papers

Publications (29)

cs.CL2018

Controlling Personality-Based Stylistic Variation with Neural Natural Language Generators

Shereen Oraby, Lena Reed, Shubhangi Tandon +3

Natural language generators for task-oriented dialogue must effectively realize system dialogue actions and their associated semantics. In many applications, it is also desirable f…

cs.CL2017

Harvesting Creative Templates for Generating Stylistically Varied Restaurant Reviews

Shereen Oraby, Sheideh Homayon, Marilyn Walker

Many of the creative and figurative elements that make language exciting are lost in translation in current natural language generation engines. In this paper, we explore a method…

cs.AI2023

Unsupervised Melody-Guided Lyrics Generation

Yufei Tian, Anjali Narayan-Chen, Shereen Oraby +7

Automatic song writing is a topic of significant practical interest. However, its research is largely hindered by the lack of training data due to copyright concerns and challenged…

cs.CL2018

Can Neural Generators for Dialogue Learn Sentence Planning and Discourse Structuring?

Lena Reed, Shereen Oraby, Marilyn Walker

Responses in task-oriented dialogue systems often realize multiple propositions whose ultimate form depends on the use of sentence planning and discourse structuring operations. Fo…

cs.CL2017

And That's A Fact: Distinguishing Factual and Emotional Argumentation in Online Dialogue

Shereen Oraby, Lena Reed, Ryan Compton +3

We investigate the characteristics of factual and emotional argumentation styles observed in online debates. Using an annotated set of "factual" and "feeling" debate forum posts, w…

cs.CL2024

LLM Self-Correction with DeCRIM: Decompose, Critique, and Refine for Enhanced Following of Instructions with Multiple Constraints

Thomas Palmeira Ferraz, Kartik Mehta, Yu-Hsiang Lin +7

Instruction following is a key capability for LLMs. However, recent studies have shown that LLMs often struggle with instructions containing multiple constraints (e.g. a request to…

cs.CL2018

SlugNERDS: A Named Entity Recognition Tool for Open Domain Dialogue Systems

Kevin K. Bowden, Jiaqi Wu, Shereen Oraby +2

In dialogue systems, the tasks of named entity recognition (NER) and named entity linking (NEL) are vital preprocessing steps for understanding user intent, especially in open doma…

cs.CL2021

Style Control for Schema-Guided Natural Language Generation

Alicia Y. Tsai, Shereen Oraby, Vittorio Perera +5

Natural Language Generation (NLG) for task-oriented dialogue systems focuses on communicating specific content accurately, fluently, and coherently. While these attributes are cruc…

cs.CL2017

Are you serious?: Rhetorical Questions and Sarcasm in Social Media Dialog

Shereen Oraby, Vrindavan Harrison, Amita Misra +2

Effective models of social dialog must understand a broad range of rhetorical and figurative devices. Rhetorical questions (RQs) are a type of figurative language whose aim is to a…

cs.CL2020

Schema-Guided Natural Language Generation

Yuheng Du, Shereen Oraby, Vittorio Perera +5

Neural network based approaches to data-to-text natural language generation (NLG) have gained popularity in recent years, with the goal of generating a natural language prompt that…

cs.CL2020

Learning from Mistakes: Combining Ontologies via Self-Training for Dialogue Generation

Lena Reed, Vrindavan Harrison, Shereen Oraby +2

Natural language generators (NLGs) for task-oriented dialogue typically take a meaning representation (MR) as input. They are trained end-to-end with a corpus of MR/utterance pairs…

cs.CL2026

SaliMory: Orchestrating Cognitive Memory for Conversational Agents

Kai Zhang, Xinyuan Zhang, Hongda Jiang +11

Conversational agents that serve as lifelong companions must maintain persistent memory across all interactions. However, simply expanding context windows with raw retrieval degrad…

cs.CL2022

Context-Situated Pun Generation

Jiao Sun, Anjali Narayan-Chen, Shereen Oraby +5

Previous work on pun generation commonly begins with a given pun word (a pair of homophones for heterographic pun generation and a polyseme for homographic pun generation) and seek…

cs.CL2018

Slugbot: An Application of a Novel and Scalable Open Domain Socialbot Framework

Kevin K. Bowden, Jiaqi Wu, Shereen Oraby +2

In this paper we introduce a novel, open domain socialbot for the Amazon Alexa Prize competition, aimed at carrying on friendly conversations with users on a variety of topics. We…

cs.CL2022

ExPUNations: Augmenting Puns with Keywords and Explanations

Jiao Sun, Anjali Narayan-Chen, Shereen Oraby +5

The tasks of humor understanding and generation are challenging and subjective even for humans, requiring commonsense and real-world knowledge to master. Puns, in particular, add t…

cs.LG2025

FLAMES: Improving LLM Math Reasoning via a Fine-Grained Analysis of the Data Synthesis Pipeline

Parker Seegmiller, Kartik Mehta, Soumya Saha +6

Recent works improving LLM math reasoning with synthetic data have used unique setups, making comparison of data synthesis strategies impractical. This leaves many unanswered quest…

cs.CL2017

Creating and Characterizing a Diverse Corpus of Sarcasm in Dialogue

Shereen Oraby, Vrindavan Harrison, Lena Reed +3

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…

cs.CL2017

Learning Lexico-Functional Patterns for First-Person Affect

Lena Reed, Jiaqi Wu, Shereen Oraby +2

Informal first-person narratives are a unique resource for computational models of everyday events and people's affective reactions to them. People blogging about their day tend no…

cs.CL2018

Neural MultiVoice Models for Expressing Novel Personalities in Dialog

Shereen Oraby, Lena Reed, Sharath TS +2

Natural language generators for task-oriented dialog should be able to vary the style of the output utterance while still effectively realizing the system dialog actions and their…

cs.CL2017

Summarizing Dialogic Arguments from Social Media

Amita Misra, Shereen Oraby, Shubhangi Tandon +3

Online argumentative dialog is a rich source of information on popular beliefs and opinions that could be useful to companies as well as governmental or public policy agencies. Com…

cs.AI2025

The Amazon Nova Family of Models: Technical Report and Model Card

Amazon AGI, Aaron Langford, Aayush Shah +783

We present Amazon Nova, a new generation of state-of-the-art foundation models that deliver frontier intelligence and industry-leading price performance. Amazon Nova Pro is a highl…

cs.CL2017

Combining Search with Structured Data to Create a More Engaging User Experience in Open Domain Dialogue

Kevin K. Bowden, Shereen Oraby, Jiaqi Wu +2

The greatest challenges in building sophisticated open-domain conversational agents arise directly from the potential for ongoing mixed-initiative multi-turn dialogues, which do no…

cs.CL2023

Unsupervised Melody-to-Lyric Generation

Yufei Tian, Anjali Narayan-Chen, Shereen Oraby +8

Automatic melody-to-lyric generation is a task in which song lyrics are generated to go with a given melody. It is of significant practical interest and more challenging than uncon…

cs.CL2017

Data-Driven Dialogue Systems for Social Agents

Kevin K. Bowden, Shereen Oraby, Amita Misra +2

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 conve…

cs.CL2025

AssoMem: Scalable Memory QA with Multi-Signal Associative Retrieval

Kai Zhang, Xinyuan Zhang, Ejaz Ahmed +11

Accurate recall from large scale memories remains a core challenge for memory augmented AI assistants performing question answering (QA), especially in similarity dense scenarios w…

cs.CL2017

"How May I Help You?": Modeling Twitter Customer Service Conversations Using Fine-Grained Dialogue Acts

Shereen Oraby, Pritam Gundecha, Jalal Mahmud +2

Given the increasing popularity of customer service dialogue on Twitter, analysis of conversation data is essential to understand trends in customer and agent behavior for the purp…

cs.CL2019

Maximizing Stylistic Control and Semantic Accuracy in NLG: Personality Variation and Discourse Contrast

Vrindavan Harrison, Lena Reed, Shereen Oraby +1

Neural generation methods for task-oriented dialogue typically generate from a meaning representation that is populated using a database of domain information, such as a table of d…

cs.CL2019

Curate and Generate: A Corpus and Method for Joint Control of Semantics and Style in Neural NLG

Shereen Oraby, Vrindavan Harrison, Abteen Ebrahimi +1

Neural natural language generation (NNLG) from structured meaning representations has become increasingly popular in recent years. While we have seen progress with generating synta…

cs.CL2018

Exploring Conversational Language Generation for Rich Content about Hotels

Marilyn A. Walker, Albry Smither, Shereen Oraby +2

Dialogue systems for hotel and tourist information have typically simplified the richness of the domain, focusing system utterances on only a few selected attributes such as price,…