and calm. The Bard has already scoured vast amounts of web text to identify phrases that have a resonant quality, and has automatically indexed these phrases on the properties they most poetically suggest.

Most phrases are found art in this respect -- they are well-formed fragments of English that the Bard thinks have both a poetic quality and a useful communicative function. But some phrases (shown in blue) have been directly composed by the Bard itself. Have a look and see what you think of the Bard’s compositional abilities.

In particular, the Bard has a rudimentary sense of irony, and so for many properties it will suggest some ironic possibilities.

You can interact with the Bard by clicking here.

You can see the knowledge-base that the Bard uses as a seed for its harvesting of found art by clicking here.

Aristotle: An Interactive Metaphor Finder

Tony Veale — Tue, 30 Jun 2009 19:38:38 GMT

Let Aristotle help you find appropriate metaphors to describe a given person or thing. Simply enter the target for your metaphor (called the tenor in metaphor research), choose a property you would like to accentuate, and Aristotle will select a range of possible vehicles to carry this meaning. Click on any of these vehicles to understand the full import of the metaphor you are about to use.

Research Mission

Tony Veale — Wed, 13 Feb 2008 01:05:01 GMT

Our group is dedicated to the computational exploration of language and its creative potential, from lexical phenomena such as Metaphor, Analogy, Metonymy, Polysemy, to complex social phenomena like Humour.
As such, we build models of creative language use, and attempt to construct applications from these models.
We are also striving to develop generalized models of creative linguistic behaviour.
The resources that drive our research are the lexical ontologies WordNet and HowNet and the open-source encyclopaedia Wikipedia.
Read or listen Tony Veale’s discussion of humour and metaphor on the radio show - PhilosophyTalk.
The ZeitGeist system for harvesting creative neologisms from Wikipedia (using WordNet) has been reported in New Scientist magazine. You can read the on-line report here. You can also read a related article in Dutch from the web magazine Planet Internet here.

Sardonicus

Tony Veale — Tue, 30 Jan 2007 17:15:33 GMT

Sardonicus is a simile-finder that knows the exemplary properties of different objects in the real world. It has acquired this knowledge by sifting the contents of the web in search of meaningful comparisons. It knows that ninjas are stealthy and that bowling balls are heavy and smooth enough to be called bald. It also has a healthy sense of irony, so it knows that roller-coasters are not exactly a model of consistency, and that turtles are not generally prized for their speed. The similes in Sardonicus are divided into straight-faced "factual" similes and tongue-in-cheek "ironic" similes, and are organized hierarchically using a taxonomy of adjectives. Try it now, it might put an ironic smile on your face.

Mondrian: Mapping of Names, Descriptions and Roles in Analogy

Tony Veale — Tue, 30 Jun 2009 19:37:16 GMT

Mondrian is a knowledge-base of commonplace associations that have been mined from the Google n-grams database of frequent web-content.

Mondrian views the world as a collection of triples, of the form Subject-Relation-Object.

You can query Mondrian to see what triples have a given Subject, Relation or Object (or any combination of these).

For instance, put Rabbi in the Subject field and Mondrian will give you all its triples in which Rabbi is the subject.

When you click on a relation, Mondrian shows you analogies for this relation. Mondrian uses the squaring rule to detect analogies: S1-R-O1 is analogical to S2-R-O2 if Mondrian thinks that S1-like-S2 and O1-like-O2. Hence, Mondrian builds squaring relations between parallel triples.

Click on a column of the relations table to see the table re-sorted with that column as a key.

Mondrian will also show you the common compounds that a subject engages in.

Click here to see Mondrian in action.

The Way of Knowledge

Dominic — Fri, 29 Sep 2006 13:31:44 GMT

Your goal is to progress through multipe levels of Karma, to finally reach Nirvana, the state of perfect enlightenment.

Answering the questions correctly will guide you toward your goal. Answering them incorrectly will distract you from the path.

However, you can always find this path again through wisdom, or sometimes, blind luck!

Take care not to fall into the Pit of Ignorance. When it is nearby, just one misstep will cause you to be cast down to a lower Karmic level.

Tread carefully along the path and enlightenment will be yours

View Instructions or Start new game

Wiki-Wanderer

Dominic — Fri, 29 Sep 2006 13:14:44 GMT

Another levels-based grid game, in which you must use your world knowledge to find a path between different start/endpoints in Wikipedia (e.g., from Zeus to Haircream). Each level has successively longer paths for you to navigate, but hints are liberally sprinkled around each level.

Play a demo version of this game

DimSum

Dominic — Tue, 03 Oct 2006 23:31:31 GMT

Different languages tend to represent different cultural and conceptual perspectives on the world. To the originating culture, such lexicalized perspectives may seem entirely conventional and stale, but to another they may well provide fresh and even innovative insights into the meaning and creative uses of words. DimSum aims to mine these insights from the lexical structure of Chinese, a logomorphemic language that exhibits its semantic structure quite openly in its orthographic realization.

Have difficulties in viewing Chinese?
If you are using Internet Explorer, try: go to tool menu and under the advanced tab, click “enable install on Demand”.

Still doesn’t work? Or you are using a different browser?
Try to include a Chinese language pack in the browser. For further information, please visit http://www.chinapage.com/font/faq01.html.

ZeitGeist

cris — Thu, 12 Oct 2006 21:27:27 GMT

Language is a dynamic landscape in which words are not fixed landmarks, but unstable signposts that switch directions as archaic senses are lost and new, more topical senses, are gained. Frequently, entirely new lexical signposts are added as newly minted word-forms enter the language.
One can experience the variety and inventiveness of the most creative new words in English with ZeitGeist, a creative neologism generator. Our system uses the semantic context provided by Wikipedia’s topology of cross-references to add corresponding semantic entries to WordNet. Start ZeitGeist

The Analogical Thesaurus

Dominic — Fri, 29 Sep 2006 12:30:53 GMT

The Analogical Thesaurus is an attempt to create a semantic index of words and ideas that can be accessed using a variety of conceptual perspectives. Besides the traditional alphabetic index (as in conventional dictionaries) and a taxonomic index (e.g., as found in WordNet), the Analogical Thesaurus provides an analogical and metonymic means of browsing through words and ideas.

As presented here, the Analogical Thesaurus has been distilled from a marriage of two resources. The first is HowNet lexical ontology, using analogical techniques described in our group publications. The second is Wikipedia, an on-line open-source encyclopedia, whose rich inter-topic reference structure allows us to extract implicit relationships from HowNet entries and their Chinese orthography.

You can access the Analogical Thesaurus on-line. Be sure to read the help documentation first.

Trail-Blazer

Dominic — Fri, 29 Sep 2006 13:28:29 GMT

This is a game that exploits a player’s knowledge of compound terms in a language. One must blaze a trail through a matrix of words, from the top row to the bottom, forming a chain composed of two-word compound terms. That is, each successive pair of words in the chain must comprise an established two-word phrase, like "queen mother" or "mother goose" (as in the chain "queen mother goose").

Play a demo version of this game

Ikarus

Dominic — Fri, 29 Sep 2006 13:16:50 GMT

This is a variant of Trail-Blazer in which the word chains you form must comprise hypernymic terms (like nude isa person isa form ...).

Play a demo version of this game

Side-Winder

Dominic — Fri, 29 Sep 2006 13:29:16 GMT

This is a variant of Trail-Blazer that exploits a player’s knowledge of synonyms and compound terms in a language. One must blaze a trail through a matrix of words, from the top row to the bottom, forming a chain composed of synonyms or two-word compound terms. That is, each successive pair of words in the chain must be synonymous or comprise an established two-word phrase, like "queen mother" or "mother goose" (as in the chain "queen mother goose"). Note that compounds can be used both forwards (as in side door) and backwards (as in door side). Note also that word chains can zig-zag from side to side.

Play a demo version of this game

Publications

Tony Veale — Mon, 30 Aug 2010 11:44:12 GMT

2010

Forceville, Charles, Veale, Tony and Feyaerts, Kurt (2010).
Forceville, Charles, Veale, Tony and Feyaerts, Kurt. (2010). Balloonics: The Visuals of Balloons in Comics. The RISE and REASON of Comics and Graphic Literature: Critical Essays on the Form, Edited by Joyce Goggin & Dan Hassler-Forest. [pdf]
Cristina Butnariu, Su Nam Kim, Preslav Nakov, Diarmuid OSeaghdha, Stan Szpakowicz, Tony Veale (2010).
Cristina Butnariu, Su Nam Kim, Preslav Nakov, Diarmuid OSeaghdha, Stan Szpakowicz, Tony Veale, "SemEval-2010 Task 9: The Interpretation of Noun Compounds Using Paraphrasing Verbs and Prepositions, ACL workshop on Semantic Evaluations (SemEval 2010)), 2010, pp. 39--44. [pdf]
Veale, T. and Hao, Y. (2010).
Veale, T. and Hao, Y. (2010). Detecting Ironic Intent in Creative Comparisons. In the proceedings of ECAI’2010, the 19th European Conference on Artificial Intelligence. Lisbon, 2010. [pdf]
Li, G., Lopez-Fernandez, A. and Veale, T. (2010)
Li, G., Lopez-Fernandez, A. and Veale, T. (2010). UCD-Goggle: A Hybrid System for Noun Compound Paraphrasing. In the proceedings of the 5th International Workshop on Semantic Evaluation, ACL 2010, pages 230–233, Uppsala, Sweden, 15-16 July 2010. [pdf]
Veale, T. and Butnariu, C. (2010).
Veale, T. and Butnariu, C. (2010). Harvesting and Understanding On-line Neologisms. Onysko, Alexander and Michel, Sascha (Eds.), Cognitive Perspectives on Word Formation. 393-416. Mouton De Gruyter. [pdf]
Veale, T. and El Mouddeb, M. (2010).
Veale, T. and El Mouddeb, M. (2010). Similarity, Comparability And Analogy In WordNet: Squaring The Analogical Circle With Mondrian. Bhattacharyya, P., Vossen, P. and Fellbaum, C. (eds.) Proceedings of the 5th Global WordNet Conference, Mumbai, India. [pdf]

2009

Cristina Butnariu, Su Nam Kim, Preslav Nakov, Diarmuid OSeaghdha, Stan Szpakowicz, Tony Veale (2009)
Cristina Butnariu, Su Nam Kim, Preslav Nakov, Diarmuid OSeaghdha, Stan Szpakowicz, Tony Veale, "SemEval-2010 Task 9: The Interpretion of Noun Compounds Using Paraphrasing Verbs and Prepositions. In Proceedings of the NAACL Workshop on Semantic Evaluations: Recent Achievements and Future Directions (SEW-2009) at NAACL, 2009, pp. 100-105. [pdf]
Cardoso, A., Veale, T., Wiggins, G. (2009)
Cardoso, A., Veale, T., Wiggins, G. (2009) ’Converging on the divergent: the history (and future) of the international joint workshops in computational creativity’ AI Magazine 30 (3) :15-22. [pdf]
Veale, T. , Li, Guofu (2009)
Veale, T., Li, Guofu. (2009). ONTOLOGICAL CLIQUES - Analogy as an Organizing Principle in Ontology Construction. In Proceedings of IC3K/KEOD, The International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management. Madeira, Portugal. [pdf]
Veale, T. (2009)
Veale, T. (2009). Hiding in Plain Sight: Figure-Ground Reversals in Humour. In Cognitive Poetics: Goals, Gains and Gaps, G. Brône and J. Vandaele (eds.), Mouton de Gruyter. [pdf]
Veale, T. and Hao, Y. (2009)
Veale, T. and Hao, Y. (2009). Support Structures for Linguistic Creativity: A Computational Analysis of Creative Irony in Similes. In proceedings of CogSci 2009, the 31st Annual Meeting of the Cognitive Science Society. Amsterdam. [pdf]
Veale, T., Li, G. and Hao, Y. (2009)
Veale, T., Li, G. and Hao, Y. (2009). Growing Finely-Discriminating Taxonomies from Seeds of Varying Quality and Size. In proceedings of EACL 2009, The 12th Conference of the European Chapter of the Association for Computational Linguistics. Athens, Greece. [pdf]

2008

Veale T. (2008)

Veale, T. (2008). Figure-Ground Duality in Humour: A Multi-Modal Perspective. Lodz Papers in Pragmatics, 4(1), pp 63 -- 81. [pdf]
Veale, T. and Hao, Y. (2008)

Veale, T. and Hao, Y. (2008). A Fluid Knowledge Representation for
Understanding and Generating Creative Metaphors. In proceedings of Coling 2008, The 22nd International Conference on Computational Linguistics. Manchester. [pdf]
Butnariu, C. and Veale, T. (2008)

Butnariu, C. and Veale, T(2008). A Concept-Centered Approach to Noun-Compound Interpretation. In proceedings of Coling 2008, The 22nd International Conference on Computational Linguistics. Manchester. [pdf]
Veale, T. and Hao, Y. (2008)

Veale, T. and Hao, Y. (2008). Talking Points in Metaphor: A Concise Usage-based Representation for Figurative Processing. In proceedings of ECAI 2008, the 18th European Conference on Artificial Intelligence. Patras, Greece. [pdf]
Veale, T., Hao, Y. and Li, G. (2008)

Veale, T., Hao, Y. and Li, G. (2008). Multilingual Harvesting of Cross-Cultural Stereotypes. In proceedings of ACL 2008, the 46th Annual Meeting of the Association of Computational Linguistics. Ohio, USA. [pdf]
Veale, T. and Hao, Y. (2008)

Veale, T. and Hao, Y. (2008). Acquiring Naturalistic Concept Descriptions from the Web. In proceedings of LREC 2008, the sixth international conference on Language Resources and Evaluation. Marrakech, Morocco. [pdf]
Veale, T. and Hao, Y. (2008)

Veale, T. and Hao, Y. (2008). A context-sensitive framework for lexical ontologies. The Knowledge Engineering Review, Vol.23:1, pp 101--115. 2008, Cambridge University Press. [pdf]

Butnariu, C. and Veale, T. (2008)
Butnariu, C. and Veale, T(2008). On the categorization of Cause and Effect in WordNet. In proceedings of GWC 2008, the 4th Global WordNet Conference. Szeged, Hungary. [pdf]
Veale, T. and Hao, Y. (2008)
Veale, T. and Hao, Y. (2008). Enriching WordNet with Folk Knowledge and Stereotypes. In proceedings of GWC 2008, the 4th Global WordNet Conference. Szeged, Hungary. [pdf]

2007

Veale, T. (2007).
Veale, T. (2007). Dynamic Creation of Analogically-Motivated Terms and Categories in Lexical Ontologies. In Judith Munat (Ed.), Lexical Creativity, Texts and Contexts (Studies in Functional and Structural Linguistics), pp 189-212. Amsterdam: John Benjamins. [pdf]
Veale, T. and Hao, Y. (2007)
Veale, T. and Hao, Y. (2007). Learning to Understand Figurative Language: From Similes to Metaphors to Irony. In proceedings of CogSci 2007, the 29th Annual Meeting of the Cognitive Science Society. Nashville, USA. [pdf]
Veale, T. and Hao, Y. (2007)
Veale, T. and Hao, Y. (2007). Comprehending and Generating Apt Metaphors: A Web-driven, Case-based Approach to Figurative Language. In proceedings of AAAI 2007, the 22nd AAAI Conference on Artificial Intelligence. Vancouver, Canada. [pdf]
Butnariu, C. and Veale, T. (2007)
Butnariu, C. and Veale, T. (2007). A hybrid model for detecting semantic relations between noun pairs in text. In the proceeding of SemEval-2007, the 4th International Workshop on Semantic Evaluations, ACL 2007. Prague, Czech Republic. [pdf]

Veale, T. and Hao, Y. (2007)

Veale, T. and Hao, Y. (2007). Making Lexical Ontologies Functional and Context-Sensitive. In proceedings of ACL 2007, the 45th Annual Meeting of the Association of Computational Linguistics, pages 57–64. Prague, Czech Republic. [pdf]

2006

Veale, T. (2006).

Veale, T. (2006). Computability as a test on linguistic theories. In Cognitive Linguistics: Current Applications and Future Perspectives, G. Kristiansen, M. Achard, R. Dirven and F. Ruiz de Mendoza Ibáñez (eds.). Applications of Cognitive Linguistics. The Hague: Mouton de Gruyter. [pdf]

Veale, T. (2006).

Veale, T. (2006). An analogy-oriented type hierarchy for linguistic creativity. Journal of Knowledge-Based Systems, Volume 19, Issue 7 , November 2006, Pages 471-479. [pdf]

Veale, T., Feyaerts, K., and Brône G. (2006).

Veale, T., Feyaerts, K., and Brône G. (2006). The Cognitive Mechanisms of Adversarial Humor. Humor: The International Journal of Humor Research, 19-3, pp 305-338. [pdf]

Veale, T. (2006).

Veale, T. (2006). Re-Representation and Creative Analogy: A Lexico-Semantic Perspective. New Generation Computing 24, pp 223-240[pdf]

Veale, T., Gervas, P. and Pease, A. (2006).

Veale, T., Gervas, P. and Pease, A. (2006). Understanding Creativity: A Computational Perspective. Introduction to the Special Issue of Computational Creativity, New Generation Computing 24, pp 203-207.[pdf]

Veale, T. (2006).

Veale, T. (2006). Tracking the Lexical Zeitgeist with Wikipedia and WordNet. In the proceedings of ECAI’2006, the 17th European Conference on Artificial Intelligence [pdf]

Veale, T. (2006).

Veale, T. (2006). ZeitGeist: A Computational Model of Neologism Processing. In Proceedings of the Second International Conference of the German Cognitive Linguistics Association. Munich, October, 2006. (abstract). [pdf]

Kim, H., Chen, S. and Veale, T. (2006).

Kim, H., Chen, S. and Veale, T. (2006). Analogical Reasoning with a Synergy of HowNet and WordNet. In the proceedings of GWC2006, the 3rd Global WordNet Conference. Cheju, Korea, January 2006. [pdf]

Veale, T. (2006).

Veale, T. (2006). A Typology of Lexical Analogy in WordNet. In the proceedings of GWC2006, the 3rd Global WordNet Conference. Cheju, Korea, January 2006.[pdf]

Costello,F., Veale,T. and Dunne,S. (2006).

Costello,F., Veale,T. and Dunne,S. (2006). Using WordNet to Automatically Deduce Relations between Words in Noun-Noun Compounds. In the Proceedings of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics [pdf]

Veale, T. and Butnariu, C. (2006).

Veale, T. and Butnariu, C. (2006). Exploring Linguistic Creativity via Predictive Lexicology. At the ECAI’2006 workshop on Computational Creativity [pdf]

Veale, T. and Hao,Y (2006).

Veale, T. and Hao,Y (2006). Corpus-Driven Contextualized Categorization. At the ECAI’2006 workshop on Contexts and Ontologies. Trento, Italy, August 2006.[pdf]

Veale, T. and Chen, S. (2006).

Veale, T. and Chen, S.(2006). Unlocking the Latent Creativity of Orthographic Structure. At the ECAI’2006 workshop on Computational Creativity. Trento, Italy, August 2006.[pdf]

Yu, Q. and Veale, T. (2006).

Yu, Q. and Veale, T. (2006). Creative Puzzle Generation from Factual Content. At the ECAI’2006 workshop on Computational Creativity. Trento, Italy, August 2006.[pdf]

Butnariu, C. and Veale, T. (2006).

Butnariu, C. and Veale, T. (2006). Lexical Combinatorial Creativity with "Gastronaut". At the ECAI’2006 workshop on Computational Creativity. Trento, Italy, August 2006. [pdf]

Hao,Y and Veale, T. (2006).

Hao,Y and Veale, T. (2006). A Fluid Category Structure for Metaphor Processing. At the ECAI’2006 workshop on Computational Creativity. Trento, Italy, August 2006. pdf]

Veale, T. and Chen, S. (2006).

Veale, T. and Chen, S.(2006). Learning to Extract Semantic Content from the Orthographic Structure of Chinese Words. In the proceedings of AICS2006, the 17th Irish conference on Artificial Intelligence and Cognitive Science, Belfast, Ireland, September 2006.[pdf]

Yu, Q. and Veale, T. (2006).

Yu, Q. and Veale, T. (2006). Creative Puzzle Generation from Factual Content. In the proceedings of AICS2006, the 17th Irish conference on Artificial Intelligence and Cognitive Science, Belfast, Ireland, September 2006.[pdf]

Hao,Y and Veale, T. (2006).

Hao,Y and Veale, T. (2006). Understanding Metaphor Using a Corpus-trained Fluid Category System. In the proceedings of AICS2006, the 17th Irish conference on Artificial Intelligence and Cognitive Science, Belfast, Ireland, September 2006. pdf]

2005

Veale, T. (2005).

Veale, T. (2005). ESSLLI Course Notes on Computational Models of Metaphor. Presented at the 2005 European Summer School on Language, Logic and Information, Edinburgh, August 8th-19th. [pdf]

Veale, T. (2005).

Veale, T. (2005). Analogy as Functional Recategorization: Abstraction with HowNet Semantics. In the proceedings of IJCNLP’2005, the International Joint Conference on Natural Language Processing. Jesu Island, South Korea. [pdf]

Veale, T. (2005).

Veale, T. (2005). Analogy Generation with HowNet. In the proceedings of IJCAI’2005, the International Joint Conference on Artificial Intelligence. [pdf]

Veale, T. (2005).

Veale, T. (2005). Analogy as Functional Recategorization: APerspective from HowNet. In the proceedings of the IJCAI’2005 workshop on Creative Systems, held as part of the 2005 International Joint Conference on Artificial Intelligence, Edinburgh, July 30th, 2005. [pdf]

Veale, T., Feyaerts, K. and Brone, G. (2005).

Veale, T., Feyaerts, K. and Brone, G. (2005). An Ontological approach to affective utterances (abstract). In the proceedings of ICLC’2005, the International Cognitive Linguistics Conference, held in Seoul, Korea, July 2005. [pdf]

Hayes, J., Veale, T. and Seco N. (2005). Hayes, J., Veale, T. and Seco N. (2005). Creative discovery in the lexical validation gap. Computer Speech & Language, Volume 19, Issue 4, October 2005, Pages 513-523. Journal of Computer speech and Language [pdf]

2004

Veale, T. (2004).

Veale, T. (2004). WordNet sits the S.A.T.: A Knowledge-based Approach to Lexical Analogy. In the proceedings of ECAI 2004, the 16th European Conference on Artificial Intelligence. Valencia, Spain. John Wiley. [pdf]

N. Seco, T. Veale and J. Hayes. (2004).

N. Seco, T. Veale and J. Hayes. (2004). An Intrinsic Information Content Metric for Semantic Similarity in WordNet. In the proceedings of ECAI 2004, the 16th European Conference on Artificial Intelligence. Valencia, Spain. John Wiley. [pdf]

Veale, T., N. Seco and J. Hayes (2004).

Veale, T., N. Seco and J. Hayes (2004). Creative Discovery in Lexical Ontologies. In the proceedings of COLING’2004, the 20th International Conference on Computational Linguistics. Geneva, Switzerland. Morgan Kaufmann. [pdf]

Veale, T. (2004).

Veale, T. (2004). Polysemy and Category Structure in WordNet: An Evidential Approach. In the proceedings of LREC 2004, the 4th international conference on Language Resources and Evaluation. Lisbon, Portugal. [pdf]

Veale, T. (2004).

Veale, T. (2004). Paths to Creativity in Lexical Ontology. In the proceedings of the 2nd Global WordNet Conference, Brno, Czech Republic, January 2004. [pdf]

Veale, T. (2004).

Veale, T. (2004). Creative Information Retrieval. In the proceedings of CICLing 2004., ed. Alexander. Gelbukh, Seoul, February 2004. [pdf]

Veale, T. (2004).

Veale, T. (2004). Incongruity in Humor: Root-Cause or Epiphenomenon? The International Journal of Humor 17/4, a Festschrift for Victor Raskin. [pdf]

Veale, T. (2004).

Veale, T. (2004). Unweaving the Analogical Rainbow with Lightweight Lexical Resources. In the AISB Quarterly, 2004. [pdf]

2003

Veale, T. (2003).

Veale, T. (2003). The Analogical Thesaurus: An Emerging Application at the Juncture of Lexical Metaphor and Information Retrieval. In the proceedings of IAAI 2003, the 2003 International Conference on Innovative Applications of Artificial Intelligence. [pdf]

Veale, T. (2003).

Veale, T. (2003). Dynamic Type Creation in Metaphor Interpretation and Analogical Reasoning: A Case-Study with WordNet. In the proceedings of ICCS2003, the 2003 International Conference on Conceptual Structures, Dresden, Germany. [pdf]

Veale, T. (2003).

Veale, T. (2003). Metaphor and Metonymy: The Cognitive Trump-Cards of Linguistic Humour. Presented as a keynote talk at the ICLC Theme Session on Cognitive Linguistic Approaches to Humour, as part of the 2003 International Conference on Cognitive Linguistics. [pdf]

Veale, T. (2003).

Veale, T. (2003). Systematicity and the Lexicon in Creative Metaphor. In the Proceedings of the ACL Workshop on Figurative Language and the Lexicon, the 2003 Applied Computational Linguistics Conference, Sapporo, Japan. [pdf]

Veale, T. (2003).

Veale, T. (2003). Qualia Extraction from WordNet. In the Proceedings of the 3rd International Workshop on Creative Systems, held as part of IJCAI 03, the 2003 International Joint Conference on Artificial Intelligence. [pdf]

2002

Veale, T. (2002).

Veale, T. (2002). Compromise in Multi-Agent Blends. In the proceedings of TWWT 2002, The Way We Think, Anders Hougaard and Steffen Nordahl Lund (eds.). Odense Working Papers in Language and Communication, No. 23, August 2002. [pdf]

Veale, T. (2002).

Veale, T. (2002). Meta-Knowledge Annotation for Efficient Natural-Language Question-Answering. In the proceedings of AICS ’2002, the 13th Irish conference on Artificial Intelligence and Cognitive Science. Lecturer Notes in AI, LNAI 2464. Berlin: Springer. [pdf]

2000

Veale, T., O Donoghue, D., Keane, M. T. (2000).

Veale, T., O Donoghue, D., Keane, M. T. (2000). Computation and Blending. Cognitive Linguistics, 11(3/4), pp 253-281. [pdf]

1999

Veale, T., O Donoghue, D., Keane, M. T. (1999).

Veale, T., O Donoghue, D., Keane, M. T. (1999). Computability as a limiting cognitive constraint: Complexity concerns in metaphor comprehension about which cognitive linguists should be aware, Cultural, Psychological and Typological Issues in Cognitive Linguistics, Ed. M. Hiraga, C. Sinha and S. Wilcox. John Benjamins: Amsterdam/Philadelphia, pp 129-155. [pdf]

1998

Veale, T., Conway, A., Collins, B. (1998).

Veale, T., Conway, A., Collins, B. (1998). The Challenges of Cross-Modal Translation: English to Sign Language Translation in the ZARDOZ System. Machine Translation 13(1). [pdf]

Veale, T. (1998).

Veale, T. (1998). ’Soft’ Approaches to Structural Alignment in the Sub-Graph Isomorphism Problem, in the Proc. of the IASTED International Conference on Soft Computing and Artificial Intelligence, Cancun, Mexico, May 1998. [pdf]

Veale, T. (1998).

Veale, T. (1998). Pragmatic Pressures in Metaphor Appreciation, presented at CMA2, An International Workshop on Computation for Metaphors, Agents and Analogy, Aizu, Japan, April 1998. (published by Springer Verlag in the Lecture Notes in Artificial Intelligence series). [pdf]

Veale, T. (1998).

Veale, T. (1998). ’Just in Time’ Analogical Mapping, An Iterative-Deepening Approach to Structure-Mapping, in the proceedings of ECAI’98, the Thirteenth European Conference on Artificial Intelligence, Brighton, UK, August 1998. [pdf]

Veale, T. and Keane, M. T. (1998).

Principal Differences in Structure-Mapping, in the proceedings of Advances in Analogical Research, edited by Keith Holyoak, Dedre Gentner & Boicho Kokinov, 1998. [pdf]

1997

Veale, T. and M. T. Keane (1997).

Veale, T. and M. T. Keane (1997). The Competence of Sub-Optimal Structure Mapping on ’Hard’ Analogies, in the proceedings of IJCAI’97, the Int. Joint Conference on Artificial Intelligence, Nagoya, Japan, 1997. [pdf]

Veale, T. and Way, A. (1997).

Veale, T. and Way, A. (1997). Gaijin: A Template-Driven Bootstrapping Approach to Example-Based Machine Translation, in the Proceedings of NeMNLP ’97, New Methods in Natural Language Processing, Sofia, Bulgaria, September 1997. [pdf]

Veale, T. and M. T. Keane (1997).

Veale, T. and M. T. Keane (1997). A Computational Treatment of Metaphoric Blends with Special Regard to Cinematic "Borrowing", in the proceedings of Mind II: Computational Models of Creative Cognition, Dublin, Ireland, 1997. [pdf]

1996

Veale, T. (1996).

Veale, T. (1996). Metaphor, Memory and Meaning. Unpublished PhD thesis on Metaphor processing (in HTML). [pdf]

1995

Veale, T., O Donoghue, D., Keane, M. T. (1995).

Veale, T., O Donoghue, D., Keane, M. T. (1995). Epistemological Issues in Metaphor Comprehension: A Comparative Analysis of Three Models of Metaphor Interpretation, presented at ICLC’95, the 4th conference of The International Cognitive Linguistics Association, Albuquerque NM. 1995. (revised chapter-length version). [pdf]

1994

Veale, T. and M. T. Keane (1994).

Veale, T. and M. T. Keane (1994). Belief Modelling, Intentionality and Perlocution in Metaphor Comprehension, in the Proc. of the Sixteenth Annual Meeting of the Cognitive Science Society, Atlanta, Georgia. Hillsdale, NJ: Lawrence Erlbaum. (This is an extended version). [pdf]

Thesaurus Rex

Tony Veale — Thu, 26 Feb 2009 20:17:54 GMT

Concept taxonomies offer a powerful means for organizing knowledge, but this organization must allow for many overlapping and fine-grained perspectives if a general-purpose taxonomy is to reflect concepts as they are actually employed and reasoned about in everyday usage. Think about a term like "tofu" or "robot" -- besides the basic meanings of Food or Robot, these terms evoke different perspectives and categorizations in different contexts and for different people. For robust natural language understanding (NLU), we require our lexicons/ontologies to appreciate and exploit all of these perspectives. Thesaurus Rex acquires finely-discriminating taxonomies from the a variety of different starting points, or seeds, via a process of bootstrapping from three different sources: WordNet, ConceptNet and the web at large.

KNOW-BEST: Knowledge-Based Entertainment and Scholastic Testing

Dominic — Wed, 11 Oct 2006 08:53:24 GMT

The KNOW-BEST Project is predicated on the belief that lexical resources like WordNet and HowNet are sufficiently rich to provide a knowledge-bsed creative language system for a new generation of computer games. Great strides have been made in producing computer games that are visually realistic and compelling, and an increasing demand for this graphical richness in turn has lead to the development of graphics-engines or physics-engines to make games even more physically immersive.

However, comparatively little academic and commercial interest has been expended on the notion of a language-engine for computer games, a creative knowledge-based layer that can provide linguistic intelligence across a variety of games.

We are looking to WordNet and HowNet for the generative means to imbue games with dynamic linguistic content, in the form of language-based puzzles and on-the-fly textual content.

This dynamic content has, additionally, a scholastic application. If games can be imbued with challenging language puzzles, this content can also be used to test and evaluate students.

Play a demo version of this game

KNOW-BEST is generously funded by an Enterprise Ireland Commercialization-Fund grant.
All game designs and implementations are copyright Tony Veale and the Creative Language Systems Group.

Group Members

Tony Veale — Mon, 25 Sep 2006 17:34:28 GMT

Principal Investigators

Dr. Tony Veale, lecturer in the department of Computer Science

Current Post-graduates

Scorain Yu, WordNet-based games development, KNOW-BEST project
Cristina Butnariu, WordNet-based games development, KNOW-BEST project
Yanfen Hao, WordNet-based games development, KNOW-BEST project
Stephen Howell, WordNet-based games development, KNOW-BEST project
ShanShan Chen, Bilingual Ontology, KNOW-BEST project
Hyesook Kim, Construction of Korean WordNet / HowNet

Past or concluding Post-graduates

Jer Hayes, Term Creation in Lexical Ontologies
Nuno Seco, Similarity Measures in Lexical Ontologies

Related Research Groups and International Collaborators

CHIL: The Creativity, Humor, Imagery and Language research-unit
at the Department of Linguistics in the University of Leuven, Belgium.
The Creative Systems Laboratory
at the University of Coimbra, Portugal.