Sarcasm can radically alter or invert a phrase's meaning. Sarcasm detection can therefore help improve natural language processing (NLP) tasks. The majority of prior research has modeled sarcasm detection as classification, with two important limitations: 1. Balanced datasets, when sarcasm is actually rather rare. 2. Using Twitter users' self-declarations in the form of hashtags to label data, when sarcasm can take many forms. To address these issues, we create an unbalanced corpus of manually annotated Twitter conversations. We compare human and machine ability to recognize sarcasm on this data under varying amounts of context. Our results indicate that both class imbalance and labelling method affect performance, and should both be considered when designing automatic sarcasm detection systems. We conclude that for progress to be made in real-world sarcasm detection, we will require a new class labelling scheme that is able to access the 'common ground' held between conversational parties.
The first account of transverse preputial island flap neo-urethroplasty was given in 1978 by Duckett (unpublished material) from Philadelphia to this association. The procedure, commonly known as the Duckett operation, is for the repair of hypospadias in boys whose urethral defect is too long for them to be treated by meatal advancement and glanduloplasty, also described by Duckett in 1980. These 2 operations leave only a very small number of hypospadiacs with a urethral defect so long that more complicated surgery is needed. Acquired urethral defects can also be repaired using transverse preputial island flap neo-urethroplasty.
Warning: this paper contains example data that may be offensive or upsetting.Over the last several years, end-to-end neural conversational agents have vastly improved in their ability to carry a chit-chat conversation with humans. However, these models are often trained on large datasets from the internet, and as a result, may learn undesirable behaviors from this data, such as toxic or otherwise harmful language. Researchers must thus wrestle with the issue of how and when to release these models. In this paper, we survey the problem landscape for safety for end-to-end conversational AI and discuss recent and related work. We highlight tensions between values, potential positive impact and potential harms, and provide a framework for making decisions about whether and how to release these models, following the tenets of value-sensitive design. We additionally provide a suite of tools to enable researchers to make better-informed decisions about training and releasing end-to-end conversational AI models.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.