Stylistics

Deconstructing Human Assisted Video Transcription and Annotation for Legislative Proceedings

foaad — Mon, 15 Aug 2022 00:40:12 +0000

Deconstructing Human Assisted Video Transcription and Annotation for Legislative Proceedings foaad Sun, 08/14/2022 - 17:40

Authorship

Thorsten Ruprechter, Foaad Khosmood and Christian Gütl

Publication

Journal of Digital Government: Research and Practice

Journal

Wednesday, November 18, 2020 - 12:00

Tags

ACM DL

Abstract

Legislative proceedings present a rich source of multidimensional information that is crucial to citizens and journalists in a democratic system. At present, no fully automated solution exists that is capable of capturing all the necessary information during such proceedings. Even if professional-quality automated transcriptions existed, other tasks such as speaker or rhetorical position identifications are not fully automatable. This work focuses on improving and evaluating the transcription software used by the Digital Democracy initiative, named Transcription Tool.

An Empathetic AI Coach for Self-Attachment Therapy

foaad — Mon, 15 Aug 2022 00:29:17 +0000

An Empathetic AI Coach for Self-Attachment Therapy foaad Sun, 08/14/2022 - 17:29

Authorship

Lisa Alazraki, Ali Ghachem, Neophytos Polydorou, Foaad Khosmood

Publication

IEEE Third International Conference on Cognitive Machine Intelligence (CogMI)

Conference

Location

Atlanta, Georgia, USA

Monday, December 13, 2021 - 12:00

Tags

Imperial College

Abstract

In this work, we present a new dataset and a computational strategy for a digital coach that aims to guide users in practicing the protocols of self-attachment therapy. Our framework augments a rule-based conversational agent with a deep-learning classifier for identifying the underlying emotion in a user’s text response, as well as a deep-learning assisted retrieval method for producing novel, fluent and empathetic utterances. We also craft a set of human-like personas that users can choose to interact with.

Multimodal speaker identification in legislative discourse

foaad — Sun, 14 Aug 2022 03:10:03 +0000

Multimodal speaker identification in legislative discourse foaad Sat, 08/13/2022 - 20:10

Authorship

Daniel Kauffman, Michael Williams, Calin Washington, Gudrun Socher, and Foaad Khosmood

Publication

Proceedings of the 19th Annual International Conference on Digital Government Research: Governance in the Data Age

Conference

Location

Delft, Netherlands

Wednesday, May 30, 2018 - 12:00

Tags

ACM DL

Abstract

A first-of-its-kind platform, Digital Democracy1 offers a searchable archive of all statements made in US state legislative hearings in four American states (California, New York, Texas and Florida) covering one third of the US population. The purpose of the platform is to increase government transparency in state legislatures. It allows citizens to follow state lawmakers, lobbyists, and advocates as they debate, craft, and vote on policy proposals. State hearings in the U.S. are typically recorded on video and broadcast on cable TV stations, but they are not transcribed or indexed.

Comparison of Sentence-level Paraphrasing Approaches for Statistical Style Transformation

foaad — Wed, 22 Aug 2012 05:48:08 +0000

Comparison of Sentence-level Paraphrasing Approaches for Statistical Style Transformation foaad Tue, 08/21/2012 - 22:48

Authorship

Foaad Khosmood

Publication

International Conference on Artificial Intelligence (ICAI)

Conference

Location

Las Vegas, Nevada

Sunday, July 1, 2012 - 12:00

Tags

ICA3949.pdf

Combining Corpus-Based Features for Selecting Best Natural Language Sentences

foaad — Wed, 22 Aug 2012 05:43:15 +0000

Combining Corpus-Based Features for Selecting Best Natural Language Sentences foaad Tue, 08/21/2012 - 22:43

Authorship

Foaad Khosmood and Robert Levinson

Publication

International Conference on Machine Learning and Applications

Conference

Location

Honolulu, Hawaii

Thursday, December 1, 2011 - 12:00

Tags

Abstract

Automated paraphrasing of natural language text has many interesting applications from aiding in better translations to generating better and more appropriate style language. In this paper, we are concerned with the problem of picking the best English sentence out of a set of machine generated paraphrase sentences, each designed to express the same content as a human generated original. We present a system of scoring sentences based on examples in large corpora.

4607b362.pdf

Taxonomy and Evaluation of Markers for Computational Stylistics

foaad — Wed, 22 Aug 2012 05:30:32 +0000

Taxonomy and Evaluation of Markers for Computational Stylistics foaad Tue, 08/21/2012 - 22:30

Authorship

Foaad Khosmood and Robert Levinson

Publication

International Conference on Artificial Intelligence (ICAI)

Conference

Location

Las Vegas, Nevada

Friday, July 1, 2011 - 12:00

Tags

Abstract

Currently, stylistic analysis of natural language texts is achieved through a wide variety of techniques containing many different algorithms, feature sets and collection methods. Most machine-learning methods rely on feature extraction to model the text and perform classification. But what are the best features for making style based distinctions? While many researchers have developed particular collections of style features – called style markers – no definitive list exists.

icai-11-kl-final.pdf

Toward Automated Stylistic Transformation of Natural Language Text

foaad — Wed, 22 Aug 2012 04:55:25 +0000

Toward Automated Stylistic Transformation of Natural Language Text foaad Tue, 08/21/2012 - 21:55

Authorship

Foaad Khosmood and Robert Levinson

Publication

Digital Humanities

Conference

Location

University of Maryland College Park

Monday, June 1, 2009 - 12:00

Automatic Natural Language Style Classification and Transformation

foaad — Wed, 22 Aug 2012 04:52:58 +0000

Automatic Natural Language Style Classification and Transformation foaad Tue, 08/21/2012 - 21:52

Authorship

Foaad Khosmood and Robert Levinson

Publication

BCS Corpus Profiling Workshop

Workshop

Location

London, UK

Wednesday, October 1, 2008 - 12:00

Tags

researchgate archive

Khosmood_BCS_2008.pdf

Toward Unification of Source Attribution Processes and Techniques

foaad — Wed, 22 Aug 2012 04:50:31 +0000

Toward Unification of Source Attribution Processes and Techniques foaad Tue, 08/21/2012 - 21:50

Authorship

Foaad Khosmood and Robert Levinson

Publication

IEEE International Conference on Machine Learning and Cybernetics (ICMLC)

Conference

Location

Dalian, China

Tuesday, August 1, 2006 - 12:00

Automatic Source Attribution of Text: A Neural Networks Approach

foaad — Wed, 22 Aug 2012 04:46:50 +0000

Automatic Source Attribution of Text: A Neural Networks Approach foaad Tue, 08/21/2012 - 21:46

Authorship

Foaad Khosmood and Franz Kurfess

Publication

International Joint Conference on Neural Networks, IJCNN-05

Conference

Location

Montreal, Canada

Monday, August 1, 2005 - 12:00

Tags

Abstract

Recent advances in automatic authorship attribution have been promising. Relatively new techniques such as N-gram analysis have shown important improvements in accuracy. Much of the work in this area does remain in the realm of statistics best suited for human assistance rather than autonomous attribution. While there have been attempts at using neural networks in the area in the past, they have been extremely limited and problem-specific 171.