no code implementations • 9 Oct 2024 • Thomas Palmeira Ferraz, Kartik Mehta, Yu-Hsiang Lin, Haw-Shiuan Chang, Shereen Oraby, Sijia Liu, Vivek Subramanian, Tagyoung Chung, Mohit Bansal, Nanyun Peng
To address the performance gap between open-source and proprietary models, we propose the Decompose, Critique and Refine (DeCRIM) self-correction pipeline, which enhances LLMs' ability to follow constraints.
1 code implementation • 30 May 2023 • Yufei Tian, Anjali Narayan-Chen, Shereen Oraby, Alessandra Cervone, Gunnar Sigurdsson, Chenyang Tao, Wenbo Zhao, YiWen Chen, Tagyoung Chung, Jing Huang, Nanyun Peng
Automatic melody-to-lyric generation is a task in which song lyrics are generated to go with a given melody.
no code implementations • 12 May 2023 • Yufei Tian, Anjali Narayan-Chen, Shereen Oraby, Alessandra Cervone, Gunnar Sigurdsson, Chenyang Tao, Wenbo Zhao, Tagyoung Chung, Jing Huang, Nanyun Peng
At inference time, we leverage the crucial alignments between melody and lyrics and compile the given melody into constraints to guide the generation process.
1 code implementation • 24 Oct 2022 • Jiao Sun, Anjali Narayan-Chen, Shereen Oraby, Shuyang Gao, Tagyoung Chung, Jing Huang, Yang Liu, Nanyun Peng
In this work, we propose a new task, context-situated pun generation, where a specific context represented by a set of keywords is provided, and the task is to first identify suitable pun words that are appropriate for the context, then generate puns based on the context keywords and the identified pun words.
1 code implementation • 24 Oct 2022 • Jiao Sun, Anjali Narayan-Chen, Shereen Oraby, Alessandra Cervone, Tagyoung Chung, Jing Huang, Yang Liu, Nanyun Peng
The tasks of humor understanding and generation are challenging and subjective even for humans, requiring commonsense and real-world knowledge to master.
no code implementations • EMNLP (NLP4ConvAI) 2021 • Alicia Y. Tsai, Shereen Oraby, Vittorio Perera, Jiun-Yu Kao, Yuheng Du, Anjali Narayan-Chen, Tagyoung Chung, Dilek Hakkani-Tur
Our results show that while high style accuracy and semantic correctness are easier to achieve for more lexically-defined styles with conditional training, stylistic control is also achievable for more semantically complex styles using discriminator-based guided decoding methods.
no code implementations • SIGDIAL (ACL) 2020 • Lena Reed, Vrindavan Harrison, Shereen Oraby, Dilek Hakkani-Tur, Marilyn Walker
Here we explore, for the first time, whether it is possible to train an NLG for a new larger ontology using existing training sets for the restaurant domain, where each set is based on a different ontology.
1 code implementation • INLG (ACL) 2020 • Yuheng Du, Shereen Oraby, Vittorio Perera, Minmin Shen, Anjali Narayan-Chen, Tagyoung Chung, Anu Venkatesh, Dilek Hakkani-Tur
We train different state-of-the-art models for neural natural language generation on this dataset and show that in many cases, including rich schema information allows our models to produce higher quality outputs both in terms of semantics and diversity.
no code implementations • WS 2019 • Vrindavan Harrison, Lena Reed, Shereen Oraby, Marilyn Walker
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 data describing a restaurant.
no code implementations • ACL 2019 • Shereen Oraby, Vrindavan Harrison, Abteen Ebrahimi, Marilyn Walker
Neural natural language generation (NNLG) from structured meaning representations has become increasingly popular in recent years.
no code implementations • WS 2018 • Lena Reed, Shereen Oraby, Marilyn Walker
While neural generation methods integrate sentence planning and surface realization in one end-to-end learning framework, previous work has not shown that neural generators can: (1) perform common sentence planning and discourse structuring operations; (2) make decisions as to whether to realize content in a single sentence or over multiple sentences; (3) generalize sentence planning and discourse relation operations beyond what was seen in training.
no code implementations • 5 Sep 2018 • Shereen Oraby, Lena Reed, Sharath TS, Shubhangi Tandon, Marilyn Walker
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 associated semantics.
no code implementations • WS 2018 • Shereen Oraby, Lena Reed, Shubhangi Tandon, T. S. Sharath, Stephanie Lukin, Marilyn Walker
We show that our most explicit model can simultaneously achieve high fidelity to both semantic and stylistic goals: this model adds a context vector of 36 stylistic parameters as input to the hidden state of the encoder at each time step, showing the benefits of explicit stylistic supervision, even when the amount of training data is large.
no code implementations • LREC 2018 • Kevin K. Bowden, Jiaqi Wu, Shereen Oraby, Amita Misra, Marilyn Walker
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 domain interaction where we cannot rely on domain-specific inference.
no code implementations • LREC 2018 • Marilyn A. Walker, Albry Smither, Shereen Oraby, Vrindavan Harrison, Hadar Shemtov
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, location and type of rooms.
no code implementations • E2E NLG Challenge System Descriptions 2018 • Shereen Oraby, Lena Reed, Shubhangi Tandon, Stephanie Lukin, Marilyn A. Walker
In the area of natural language generation (NLG), there has been a great deal of interest in end-to-end (E2E) neural models that learn and generate natural language sentence realizations in one step.
Ranked #7 on
Data-to-Text Generation
on E2E NLG Challenge
(using extra training data)
no code implementations • 4 Jan 2018 • Kevin K. Bowden, Jiaqi Wu, Shereen Oraby, Amita Misra, Marilyn Walker
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.
no code implementations • 31 Oct 2017 • Amita Misra, Shereen Oraby, Shubhangi Tandon, Sharath TS, Pranav Anand, Marilyn Walker
We show that we can identify the most important arguments by using the dialog context with a best F-measure of 0. 74 for gun control, 0. 71 for gay marriage, and 0. 67 for abortion.
no code implementations • 15 Sep 2017 • Kevin K. Bowden, Shereen Oraby, Jiaqi Wu, Amita Misra, Marilyn Walker
The greatest challenges in building sophisticated open-domain conversational agents arise directly from the potential for ongoing mixed-initiative multi-turn dialogues, which do not follow a particular plan or pursue a particular fixed information need.
no code implementations • WS 2016 • Shereen Oraby, Vrindavan Harrison, Lena Reed, Ernesto Hernandez, Ellen Riloff, Marilyn Walker
The use of irony and sarcasm in social media allows us to study them at scale for the first time.
no code implementations • 15 Sep 2017 • Shereen Oraby, Pritam Gundecha, Jalal Mahmud, Mansurul Bhuiyan, Rama Akkiraju
We characterize differences between customer and agent behavior in Twitter customer service conversations, and investigate the effect of testing our system on different customer service industries.
no code implementations • WS 2015 • Shereen Oraby, Lena Reed, Ryan Compton, Ellen Riloff, Marilyn Walker, Steve Whittaker
We investigate the characteristics of factual and emotional argumentation styles observed in online debates.
no code implementations • WS 2017 • Shereen Oraby, Vrindavan Harrison, Amita Misra, Ellen Riloff, Marilyn Walker
We present experiments to distinguish between these uses of RQs using SVM and LSTM models that represent linguistic features and post-level context, achieving results as high as 0. 76 F1 for "sarcastic" and 0. 77 F1 for "other" in forums, and 0. 83 F1 for both "sarcastic" and "other" in tweets.
no code implementations • WS 2017 • Shereen Oraby, Sheideh Homayon, Marilyn Walker
We learn hyperbolic adjective patterns that are representative of the strongly-valenced expressive language commonly used in either positive or negative reviews.
no code implementations • 10 Sep 2017 • Kevin K. Bowden, Shereen Oraby, Amita Misra, Jiaqi Wu, Stephanie Lukin
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.
no code implementations • ACL 2017 • Lena Reed, Jiaqi Wu, Shereen Oraby, Pranav Anand, Marilyn Walker
Informal first-person narratives are a unique resource for computational models of everyday events and people's affective reactions to them.