Shereen Oraby

Creating and Characterizing a Diverse Corpus of Sarcasm in Dialogue.

The use of irony and sarcasm in social media allows us to study them at scale for the first time. However, their diversity has made it difficult to construct a high-quality corpus of sarcasm in dialogue. Here, we describe the process of creating a large- scale, highly-diverse corpus of online debate forums dialogue, and our novel methods for operationalizing classes of sarcasm in the form of rhetorical questions and hyperbole. We show that we can use lexico-syntactic cues to reliably retrieve sarcastic utterances with high accuracy. To demonstrate the properties and quality of our corpus, we conduct supervised learning experiments with simple features, and show that we achieve both higher precision and F than previous work on sarcasm in debate forums dialogue. We apply a weakly-supervised linguistic pattern learner and qualitatively analyze the linguistic differences in each class.

Data-Driven Dialogue Systems for Social Agents

In order to build dialogue systems to tackle the ambitious task of holding social conversations, we argue that we need a data driven approach that includes insight into human conversational chit chat, and which incorporates different natural language processing modules. Our strategy is to analyze and index large corpora of social media data, including Twitter conversations, online debates, dialogues between friends, and blog posts, and then to couple this data retrieval with modules that perform tasks such as sentiment and style analysis, topic modeling, and summarization. We aim for personal assistants that can learn more nuanced human language, and to grow from task-oriented agents to more personable social bots.

Learning Lexico-Functional Patterns for First-Person Affect

Informal first-person narratives are a unique resource for computational models of everyday events and peoples affective reactions to them. People blogging about their day tend not to explicitly say I am happy. Instead they describe situations from which other humans can readily infer their affective reactions. However current sentiment dictionaries are missing much of the information needed to make similar inferences. We build on recent work that models affect in terms of lexical predicate functions and affect on the predicates arguments. We present a method to learn proxies for these functions from first-person narratives. We construct a novel fine-grained test set, and show that the patterns we learn improve our ability to predict first-person affective reactions to everyday events, from a Stanford sentiment baseline of .67F to .75F.

Characterizing and Modeling Linguistic Style in Dialogue for Intelligent Social Agents

With increasing interest in the development of intelligent agents capable of learning, proficiently automating tasks, and gaining world knowledge, the importance of integrating the ability to converse naturally with users is more crucial now than ever before. This thesis aims to understand and characterize different aspects of social language to facilitate the development of intelligent agents that are socially aware and able to engage users to a level that was not previously possible with language generation systems. Using various machine learning algorithms and data-driven approaches to model the nuances of social language in dialogue, such as factual and emotional expression, sarcasm and humor and the related subclasses of rhetorical questions and hyperbole, we can come closer to modeling the characteristics of the social language that allows us to express emotion and knowledge, and thereby exhibit these styles in the agents we develop.