Ph.D. Candidate, University of Southern California
Neural Creative Language Generation
Natural language generation (NLG) is a well-studied and still very challenging field in natural language processing. One of the less studied NLG tasks is generation of creative texts such as jokes, puns, or poems. Multiple reasons contribute to the difficulty of research in this area. First, no immediate application exists for creative language generation. This has made the research on creative NLG extremely diverse, having different goals, assumptions and constraints. Second, no quantitative measure exists for creative NLG tasks. Consequently, it is often difficult to tune the parameters of creative generation models and drive improvements to these systems. Lack of a quantitative metric and the absence of a well-defined immediate application makes comparing different methods and finding the state of the art an almost impossible task in this area. Finally, rule based systems for creative language generation are not yet combined with deep learning methods. Rule-based systems are powerful in capturing human knowledge, but it is often too time consuming to present all the required knowledge in rules. On the other hand, deep learning models can automatically extract knowledge from the data, but they often miss out some essential knowledge that can be easily captured in rule based systems.
In this work, we address these challenges for poetry generation, which is one of the main areas of creative language generation. We introduce password poems as a new application for poetry generation. These passwords are highly secure, and we show that they are easier to recall and preferable compared to passwords created by other methods that guarantee the same level of security. Furthermore, we combine finite-state machinery with deep learning models in a system for generating poems for any given topic. We introduce a quantitative metric for evaluating the generated poems and build the first interactive poetry generation system that enables users to revise system generated poems by adjusting style configuration settings like alliteration, concreteness and the sentiment of the poem. The system interface also allows users to rate the quality of the poem. We collect users’ rating for poems with various style settings and use them to automatically tune the system style parameters. In order to improve the poetry generation system, we propose to borrow ideas from human literature and develop a poetry translation system. We study human poetry translation and measure the language variation in this process. We study how human poetry translation is different from human translation in general and whether a translator translates poetry more freely. Based on these findings, we propose to develop a machine translation system specifically for translating poetry which uses language variation in the translation process to generate rhythmic and rhyming translations.
Marjan Ghazvininejad is a fifth year Ph.D. candidate in Computer Science department at University of Southern California (USC), advised by Prof. Kevin Knight. Her main research interest lies in Natural Language Processing, especially the application of deep learning techniques in this area. She is particularly interested in creative natural language generation. Her works are published at prestigious conferences and also appeared in news articles such as Washington Post and NPR. She is a recipient of finalist award in Amazon Alexa skill challenge, the first and second place winner of the Dartmouth Turing Tests in the Creative Arts in poetry generation in 2016 and 2017, and Best Demo Award at the Annual Meeting of the Association for Computational Linguistics (ACL) in 2017.