Metaphoria: An Algorithmic Companion For Metaphor
Metaphoria: An Algorithmic Companion forMetaphor CreationKaty Ilonka GeroColumbia Universitykaty@cs.columbia.eduLydia B. ChiltonColumbia Universitychilton@cs.columbia.eduABSTRACTCreative writing, from poetry to journalism, is at the cruxof human ingenuity and social interaction. Existing creativewriting support tools produce entire passages or fully formedsentences, but these approaches fail to adapt to the writer’sown ideas and intentions. Instead we posit to build tools thatgenerate ideas coherent with the writer’s context and encourage writers to produce divergent outcomes. To explorethis, we focus on supporting metaphor creation. We presentMetaphoria, an interactive system that generates metaphorical connections based on an input word from the writer. Ourstudies show that Metaphoria provides more coherent suggestions than existing systems, and supports the expressionof writers’ unique intentions. We discuss the complex issueof ownership in human-machine collaboration and how tobuild adaptive creativity support tools in other domains.CCS CONCEPTS Human-centered computing Interactive systemsand tools; Natural language interfaces; Applied computing Arts and humanities;Figure 1: A poet using Metaphoria to find metaphorical connections between america and wood.KEYWORDShuman-computer collaboration; co-creativity; generative art;writing support; natural language processingACM Reference Format:Katy Ilonka Gero and Lydia B. Chilton. 2019. Metaphoria: An Algorithmic Companion for Metaphor Creation. In CHI Conferenceon Human Factors in Computing Systems Proceedings (CHI 2019),May 4–9, 2019, Glasgow, Scotland UK. ACM, New York, NY, USA,12 pages. https://doi.org/10.1145/3290605.3300526Permission to make digital or hard copies of all or part of this work forpersonal or classroom use is granted without fee provided that copiesare not made or distributed for profit or commercial advantage and thatcopies bear this notice and the full citation on the first page. Copyrightsfor components of this work owned by others than the author(s) mustbe honored. Abstracting with credit is permitted. To copy otherwise, orrepublish, to post on servers or to redistribute to lists, requires prior specificpermission and/or a fee. Request permissions from permissions@acm.org.CHI 2019, May 4–9, 2019, Glasgow, Scotland UK 2019 Copyright held by the owner/author(s). Publication rights licensedto ACM.ACM ISBN 978-1-4503-5970-2/19/05. . . DUCTIONCreative writing, from poetry to journalism, is at the crux ofhuman ingenuity and social interaction. It conveys not onlyinformation but also experience, emotion, and beauty. Whilecomputation has opened a floodgate of creative tools formusic and the visual arts, little of that fervor has transferredto text. Word processors that detect grammatical errors areuseful, but do not support the creative elements of writing.Past work in computational support for creative writinghas focused on suggesting next sentences while writing stories [3, 26, 36] or fully generating a creative output based ona topic [11]. These ideas have potential, but current systemsfail to provide strong coherence with the intention of thewriter—either the text that they have already written or theirintention for the entire output. Since these tools are not usercentric, they are most useful during ideation when there arefewer constraints. In this case, a system’s failure to providecoherence can be seen as a feature: a random suggestion canhelp a writer move in an unexpected direction.
CHI 2019, May 4–9, 2019, Glasgow, Scotland UKWe can improve tools for creative writing by designingthem from a user-centric perspective. To do so, we proposefocusing on the building blocks of creative writing, in whichwriters have more specific goals. Instead of providing complete sentences generally applicable to wherever the writeris, we can improve the relevance of our support by constraining the idea space to a specific writing goal, and allow itto be used at more points in the writing process. We focuson metaphor, which famously conveys complex or abstractideas succinctly and is used in everything from poetry tojournalism to science education [19, 28, 29].Creating unconventional and expressive metaphors is challenging [10], requiring divergent and lateral cognitive processes [13]. We present Metaphoria: an interactive systemthat generates potential metaphorical connections for any input word. Metaphoria uses an open source knowledge graphand a modified Word Mover’s Distance algorithm to finda large, ranked list of suggested metaphorical connections.These suggestions are embedded in an interactive interfacethat allows writers to generate ideas for any input. Figure 1shows the system while used by a professional poet.We ran three studies to evaluate Metaphoria. First, wecompare our method for generating suggestions to state-ofthe-art systems and show it performs better across threemetrics for metaphor quality. Second, we have novices writeextended metaphors with and without Metaphoria and showthat Metaphoria generates meaningful and inspirational suggestions given a specific writing task. Third, we have professional poets write poems with Metaphoria and show therange of expression using the system. In the Discussion, wereport on issues of ownership that arise when a computational system produces “human-like” output, and suggestfuture work to mitigate these concerns.We make the following contributions: A computational method for producing metaphoricalconnections better than state-of-the-art algorithms. Metaphoria, an interactive system for collaborativelywriting metaphors with a computer. User studies with novice and expert writers, showingthat Metaphoria gives people useful and inspirationalsuggestions and increases the diversity of responses. Design implications for ownership in co-creative systems more generally.2RELATED WORKWriting supportWriting support has a long history; editing has existed perhaps as long as writing and the introduction of dictionariesand thesauri gave writers external tools they could use ontheir own. Experimental writing movements, such as theDadaists with their cut-up technique and the Oulipo withKaty Ilonka Gero and Lydia B. Chiltontheir constrained methods, employed algorithmic ideas totrigger inspiration, pre-dating the advent of computers.One of the early successes of computation was the development of spell-check [33], and grammar-checking remainsan active area of research today [20]. Recent computationalwork has leveraged cognitive apprenticeship models to improve writing with highly specific goals, such as an emailto request help [15], an essay for a standardized test [2], ora piece of journalism [25]. Work on collaborative writing[1, 17, 39] has shown that writing can be broken into microtasks in which individuals can contribute usefully withoutaccess to the full writing document.This success suggests applying user-centric ideas to creative writing. Support for creative writing has focused ongenerating next sentences for a story [3, 36, 38] or generatingentire poems given a topic [11, 31]. While this paradigm haspotential to trigger inspiration similar to the earlier, experimental movements, we focus on providing more coherentsuggestions by responding to the need for rhetorical devices.We provide support for metaphor creation, a common butchallenging rhetorical device [10]. This narrowing of thegoal, similar to previous HCI work on writing, allows us toachieve the coherence necessary to move beyond randomassociation and support the creation of meaning.Creativity support and co-creativityCreativity support tools have flourished for music and thevisual arts, from the widespread adoption of software for generation and editing to the development of medium-specificprogramming languages [22, 34, 45]. These tools are beginning to tackle how to be compatible with existing manualpractices [16], as well as how to be more compatible withcurrent artificial intelligence frameworks [6, 30].The way in which creativity support tools integrate withan artist’s practice is at the heart of these issues. When asupport tool provides more complete or conceptual contributions, or provides contributions without a request from theartist (as in mixed-initiative user interfaces [14]), the termco-creativity is often used. Critically, Davis defines humancomputer co-creativity as when the “program is adaptingto the input of the user” [5]. This distinguishes co-creativesystems from more procedural contributions, in which anartist either has a high level of control over the outputs, asin a synthesizer, or little to no control over the outputs, as ina computer-generated poem based on a topic [11].It is essential to think about tools as supporting artists intheir desired practice, rather than replacing aspects deemedcomputationally tractable. Support for creative writing shouldalign with the ‘wide walls’ design principle of creativity support tools, in which tools aim to “support and suggest a widerange of explorations” [35]. Unlike more specified writing
Metaphoria: An Algorithmic Companion for Metaphor Creationtasks (such as writing an email to request help), creative writers do not want tools that will make their writing sound thesame as others [38]. Thus, in co-creative domains, systemsshould be conducive to divergent outcomes.CHI 2019, May 4–9, 2019, Glasgow, Scotland UKhighlowMetaphor generation algorithmsMetaphor generation is a version of conceptual blending[7] that has been correlated with general fluid intelligence[37] and is considered an important challenge in artificialintelligence [44].Current metaphor generation systems find properties thatcan be attributed to the two concepts in the metaphor. Twoprominent algorithms are Thesaurus Rex [40, 42] and Intersecting Word Vectors [8]. Thesaurus Rex [40, 42] is a webservice that provides shared attributes and categories for input concepts. For example, inputting coffee & cola producesresults such as acidic food and nonalcoholic beverage. Thesaurus Rex is explicitly designed to support metaphor generation [41, 43]. Intersecting Word Vectors [8] is a metaphorgeneration algorithm in which connector words are foundusing word embeddings. Connector words are those foundin the intersection of the 1000 words closest to each of theconcept words. For example, connector words for storm &surrender include barrage and onslaught. These systems arestrong baselines for metaphor generation from the artificialintelligence and natural language processing communities.Theories of metaphor often conform to structural alignment theory [9] in which analogies are discovered by findingisomorphic sections of knowledge graphs, where each edge isa structural relation between concepts. Work on using analogies for product design [12] has focused on the differencebetween structural and functional aspects of products forideation. We draw on these ideas of structural and functionalconnections as a search function for concept attributes.3DESIGN OF METAPHORIADesign GoalsBased on our literature review, coherence to context is thebiggest barrier to use for creative writing support tools [3, 26,36]. Secondarily, writers do not want tools that make theirwriting sound the same as others [38]. Thus, suggestions thatresult in divergent outcomes for writers is crucial. Thesegoals map to previous methodology in HCI for the evaluationof generative drawing tools; Jacobs et. al. [16] evaluate theirdrawing tool on compatibility (coherence to context) andexpressiveness (ability to express a divergent set of ideas) .A system that is coherent to context provides suggestions that are relevant to the task at hand. If writers cometo the system with an idea or intention, the system shouldgenerate metaphorical phrases coherent with this context,and should be flexible enough to be coherent for a wide rangeenvy is used for getting attention like a bellenvy is for alerting you to something like a bell.envy is used to toll like bellenvy is for playing music like a bellTable 1: Examples of connections with high and lowrelevance for the seed envy is a bell.of writer ideas and intentions. A system that encourages divergent outcomes provides many compelling options andincreases the variation in writers’ work rather than propelall writers toward similar metaphors.To address coherence to context, we focus on generatingmetaphorical connections for a given “seed metaphor”. Seedmetaphors are of the form [source] is [vehicle], e.g. envy isa bell, where envy is the source and bell is the vehicle. Byfocusing on connections between the words, such as ‘envycan sound the alarm like a bell’, rather than the selection ofthe seed words, we leave open the possibility that the writerinputs one or both words of the seed metaphor.To address divergent outcomes, we generate and presentmultiple, distinct suggestions for each seed metaphor. Thisapproach allows writers to select a suggestion salient forthem in particular.Generating coherent connectionsStarting with a seed metaphor, our approach is to first generate many features of the vehicle (bell), and then rank thesefeatures by how related they are to the source (envy). Thisaligns with traditional metaphor usage, in which features ofthe vehicle are used to explain the source.To find features of the vehicle we use ConceptNet [24],an open-source knowledge graph, as a source of structuraland functional properties of words. Structural properties areelements that define or compose an object. For example, abell has a clapper and a mouth. In ConceptNet, we select forstructural features by querying the “HasA” relations of thevehicle. Functional properties focus on an object’s actionsand purpose. For example, a bell can make noise and be usedfor alerting. In ConceptNet, we select for functional featuresby querying the “UsedFor” and “CapableOf” relations. Together, structural and functional properties provide a largeset of potential connections from the vehicle to the source.Not all features of the vehicle (bell) will metaphoricallymap to the source (envy). To find the most relevant ones,we rank how related the vehicle features (e.g. used for getting attention) are to the source (envy). To rank suggestionswe use GloVe word embeddings [32] trained on Wikipedia2014 Gigaword 5. Word embeddings are a common way tomeasure the semantic similarity between words [27]. Here,
CHI 2019, May 4–9, 2019, Glasgow, Scotland UKKaty Ilonka Gero and Lydia B. Chiltonwe use them to measure the semantic similarity betweenthe vehicle property and source word. Examples of vehicleproperties with high and low relevance are found in Table 1.To find the semantic distance between vehicle features andthe source word, we use a modified Word Mover’s Distance(WMD) [18]. WMD is an algorithm for finding the smallestdistance between two documents, i.e. sets of words, in a wordembedding space. It formulates distance between documentsas a transportation problem: we denote c(i, j) as the distancebetween words x i and x j , where c(i, j) is the cosine distancebetween the two word vectors. Given two documents D 1 andD 2 , we allow each word i in D 1 to be transformed into anyword in D 2 in total or in parts. We denote Ti j as how muchof word i in D 1 is transformed to word j in D 2 ; thereforeÍi, j Ti j 1.We can define the distance between two documents as theminimum cumulative cost of moving all words in D 1 to allwords in D 2 . This is equivalent to solving the linear programminÕTi j c(i, j)(1)i, jfor which specialized solvers have been developed. Forexample, this would find the shortest distance from makingnoise to envy.1 From this ranking of connections, we canselect the top n as the most coherent.Selecting multiple distinct connectionsIn order to promote diverse outcomes, our systems presentswriters with 10 coherent suggestions that are semanticallydistinct. For instance get attention and getting people’s attention may both be coherent, yet they give effectively thesame idea to the writer. For this reason, as we build our listof suggestions to show the writer, we throw out any featurethat is too close to any of the features already ranked. Thiscloseness is again calculated with the Word Mover’s Distance, this time between two features. Through observation,we find a distance of less than 4 indicates two features arenot semantically distinct.Additional coherence with valence rankingThe word embedding space is not sensitive to antonymsand thus some highly ranked features have a mismatchedsentiment with the source concept. Pilot testing showedthat people found mismatched sentiments to be jarring andcaused them to lose faith in the system. However, peoplewho are first shown more intuitive features were more likelyto appreciate the antonym features. Thus, we first select thesuggestions as shown above, and then re-rank them by howsimilar the valence of each one is to the source concept.1 Inthis usage, D 2 is always a single word, the source concept, although ourimplementation allows for natural expansion into multi-word sources.Figure 2: Screenshot of Metaphoria with suggestion for jealousy is a garden expanded.Valence is the positive or negative connotation of a wordand we assign valence scores to all words based on Warriner,et. al’s database [46]. We denote the valence of the source asVsour ce and the valence of word i in the feature Vi for words1, ., n. Then we define the valence distance asVdist Vsour ce avg(V1 , ., Vn ) (2)We can then reorder the suggestions from the smallestvalence distance to the largest.Finally, we rephrase all connections into a suggestion forthe writer; given the source envy, the vehicle bell and theconnecting feature making noise, the suggestion is presentedas ‘envy is used for making noise like a bell’.Additional distinctness with suggestion expansionGreat metaphors are specific; we want to support writing specific metaphors by expanding them to include more detailsof how the source and vehicle are connected. If envy makesnoise like a bell, we can expand on the details of the noise abell makes (e.g. vibrato, reverberation, high/low pitch) and howthese details relate to envy. For example, the noise of a bellhas reverberation; and envy has lasting bitterness. Metaphoriaprovides multiple detailed metaphoric expansions for eachsuggestion to give writers more diverse options.To generate the expanded metaphors, we first split eachsuggestion into two parallel sentences: one about the vehicle(bells make noise) and one about the source (envy makes noise).We want to find several alternative words to replace noisein each sentence. To generate these words, we again rely onword embeddings. This time, however, we want to discoverwords that will syntactically match the sentence–for thisreason, we use word embeddings trained using a dependencyparse as the context [21]. This results in similar words alsohaving a similar part of speech. We use the word embeddingsto create list of 60 words similar to the content word (noise)and 60 words similar to source (envy). Then, we order thesewords by similarity to the vehicle (bell) and original word(noise), respectively, and return the 10 most related words
Metaphoria: An Algorithmic Companion for Metaphor Creationin each case. Figure 2 shows the interface where a writerselects the suggestion “jealousy is for growing flowers like agarden” and can click through suggested expansions such as“jealousy is for growing sorrow.”InteractivityThe above methods are embedded in a Flask-based web application, as shown in Figure 1. Writers can input their ownsource and click through a set of common vehicles. Eachcombination will generate a list of up to 10 suggestions, andeach suggestion can be expanded.The design of Metaphoria has our goals of coherenceto context and divergent outcomes in mind. By allowingwriters to input a source and change the vehic
Metaphoria: An Algorithmic Companion for Metaphor Creation CHI 2019, May 4–9, 2019, Glasgow, Scotland UK tasks (such as writing an email to request help), creative writ-ers do not want tools that will make their writing sound the same as others [38]. Thus, in co-creative do
Bruksanvisning för bilstereo . Bruksanvisning for bilstereo . Instrukcja obsługi samochodowego odtwarzacza stereo . Operating Instructions for Car Stereo . 610-104 . SV . Bruksanvisning i original
10 tips och tricks för att lyckas med ert sap-projekt 20 SAPSANYTT 2/2015 De flesta projektledare känner säkert till Cobb’s paradox. Martin Cobb verkade som CIO för sekretariatet för Treasury Board of Canada 1995 då han ställde frågan
service i Norge och Finland drivs inom ramen för ett enskilt företag (NRK. 1 och Yleisradio), fin ns det i Sverige tre: Ett för tv (Sveriges Television , SVT ), ett för radio (Sveriges Radio , SR ) och ett för utbildnings program (Sveriges Utbildningsradio, UR, vilket till följd av sin begränsade storlek inte återfinns bland de 25 största
Hotell För hotell anges de tre klasserna A/B, C och D. Det betyder att den "normala" standarden C är acceptabel men att motiven för en högre standard är starka. Ljudklass C motsvarar de tidigare normkraven för hotell, ljudklass A/B motsvarar kraven för moderna hotell med hög standard och ljudklass D kan användas vid
LÄS NOGGRANT FÖLJANDE VILLKOR FÖR APPLE DEVELOPER PROGRAM LICENCE . Apple Developer Program License Agreement Syfte Du vill använda Apple-mjukvara (enligt definitionen nedan) för att utveckla en eller flera Applikationer (enligt definitionen nedan) för Apple-märkta produkter. . Applikationer som utvecklas för iOS-produkter, Apple .
A Companion to Greek Tragedy Edited by Justina Gregory A Companion to Classical Mythology Edited by Ken Dowden A Companion to Greek and Roman Historiography Edited by John Marincola A Companion to Greek Religion Edited by Daniel Ogden A Companion to Greek Rhetoric Edited by Ian Worthington A Companion to Roman Rhetoric Edited by William J .
A Companion to Greek Rhetoric Edited by Ian Worthington A Companion to Ancient Epic Edited by John Miles Foley A Companion to Greek Tragedy Edited by Justina Gregory A Companion to Latin Literature Edited by Stephen Harrison A Companion to Greek and Roman Political Thought Edited by Ryan K. Balot A Companion to Ovid Edited by Peter E. Knox
Albert Woodfox, myself and all political prisoners over the years. Thank you for helping to bring these injustices to the forefront. If I omitted anyone it was an honest mistake, my apologies and sincere thanks for everything you have done too!! Free The Angola 3! Free ALL political prisoners and prisoners of conscience! All Power to the People! ROBERT KING AKA Robert King Wilkerson 2008. 15 .
