@inproceedings{georgila_comparing_2024,

title = {Comparing Pre-Trained Embeddings and Domain-Independent Features for Regression-Based Evaluation of Task-Oriented Dialogue Systems},

author = {Kallirroi Georgila},

url = {https://aclanthology.org/2024.sigdial-1.52},

doi = {10.18653/v1/2024.sigdial-1.52},

year  = {2024},

date = {2024-09-01},

urldate = {2024-10-15},

booktitle = {Proceedings of the 25th Annual Meeting of the Special Interest Group on Discourse and Dialogue},

pages = {610–623},

publisher = {Association for Computational Linguistics},

address = {Kyoto, Japan},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{artstein_augmenting_nodate,

title = {Augmenting Training Data for a Virtual Character Using GPT-3.5},

author = {Ron Artstein and Elizabeth Chen},

url = {https://journals.flvc.org/FLAIRS/article/view/135552},

year  = {2024},

date = {2024-05-13},

volume = {37},

publisher = {Tyhe Florida Artificial Intelligence Research Society},

abstract = {This paper compares different methods of using a large lan-guage model (GPT-3.5) for creating synthetic training datafor a retrieval-based conversational character. The trainingdata are in the form of linked questions and answers, whichallow a classifier to retrieve a pre-recorded answer to an un-seen question; the intuition is that a large language modelcould predict what human users might ask, thus saving theeffort of collecting real user questions as training data. Re-sults show small improvements in test performance for allsynthetic datasets. However, a classifier trained on only smallamounts of collected user data resulted in a higher F-scorethan the classifiers trained on much larger amounts of syn-thetic data generated using GPT-3.5. Based on these results,we see a potential in using large language models for gener-ating training data, but at this point it is not as valuable ascollecting actual user data for training.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{georgila_evaluation_2024,

title = {Evaluation of Off-the-shelf Whisper Models for Speech Recognition Across Diverse Dialogue Domains},

author = {Kallirroi Georgila and David Traum},

url = {chrome-extension://efaidnbmnnnibpcajpcglclefindmkaj/https://kgeorgila.github.io/publications/georgila_iwsds24.pdf},

year  = {2024},

date = {2024-03-01},

booktitle = {Proceedings of the 14th International Workshop on Spoken Dialogue Systems Technology},

address = {Sapporo, Japan},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{harris_im_2024,

title = {I’m not sure I heard you right, but I think I know what you mean – investigations into the impact of speech recognition errors on response selection for a virtual human.},

author = {Vera Harris and Robert Braggs and David Traum},

url = {chrome-extension://efaidnbmnnnibpcajpcglclefindmkaj/https://people.ict.usc.edu/~traum/Papers/23-harris-iwsds2024.pdf},

year  = {2024},

date = {2024-03-01},

address = {Sapporo Japan},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{brixey_why_2024,

title = {Why should a dialogue system speak more than one language?},

author = {Jacqueline Brixey and David Traum},

url = {chrome-extension://efaidnbmnnnibpcajpcglclefindmkaj/https://people.ict.usc.edu/~traum/Papers/24-Why%20should%20a%20dialogue%20system%20speak%20more%20than%20one%20language.pdf},

year  = {2024},

date = {2024-03-01},

address = {Sapporo Japan},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{nasihati_gilani_multimodal_2023,

title = {Multimodal Prediction of User's Performance in High-Stress Dialogue Interactions},

author = {Setareh Nasihati Gilani and Kimberly Pollard and David Traum},

url = {https://dl.acm.org/doi/10.1145/3610661.3617166},

doi = {10.1145/3610661.3617166},

isbn = {979-8-4007-0321-8},

year  = {2023},

date = {2023-10-01},

urldate = {2023-12-07},

booktitle = {International Cconference on Multimodal Interaction},

pages = {71–75},

publisher = {ACM},

address = {Paris France},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{gainer_divis_2023,

title = {DIVIS: Digital Interactive Victim Intake Simulator},

author = {Alesia Gainer and Allison Aptaker and Ron Artstein and David Cobbins and Mark Core and Carla Gordon and Anton Leuski and Zongjian Li and Chirag Merchant and David Nelson and Mohammad Soleymani and David Traum},

url = {https://dl.acm.org/doi/10.1145/3570945.3607328},

doi = {10.1145/3570945.3607328},

isbn = {978-1-4503-9994-4},

year  = {2023},

date = {2023-09-01},

urldate = {2024-02-20},

booktitle = {Proceedings of the 23rd ACM International Conference on Intelligent Virtual Agents},

pages = {1–2},

publisher = {ACM},

address = {Würzburg Germany},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{georgila_considerations_2023,

title = {Considerations for Child Speech Synthesis for Dialogue Systems},

author = {Kallirroi Georgila},

url = {https://kgeorgila.github.io/publications/georgila_aiaic23.pdf},

year  = {2023},

date = {2023-03-01},

address = {Los Angeles, CA},

abstract = {We present a number of important issues for consideration with regard to child speech synthesis for dialogue systems. We specifically discuss challenges in building child synthetic voices compared to adult synthetic voices, synthesizing expressive conversational speech, and evaluating speech synthesis quality.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{brixey_towards_2022,

title = {Towards an Automatic Speech Recognizer for the Choctaw language},

author = {Jacqueline Brixey and David Traum},

url = {https://www.isca-speech.org/archive/s4sg_2022/brixey22_s4sg.html},

doi = {10.21437/S4SG.2022-2},

year  = {2022},

date = {2022-09-01},

urldate = {2023-03-31},

booktitle = {1st Workshop on Speech for Social Good (S4SG)},

pages = {6–9},

publisher = {ISCA},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{georgila_comparing_2022,

title = {Comparing Regression Methods for Dialogue System Evaluation on a Richly Annotated Corpus},

author = {Kallirroi Georgila},

url = {http://semdial.org/anthology/papers/Z/Z22/Z22-3011/},

year  = {2022},

date = {2022-08-01},

urldate = {2023-03-31},

booktitle = {Proceedings of the 26th Workshop on the Semantics and Pragmatics of Dialogue - Full Papers},

abstract = {Wecompare various state-of-the-art regression methods for predicting user ratings of their interaction with a dialogue system using a richly annotated corpus. We vary the size of the training data and, in particular for kernel-based methods, we vary the type of kernel used. Furthermore, we experiment with various domainindependent features, including feature combinations that do not rely on complex annotations. We present detailed results in terms of root mean square error, and Pearson’s r and Spearman’s ρ correlations. Our results show that in many cases Gaussian Process Regression leads to modest but statistically significant gains compared to Support Vector Regression (a strong baseline), and that the type of kernel used matters. The gains are even larger when compared to linear regression. The larger the training data set the higher the gains but for some cases more data may result in over-fitting. Finally, some feature combinations work better than others but overall the best results are obtained when all features are used.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{speggiorin_taskmad_2022,

title = {TaskMAD: A Platform for Multimodal Task-Centric Knowledge-Grounded Conversational Experimentation},

author = {Alessandro Speggiorin and Jeffrey Dalton and Anton Leuski},

url = {https://dl.acm.org/doi/10.1145/3477495.3531679},

doi = {10.1145/3477495.3531679},

isbn = {978-1-4503-8732-3},

year  = {2022},

date = {2022-07-01},

urldate = {2022-09-22},

booktitle = {Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval},

pages = {3240–3244},

publisher = {ACM},

address = {Madrid Spain},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{tur_comparing_2022,

title = {Comparing Approaches to Language Understanding for Human-Robot Dialogue: An Error Taxonomy and Analysis},

author = {Ada Tur and David Traum},

url = {https://aclanthology.org/2022.lrec-1.625},

year  = {2022},

date = {2022-06-01},

urldate = {2023-02-10},

booktitle = {Proceedings of the Thirteenth Language Resources and Evaluation Conference},

pages = {5813–5820},

publisher = {European Language Resources Association},

address = {Marseille, France},

abstract = {In this paper, we compare two different approaches to language understanding for a human-robot interaction domain in which a human commander gives navigation instructions to a robot. We contrast a relevance-based classifier with a GPT-2 model, using about 2000 input-output examples as training data. With this level of training data, the relevance-based model outperforms the GPT-2 based model 79% to 8%. We also present a taxonomy of types of errors made by each model, indicating that they have somewhat different strengths and weaknesses, so we also examine the potential for a combined model.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{tadimeti_evaluation_2022,

title = {Evaluation of Off-the-shelf Speech Recognizers on Different Accents in a Dialogue Domain},

author = {Divya Tadimeti and Kallirroi Georgila and David Traum},

url = {https://aclanthology.org/2022.lrec-1.645},

year  = {2022},

date = {2022-06-01},

booktitle = {Proceedings of the Language Resources and Evaluation Conference},

pages = {6001–6008},

publisher = {European Language Resources Association},

address = {Marseille, France},

abstract = {We evaluate several publicly available off-the-shelf (commercial and research) automatic speech recognition (ASR) systems on dialogue agent-directed English speech from speakers with General American vs. non-American accents. Our results show that the performance of the ASR systems for non-American accents is considerably worse than for General American accents. Depending on the recognizer, the absolute difference in performance between General American accents and all non-American accents combined can vary approximately from 2% to 12%, with relative differences varying approximately between 16% and 49%. This drop in performance becomes even larger when we consider specific categories of non-American accents indicating a need for more diligent collection of and training on non-native English speaker data in order to narrow this performance gap. There are performance differences across ASR systems, and while the same general pattern holds, with more errors for non-American accents, there are some accents for which the best recognizer is different than in the overall case. We expect these results to be useful for dialogue system designers in developing more robust inclusive dialogue systems, and for ASR providers in taking into account performance requirements for different accents.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{karkada_strategy-level_2022,

title = {Strategy-level Entrainment of Dialogue System Users in a Creative Visual Reference Resolution Task},

author = {Deepthi Karkada and Ramesh Manuvinakurike and Maike Paetzel-Prüsmann and Kallirroi Georgila},

url = {https://aclanthology.org/2022.lrec-1.620},

year  = {2022},

date = {2022-06-01},

urldate = {2023-03-31},

booktitle = {Proceedings of the Thirteenth Language Resources and Evaluation Conference},

pages = {5768–5777},

publisher = {European Language Resources Association},

address = {Marseille, France},

abstract = {In this work, we study entrainment of users playing a creative reference resolution game with an autonomous dialogue system. The language understanding module in our dialogue system leverages annotated human-wizard conversational data, openly available knowledge graphs, and crowd-augmented data. Unlike previous entrainment work, our dialogue system does not attempt to make the human conversation partner adopt lexical items in their dialogue, but rather to adapt their descriptive strategy to one that is simpler to parse for our natural language understanding unit. By deploying this dialogue system through a crowd-sourced study, we show that users indeed entrain on a “strategy-level” without the change of strategy impinging on their creativity. Our work thus presents a promising future research direction for developing dialogue management systems that can strategically influence people's descriptive strategy to ease the system's language understanding in creative tasks.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{johnson_using_2021,

title = {Using Intelligent Agents to Examine Gender in Negotiations},

author = {Emmanuel Johnson and Jonathan Gratch and Jill Boberg and David DeVault and Peter Kim and Gale Lucas},

url = {https://dl.acm.org/doi/10.1145/3472306.3478348},

doi = {10.1145/3472306.3478348},

isbn = {978-1-4503-8619-7},

year  = {2021},

date = {2021-09-01},

urldate = {2022-09-28},

booktitle = {Proceedings of the 21th ACM International Conference on Intelligent Virtual Agents},

pages = {90–97},

publisher = {ACM},

address = {Virtual Event Japan},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{bonial_context_2021,

title = {Context is key: Annotating situated dialogue relations in multi-floor dialogue},

author = {Claire Bonial and Mitchell Abrams and Anthony L. Baker and Taylor Hudson and Stephanie Lukin and David Traum and Clare Voss},

url = {http://semdial.org/anthology/papers/Z/Z21/Z21-3006/},

year  = {2021},

date = {2021-09-01},

urldate = {2022-09-23},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{chaffey_identity_2021,

title = {Identity models for role-play dialogue characters},

author = {Patricia Chaffey and David Traum},

url = {http://semdial.org/anthology/papers/Z/Z21/Z21-4022/},

year  = {2021},

date = {2021-09-01},

urldate = {2022-09-23},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{bonial_builder_2021,

title = {Builder, we have done it: Evaluating & Extending Dialogue-AMR NLU Pipeline for Two Collaborative Domains},

author = {Claire Bonial and Mitchell Abrams and David Traum and Clare Voss},

url = {https://aclanthology.org/2021.iwcs-1.17},

year  = {2021},

date = {2021-06-01},

urldate = {2022-09-23},

booktitle = {Proceedings of the 14th International Conference on Computational Semantics (IWCS)},

pages = {173–183},

publisher = {Association for Computational Linguistics},

address = {Groningen, The Netherlands (online)},

abstract = {We adopt, evaluate, and improve upon a two-step natural language understanding (NLU) pipeline that incrementally tames the variation of unconstrained natural language input and maps to executable robot behaviors. The pipeline first leverages Abstract Meaning Representation (AMR) parsing to capture the propositional content of the utterance, and second converts this into “Dialogue-AMR,” which augments standard AMR with information on tense, aspect, and speech acts. Several alternative approaches and training datasets are evaluated for both steps and corresponding components of the pipeline, some of which outperform the original. We extend the Dialogue-AMR annotation schema to cover a different collaborative instruction domain and evaluate on both domains. With very little training data, we achieve promising performance in the new domain, demonstrating the scalability of this approach.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{kawano_dialogue_2021,

title = {Dialogue Structure Parsing on Multi-Floor Dialogue Based on Multi-Task Learning},

author = {Seiya Kawano and Koichiro Yoshino and David Traum and Satoshi Nakamura},

url = {http://www.isca-speech.org/archive/RobotDial_2021/abstracts/4.html},

doi = {10.21437/RobotDial.2021-4},

year  = {2021},

date = {2021-01-01},

urldate = {2021-04-15},

booktitle = {1st RobotDial Workshop on Dialogue Models for Human-Robot Interaction},

pages = {21–29},

publisher = {ISCA},

abstract = {A multi-floor dialogue consists of multiple sets of dialogue participants, each conversing within their own floor, but also at least one multicommunicating member who is a participant of multiple floors and coordinating each to achieve a shared dialogue goal. The structure of such dialogues can be complex, involving intentional structure and relations that are within or across floors. In this study, we propose a neural dialogue structure parser based on multi-task learning and an attention mechanism on multi-floor dialogues in a collaborative robot navigation domain. Our experimental results show that our proposed model improved the dialogue structure parsing performance more than those of single models, which are trained on each dialogue structure parsing task in multi-floor dialogues.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{czyzewski_agent_2020,

title = {Agent Dialogue: A Platform for Conversational Information Seeking Experimentation},

author = {Adam Czyzewski and Jeffrey Dalton and Anton Leuski},

url = {https://dl.acm.org/doi/10.1145/3397271.3401397},

doi = {10.1145/3397271.3401397},

isbn = {978-1-4503-8016-4},

year  = {2020},

date = {2020-07-01},

booktitle = {Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval},

pages = {2121–2124},

publisher = {ACM},

address = {Virtual Event China},

abstract = {Conversational Information Seeking (CIS) is an emerging area of Information Retrieval focused on interactive search systems. As a result there is a need for new benchmark datasets and tools to enable their creation. In this demo we present the Agent Dialogue (AD) platform, an open-source system developed for researchers to perform Wizard-of-Oz CIS experiments. AD is a scalable cloud-native platform developed with Docker and Kubernetes with a flexible and modular micro-service architecture built on production-grade stateof-the-art open-source tools (Kubernetes, gRPC streaming, React, and Firebase). It supports varied front-ends and has the ability to interface with multiple existing agent systems, including Google Assistant and open-source search libraries. It includes support for centralized structure logging as well as offline relevance annotation.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{georgila_predicting_2020,

title = {Predicting Ratings of Real Dialogue Participants from Artificial Data and Ratings of Human Dialogue Observers},

author = {Kallirroi Georgila and Carla Gordon and Volodymyr Yanov and David Traum},

url = {https://aclanthology.org/2020.lrec-1.91},

isbn = {979-10-95546-34-4},

year  = {2020},

date = {2020-05-01},

urldate = {2023-03-31},

booktitle = {Proceedings of the Twelfth Language Resources and Evaluation Conference},

pages = {726–734},

publisher = {European Language Resources Association},

address = {Marseille, France},

abstract = {We collected a corpus of dialogues in a Wizard of Oz (WOz) setting in the Internet of Things (IoT) domain. We asked users participating in these dialogues to rate the system on a number of aspects, namely, intelligence, naturalness, personality, friendliness, their enjoyment, overall quality, and whether they would recommend the system to others. Then we asked dialogue observers, i.e., Amazon Mechanical Turkers (MTurkers), to rate these dialogues on the same aspects. We also generated simulated dialogues between dialogue policies and simulated users and asked MTurkers to rate them again on the same aspects. Using linear regression, we developed dialogue evaluation functions based on features from the simulated dialogues and the MTurkers' ratings, the WOz dialogues and the MTurkers' ratings, and the WOz dialogues and the WOz participants' ratings. We applied all these dialogue evaluation functions to a held-out portion of our WOz dialogues, and we report results on the predictive power of these different types of dialogue evaluation functions. Our results suggest that for three conversational aspects (intelligence, naturalness, overall quality) just training evaluation functions on simulated data could be sufficient.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{bonial_dialogue-amr_2020,

title = {Dialogue-AMR: Abstract Meaning Representation for Dialogue},

author = {Claire Bonial and Lucia Donatelli and Mitchell Abrams and Stephanie M Lukin and Stephen Tratz and Matthew Marge and Ron Artstein and David Traum and Clare R Voss},

url = {https://www.aclweb.org/anthology/2020.lrec-1.86/},

year  = {2020},

date = {2020-05-01},

booktitle = {Proceedings of the 12th Language Resources and Evaluation Conference},

pages = {12},

publisher = {European Language Resources Association},

address = {Marseille, France},

abstract = {This paper describes a schema that enriches Abstract Meaning Representation (AMR) in order to provide a semantic representation for facilitating Natural Language Understanding (NLU) in dialogue systems. AMR offers a valuable level of abstraction of the propositional content of an utterance; however, it does not capture the illocutionary force or speaker’s intended contribution in the broader dialogue context (e.g., make a request or ask a question), nor does it capture tense or aspect. We explore dialogue in the domain of human-robot interaction, where a conversational robot is engaged in search and navigation tasks with a human partner. To address the limitations of standard AMR, we develop an inventory of speech acts suitable for our domain, and present “Dialogue-AMR”, an enhanced AMR that represents not only the content of an utterance, but the illocutionary force behind it, as well as tense and aspect. To showcase the coverage of the schema, we use both manual and automatic methods to construct the “DialAMR” corpus—a corpus of human-robot dialogue annotated with standard AMR and our enriched Dialogue-AMR schema. Our automated methods can be used to incorporate AMR into a larger NLU pipeline supporting human-robot dialogue.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{alavi_which_2020,

title = {Which Model Should We Use for a Real-World Conversational Dialogue System? a Cross-Language Relevance Model or a Deep Neural Net?},

author = {Seyed Hossein Alavi and Anton Leuski and David Traum},

url = {https://www.aclweb.org/anthology/2020.lrec-1.92/},

year  = {2020},

date = {2020-05-01},

booktitle = {Proceedings of the 12th Language Resources and Evaluation Conference},

pages = {735–742},

publisher = {European Language Resources Association},

address = {Marseille, France},

abstract = {We compare two models for corpus-based selection of dialogue responses: one based on cross-language relevance with a cross-language LSTM model. Each model is tested on multiple corpora, collected from two different types of dialogue source material. Results show that while the LSTM model performs adequately on a very large corpus (millions of utterances), its performance is dominated by the cross-language relevance model for a more moderate-sized corpus (ten thousands of utterances).},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{chaffey_human_2020,

title = {Human swarm interaction using plays, audibles, and a virtual spokesperson},

author = {Patricia Chaffey and Ron Artstein and Kallirroi Georgila and Kimberly A. Pollard and Setareh Nasihati Gilani and David M. Krum and David Nelson and Kevin Huynh and Alesia Gainer and Seyed Hossein Alavi and Rhys Yahata and Anton Leuski and Volodymyr Yanov and David Traum},

url = {https://www.spiedigitallibrary.org/conference-proceedings-of-spie/11413/2557573/Human-swarm-interaction-using-plays-audibles-and-a-virtual-spokesperson/10.1117/12.2557573.full},

doi = {10.1117/12.2557573},

isbn = {978-1-5106-3603-3 978-1-5106-3604-0},

year  = {2020},

date = {2020-04-01},

booktitle = {Proceedings of Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications II},

pages = {40},

publisher = {SPIE},

address = {Online Only, United States},

abstract = {This study explores two hypotheses about human-agent teaming: 1. Real-time coordination among a large set of autonomous robots can be achieved using predefined “plays” which define how to execute a task, and “audibles” which modify the play on the fly; 2. A spokesperson agent can serve as a representative for a group of robots, relaying information between the robots and human teammates. These hypotheses are tested in a simulated game environment: a human participant leads a search-and-rescue operation to evacuate a town threatened by an approaching wildfire, with the object of saving as many lives as possible. The participant communicates verbally with a virtual agent controlling a team of ten aerial robots and one ground vehicle, while observing a live map display with real-time location of the fire and identified survivors. Since full automation is not currently possible, two human controllers control the agent’s speech and actions, and input parameters to the robots, which then operate autonomously until the parameters are changed. Designated plays include monitoring the spread of fire, searching for survivors, broadcasting warnings, guiding residents to safety, and sending the rescue vehicle. A successful evacuation of all the residents requires personal intervention in some cases (e.g., stubborn residents) while delegating other responsibilities to the spokesperson agent and robots, all in a rapidly changing scene. The study records the participants’ verbal and nonverbal behavior in order to identify strategies people use when communicating with robotic swarms, and to collect data for eventual automation.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{shmueli-scheuer_user2agent_2020,

title = {user2agent: 2nd Workshop on User-Aware Conversational Agents},

author = {Michal Shmueli-Scheuer and Ron Artstein and Yasaman Khazaeni and Hao Fang and Q. Vera Liao},

url = {https://doi.org/10.1145/3379336.3379356},

doi = {10.1145/3379336.3379356},

isbn = {978-1-4503-7513-9},

year  = {2020},

date = {2020-03-01},

urldate = {2023-03-31},

booktitle = {Proceedings of the 25th International Conference on Intelligent User Interfaces Companion},

pages = {9–10},

publisher = {Association for Computing Machinery},

address = {New York, NY, USA},

series = {IUI '20},

abstract = {Conversational agents are becoming increasingly popular. These systems present an extremely rich and challenging research space for addressing many aspects of user awareness and adaptation, such as user profiles, contexts, personalities, emotions, social dynamics, conversational styles, etc. Adaptive interfaces are of long-standing interest for the HCI community. Meanwhile, new machine learning approaches are introduced in the current generation of conversational agents, such as deep learning, reinforcement learning, and active learning. It is imperative to consider how various aspects of user-awareness should be handled by these new techniques. The goal of this workshop is to bring together researchers in HCI, user modeling, and the AI and NLP communities from both industry and academia, who are interested in advancing the state-of-the-art on the topic of user-aware conversational agents. Through a focused and open exchange of ideas and discussions, we will work to identify central research topics in user-aware conversational agents and develop a strong interdisciplinary foundation to address them.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{georgila_evaluation_2020,

title = {Evaluation of Off-the-shelf Speech Recognizers Across Diverse Dialogue Domains},

author = {Kallirroi Georgila and Anton Leuski and Volodymyr Yanov and David Traum},

url = {https://aclanthology.org/2020.lrec-1.797.pdf},

year  = {2020},

date = {2020-01-01},

booktitle = {Proceedings of the Twelfth Language Resources and Evaluation Conference},

pages = {6469–6476},

publisher = {European Language Resources Association},

address = {Sapporo, Japan},

abstract = {We evaluate several publicly available off-the-shelf (commercial and research) automatic speech recognition (ASR) systems across diverse dialogue domains (in US-English). Our evaluation is aimed at non-experts with limited experience in speech recognition. Our goal is not only to compare a variety of ASR systems on several diverse data sets but also to measure how much ASR technology has advanced since our previous large-scale evaluations on the same data sets. Our results show that the performance of each speech recognizer can vary significantly depending on the domain. Furthermore, despite major recent progress in ASR technology, current state-of-the-art speech recognizers perform poorly in domains that require special vocabulary and language models, and under noisy conditions. We expect that our evaluation will prove useful to ASR consumers and dialogue system designers.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}