Marilyn Walker
YOU?
Author Swipe
View article: The RATT PARROT: serendipitous discovery of a peculiarly scintillating pulsar in MeerKAT imaging observations of the Great Saturn – Jupiter Conjunction of 2020. I. Dynamic imaging and data analysis
The RATT PARROT: serendipitous discovery of a peculiarly scintillating pulsar in MeerKAT imaging observations of the Great Saturn – Jupiter Conjunction of 2020. I. Dynamic imaging and data analysis Open
We report on a radiopolarimetric observation of the Saturn–Jupiter Great Conjunction of 2020 using the MeerKAT L-band system, initially carried out for science verification purposes, which yielded a serendipitous discovery of a pulsar. The…
View article: Knowledge-Grounded Dialogue Act Transfer using Prompt-Based Learning for Controllable Open-Domain NLG
Knowledge-Grounded Dialogue Act Transfer using Prompt-Based Learning for Controllable Open-Domain NLG Open
Open domain spoken dialogue systems need to controllably generate many different dialogue acts (DAs) to allow Natural Language Generation (NLG) to create interesting and engaging conversational interactions with users. We aim to create an …
View article: Athena 2.0: Discourse and User Modeling in Open Domain Dialogue
Athena 2.0: Discourse and User Modeling in Open Domain Dialogue Open
Conversational agents are consistently growing in popularity and many people interact with them every day. While many conversational agents act as personal assistants, they can have many different goals. Some are task-oriented, such as pro…
View article: Controllable Generation of Dialogue Acts for Dialogue Systems via Few-Shot Response Generation and Ranking
Controllable Generation of Dialogue Acts for Dialogue Systems via Few-Shot Response Generation and Ranking Open
Dialogue systems need to produce responses that realize multiple types of dialogue acts (DAs) with high semantic fidelity. In the past, natural language generators (NLGs) for dialogue were trained on large parallel corpora that map from a …
View article: Let's Get Personal: Personal Questions Improve SocialBot Performance in the Alexa Prize
Let's Get Personal: Personal Questions Improve SocialBot Performance in the Alexa Prize Open
There has been an increased focus on creating conversational open-domain dialogue systems in the spoken dialogue community. Unlike traditional dialogue systems, these conversational systems cannot assume any specific information need or do…
View article: Dependency Dialogue Acts -- Annotation Scheme and Case Study
Dependency Dialogue Acts -- Annotation Scheme and Case Study Open
In this paper, we introduce Dependency Dialogue Acts (DDA), a novel framework for capturing the structure of speaker-intentions in multi-party dialogues. DDA combines and adapts features from existing dialogue annotation frameworks, and em…
View article: Controlling Personality Style in Dialogue with Zero-Shot Prompt-Based Learning
Controlling Personality Style in Dialogue with Zero-Shot Prompt-Based Learning Open
Prompt-based or in-context learning has achieved high zero-shot performance on many natural language generation (NLG) tasks. Here we explore the performance of prompt-based learning for simultaneously controlling the personality and the se…
View article: Improving Open-Domain Dialogue Evaluation with a Causal Inference Model
Improving Open-Domain Dialogue Evaluation with a Causal Inference Model Open
Effective evaluation methods remain a significant challenge for research on open-domain conversational dialogue systems. Explicit satisfaction ratings can be elicited from users, but users often do not provide ratings when asked, and those…
View article: Controllable Generation of Dialogue Acts for Dialogue Systems via Few-Shot Response Generation and Ranking
Controllable Generation of Dialogue Acts for Dialogue Systems via Few-Shot Response Generation and Ranking Open
Dialogue systems need to produce responses that realize multiple types of dialogue acts (DAs) with high semantic fidelity. In the past, natural language generators (NLGs) for dialogue were trained on large parallel corpora that map from a …
View article: Modeling Performance in Open-Domain Dialogue with PARADISE
Modeling Performance in Open-Domain Dialogue with PARADISE Open
There has recently been an explosion of work on spoken dialogue systems, along with an increased interest in open-domain systems that engage in casual conversations on popular topics such as movies, books and music. These systems aim to so…
View article: Jurassic is (almost) All You Need: Few-Shot Meaning-to-Text Generation for Open-Domain Dialogue
Jurassic is (almost) All You Need: Few-Shot Meaning-to-Text Generation for Open-Domain Dialogue Open
One challenge with open-domain dialogue systems is the need to produce truthful, high-quality responses on any topic. We aim to improve the quality and coverage of Athena, an Alexa Prize dialogue system. We experiment with few-shot prompt-…
View article: Attention Is Indeed All You Need: Semantically Attention-Guided Decoding for Data-to-Text NLG
Attention Is Indeed All You Need: Semantically Attention-Guided Decoding for Data-to-Text NLG Open
Ever since neural models were adopted in data-to-text language generation, they have invariably been reliant on extrinsic components to improve their semantic accuracy, because the models normally do not exhibit the ability to generate tex…
View article: Referential Communication Between Friends and Strangers in the Wild
Referential Communication Between Friends and Strangers in the Wild Open
The Map Task (Anderson et al., 1991) and Tangram Task (Clark & Wilkes-Gibbs, 1986) are traditional referential communication tasks that are used in psycholinguistics research to demonstrate how conversational partners mutually agree on des…
View article: Attention Is Indeed All You Need: Semantically Attention-Guided Decoding for Data-to-Text NLG
Attention Is Indeed All You Need: Semantically Attention-Guided Decoding for Data-to-Text NLG Open
Ever since neural models were adopted in data-to-text language generation, they have invariably been reliant on extrinsic components to improve their semantic accuracy, because the models normally do not exhibit the ability to generate tex…
View article: Athena 2.0: Contextualized Dialogue Management for an Alexa Prize SocialBot
Athena 2.0: Contextualized Dialogue Management for an Alexa Prize SocialBot Open
Marilyn Walker, Vrindavan Harrison, Juraj Juraska, Lena Reed, Kevin Bowden, Wen Cui, Omkar Patil, Adwait Ratnaparkhi. Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing: System Demonstrations. 2021.
View article: Learning from Mistakes: Combining Ontologies via Self-Training for\n Dialogue Generation
Learning from Mistakes: Combining Ontologies via Self-Training for\n Dialogue Generation Open
Natural language generators (NLGs) for task-oriented dialogue typically take\na meaning representation (MR) as input. They are trained end-to-end with a\ncorpus of MR/utterance pairs, where the MRs cover a specific set of dialogue\nacts an…
View article: Learning from Mistakes: Combining Ontologies via Self-Training for Dialogue Generation
Learning from Mistakes: Combining Ontologies via Self-Training for Dialogue Generation Open
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, where the MRs cover a specific set of dialogue acts and d…
View article: Entertaining and Opinionated but Too Controlling: A Large-Scale User Study of an Open Domain Alexa Prize System
Entertaining and Opinionated but Too Controlling: A Large-Scale User Study of an Open Domain Alexa Prize System Open
Conversational systems typically focus on functional tasks such as scheduling appointments or creating todo lists. Instead we design and evaluate SlugBot (SB), one of 8 semifinalists in the 2018 AlexaPrize, whose goal is to support casual …
View article: SlugBot: Developing a Computational Model andFramework of a Novel Dialogue Genre
SlugBot: Developing a Computational Model andFramework of a Novel Dialogue Genre Open
One of the most interesting aspects of the Amazon Alexa Prize competition is that the framing of the competition requires the development of new computational models of dialogue and its structure. Traditional computational models of dialog…
View article: Implicit Discourse Relation Identification for Open-domain Dialogues
Implicit Discourse Relation Identification for Open-domain Dialogues Open
Discourse relation identification has been an active area of research for many years, and the challenge of identifying implicit relations remains largely an unsolved task, especially in the context of an open-domain dialogue system. Previo…
View article: A Narrative Sentence Planner and Structurer for Domain Independent, Parameterizable Storytelling
A Narrative Sentence Planner and Structurer for Domain Independent, Parameterizable Storytelling Open
Storytelling is an integral part of daily life and a key part of how we share information and connect with others. The ability to use Natural Language Generation (NLG) to produce stories that are tailored and adapted to the individual read…
View article: Curate and Generate: A Corpus and Method for Joint Control of Semantics and Style in Neural NLG
Curate and Generate: A Corpus and Method for Joint Control of Semantics and Style in Neural NLG Open
Neural natural language generation (NNLG) from structured meaning representations has become increasingly popular in recent years. While we have seen progress with generating syntactically correct utterances that preserve semantics, variou…
View article: ViGGO: A Video Game Corpus for Data-To-Text Generation in Open-Domain Conversation
ViGGO: A Video Game Corpus for Data-To-Text Generation in Open-Domain Conversation Open
The uptake of deep learning in natural language generation (NLG) led to the release of both small and relatively large parallel corpora for training neural models. The existing data-to-text datasets are, however, aimed at task-oriented dia…
View article: Maximizing Stylistic Control and Semantic Accuracy in NLG: Personality Variation and Discourse Contrast
Maximizing Stylistic Control and Semantic Accuracy in NLG: Personality Variation and Discourse Contrast Open
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. While earlier work focused sol…
View article: Implicit Discourse Relation Identification for Open-domain Dialogues
Implicit Discourse Relation Identification for Open-domain Dialogues Open
Discourse relation identification has been an active area of research for many years, and the challenge of identifying implicit relations remains largely an unsolved task, especially in the context of an open-domain dialogue system. Previo…
View article: Characterizing Variation in Crowd-Sourced Data for Training Neural Language Generators to Produce Stylistically Varied Outputs
Characterizing Variation in Crowd-Sourced Data for Training Neural Language Generators to Produce Stylistically Varied Outputs Open
One of the biggest challenges of end-to-end language generation from meaning representations in dialogue systems is making the outputs more natural and varied. Here we take a large corpus of 50K crowd-sourced utterances in the restaurant d…
View article: Neural Generation of Diverse Questions using Answer Focus, Contextual\n and Linguistic Features
Neural Generation of Diverse Questions using Answer Focus, Contextual\n and Linguistic Features Open
Question Generation is the task of automatically creating questions from\ntextual input. In this work we present a new Attentional Encoder--Decoder\nRecurrent Neural Network model for automatic question generation. Our model\nincorporates …
View article: Neural MultiVoice Models for Expressing Novel Personalities in Dialog
Neural MultiVoice Models for Expressing Novel Personalities in Dialog Open
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. While the use of neural generation fo…