Kevin Lu


pdf bib
PINEAPPLE: Personifying INanimate Entities by Acquiring Parallel Personification Data for Learning Enhanced Generation
Sedrick Scott Keh | Kevin Lu | Varun Gangal | Steven Y. Feng | Harsh Jhamtani | Malihe Alikhani | Eduard Hovy
Proceedings of the 29th International Conference on Computational Linguistics

A personification is a figure of speech that endows inanimate entities with properties and actions typically seen as requiring animacy. In this paper, we explore the task of personification generation. To this end, we propose PINEAPPLE: Personifying INanimate Entities by Acquiring Parallel Personification data for Learning Enhanced generation. We curate a corpus of personifications called PersonifCorp, together with automatically generated de-personified literalizations of these personifications. We demonstrate the usefulness of this parallel corpus by training a seq2seq model to personify a given literal input. Both automatic and human evaluations show that fine-tuning with PersonifCorp leads to significant gains in personification-related qualities such as animacy and interestingness. A detailed qualitative analysis also highlights key strengths and imperfections of PINEAPPLE over baselines, demonstrating a strong ability to generate diverse and creative personifications that enhance the overall appeal of a sentence.


pdf bib
Character-Based Models for Adversarial Phone Extraction: Preventing Human Sex Trafficking
Nathanael Chambers | Timothy Forman | Catherine Griswold | Kevin Lu | Yogaish Khastgir | Stephen Steckler
Proceedings of the 5th Workshop on Noisy User-generated Text (W-NUT 2019)

Illicit activity on the Web often uses noisy text to obscure information between client and seller, such as the seller’s phone number. This presents an interesting challenge to language understanding systems; how do we model adversarial noise in a text extraction system? This paper addresses the sex trafficking domain, and proposes some of the first neural network architectures to learn and extract phone numbers from noisy text. We create a new adversarial advertisement dataset, propose several RNN-based models to solve the problem, and most notably propose a visual character language model to interpret unseen unicode characters. We train a CRF jointly with a CNN to improve number recognition by 89% over just a CRF. Through data augmentation in this unique model, we present the first results on characters never seen in training.