Matching Items (2)
Description
For the past three decades, the design of an effective strategy for generating poetry that matches that of a human’s creative capabilities and complexities has been an elusive goal in artificial intelligence (AI) and natural language generation (NLG) research, and among linguistic creativity researchers in particular. This thesis presents a novel approach to fixed verse poetry generation using neural word embeddings. During the course of generation, a two layered poetry classifier is developed. The first layer uses a lexicon based method to classify poems into types based on form and structure, and the second layer uses a supervised classification method to classify poems into subtypes based on content with an accuracy of 92%. The system then uses a two-layer neural network to generate poetry based on word similarities and word movements in a 50-dimensional vector space.
The verses generated by the system are evaluated using rhyme, rhythm, syllable counts and stress patterns. These computational features of language are considered for generating haikus, limericks and iambic pentameter verses. The generated poems are evaluated using a Turing test on both experts and non-experts. The user study finds that only 38% computer generated poems were correctly identified by nonexperts while 65% of the computer generated poems were correctly identified by experts. Although the system does not pass the Turing test, the results from the Turing test suggest an improvement of over 17% when compared to previous methods which use Turing tests to evaluate poetry generators.
The verses generated by the system are evaluated using rhyme, rhythm, syllable counts and stress patterns. These computational features of language are considered for generating haikus, limericks and iambic pentameter verses. The generated poems are evaluated using a Turing test on both experts and non-experts. The user study finds that only 38% computer generated poems were correctly identified by nonexperts while 65% of the computer generated poems were correctly identified by experts. Although the system does not pass the Turing test, the results from the Turing test suggest an improvement of over 17% when compared to previous methods which use Turing tests to evaluate poetry generators.
ContributorsMagge, Arjun (Author) / Syrotiuk, Violet R. (Thesis advisor) / Baral, Chitta (Committee member) / Hogue, Cynthia (Committee member) / Bazzi, Rida (Committee member) / Arizona State University (Publisher)
Created2016
Description
Creativity is increasingly cited as an educational goal in many international contexts and as a facet of academic and economic success. However, many myths surround creativity that impede its facilitation in the classroom: it is an individual talent, not teachable, and not relevant to adult life outside of artistic domains. Further, perceptions of creativity are largely informed by treatment in North American contexts. In second language instruction, linguistic creativity in particular faces greater hurdles for recognition and value, as language learners’ creative language use is often treated as error. In this paper, I argue that creative pedagogies and second language instruction can inform each other; creative pedagogy can lead to greater recognition of the creative power of language learners, and second language research can provide a cultural lens through which to gain understanding of how creativity is enacted in language. To argue that creativity facilitates language learning and is a necessary component of proficiency, I employ B. Kachru’s (1985) notion of bilingual creativity to demonstrate the ubiquity of linguistic creativity in the lives of bilingual language users. With support from Carter (2016) and G. Cook’s (2000) works on everyday creative language and language play, respectively, I demonstrate the value of linguistic creativity for language learning and language socialization. I end by suggesting five guidelines for second language instructors interested in implementing a creative pedagogy framework: (1) promote reflection and noticing in learning and creativity, (2) offer authentic models of linguistic creativity, (3) provide emotion language and multiple methods for emotional expression in interaction, (4) allow for a fusion of L1 and L2 linguistic and cultural knowledge, and (5) respond actively to opportunities for collaborative creativity.
ContributorsWinemiller, Carolena Isabel (Author) / Matsuda, Aya (Thesis advisor) / Gelderen, Elly van (Committee member) / James, Mark (Committee member) / Arizona State University (Publisher)
Created2020