Casey Kennington
YOU?
Author Swipe
Could the Road to Grounded, Neuro-symbolic AI be Paved with Words-as-Classifiers? Open
Formal, Distributional, and Grounded theories of computational semantics each have their uses and their drawbacks. There has been a shift to ground models of language by adding visual knowledge, and there has been a call to enrich models o…
Prior Lessons of Incremental Dialogue and Robot Action Management for the Age of Language Models Open
Efforts towards endowing robots with the ability to speak have benefited from recent advancements in natural language processing, in particular large language models. However, current language models are not fully incremental, as their pro…
Precision or Peril: Evaluating Code Quality from Quantized Large Language Models Open
When scaled to hundreds of billions of parameters, Large Language Models (LLMs) such as GPT-4 and LLaMA-405b have demonstrated remarkable capabilities in tasks such as code generation, code completion, and writing test cases. However, scal…
Renaissance: Investigating the Pretraining of Vision-Language Encoders Open
In the past several years there has been an explosion of available models for vision-language tasks. Unfortunately, the literature still leaves open a number of questions related to best practices in designing and training such models. In …
Word Concreteness and Word Originality Open
Basque is the oldest known spoken language of Western Europe that is not descended from Indo-European. Despite efforts to stop its use from external influences, the Basque people have shown resiliency throughout their history to keep the l…
Unsupervised, Bottom-up Category Discovery for Symbol Grounding with a Curious Robot Open
Towards addressing the Symbol Grounding Problem and motivated by early childhood language development, we leverage a robot which has been equipped with an approximate model of curiosity with particular focus on bottom-up building of unsupe…
Dialogue with Robots: Proposals for Broadening Participation and Research in the SLIVAR Community Open
The ability to interact with machines using natural human language is becoming not just commonplace, but expected. The next step is not just text interfaces, but speech interfaces and not just with computers, but with all machines includin…
Understanding Survey Paper Taxonomy about Large Language Models via Graph Representation Learning Open
As new research on Large Language Models (LLMs) continues, it is difficult to keep up with new research and models. To help researchers synthesize the new research many have written survey papers, but even those have become numerous. In th…
Multi-Perspective Learning to Rank to Support Children's Information Seeking in the Classroom Open
We introduce a re-ranking model that augments the functionality of standard search engines to aid classroom search activities for children (ages 6–11). This model extends the known listwise learning-to-rank framework by balancing risk and …
A Multi-Perspective Learning to Rank Approach to Support Children's Information Seeking in the Classroom Open
We introduce a novel re-ranking model that aims to augment the functionality of standard search engines to support classroom search activities for children (ages 6 to 11). This model extends the known listwise learning-to-rank framework by…
On the Computational Modeling of Meaning: Embodied Cognition Intertwined with Emotion Open
This document chronicles this author's attempt to explore how words come to mean what they do, with a particular focus on child language acquisition and what that means for models of language understanding.\footnote{I say \emph{historical}…
Vision Language Transformers: A Survey Open
Vision language tasks, such as answering questions about or generating captions that describe an image, are difficult tasks for computers to perform. A relatively recent body of research has adapted the pretrained transformer architecture …
“Who are you?”: Identifying Young Users from a Single Search Query Open
As an initial step towards enabling the adaptation of (popular, and widely used) web search environments so that they can better serve children and ease their path towards information discovery, we introduce Recognizing Young Searchers (RY…
Who's in Charge? Roles and Responsibilities of Decision-Making Components in Conversational Robots Open
Software architectures for conversational robots typically consist of multiple modules, each designed for a particular processing task or functionality. Some of these modules are developed for the purpose of making decisions about the next…
Conversational Agents and Children: Let Children Learn Open
Using online information discovery as a case study, in this position paper we discuss the need to design, develop, and deploy (conversational) agents that can -- non-intrusively -- guide children in their quest for online resources rather …
Evaluating Automatic Speech Recognition in an Incremental Setting Open
The increasing reliability of automatic speech recognition has proliferated its everyday use. However, for research purposes, it is often unclear which model one should choose for a task, particularly if there is a requirement for speed as…
Exploring Transformers as Compact, Data-efficient Language Models Open
Large scale transformer models, trained with massive datasets have become the standard in natural language processing. The huge size of most transformers make research with these models impossible for those with limited computational resou…
Tiny Language Models Enriched with Multimodal Knowledge from Multiplex Networks Open
Large transformer language models trained exclusively on massive quantities of text are now the standard in NLP.In addition to the impractical amounts of data used to train them, they require enormous computational resources for training.F…
Evaluating and Improving Automatic Speech Recognition using Severity Open
A common metric for evaluating Automatic Speech Recognition (ASR) is Word Error Rate (WER) which solely takes into account discrepancies at the word-level. Although useful, WER is not guaranteed to correlate well with human judgment or per…
Investigating preferential acquisition and attachment in early word learning through cognitive, visual and latent multiplex lexical networks Open
Children learn their first language in a highly multimodal environment. This paper outlines a quantitative framework capturing children's typical language acquisition through multimodal conceptual features. Building on prior research from …
Symbol and Communicative Grounding through Object Permanence with a Mobile Robot Open
Object permanence is the ability to form and recall mental representations of objects even when they are not in view. Despite being a crucial developmental step for children, object permanence has had only some exploration as it relates to…
The State of SLIVAR: What's next for robots, human-robot interaction, and (spoken) dialogue systems? Open
We synthesize the reported results and recommendations of recent workshops and seminars that convened to discuss open questions within the important intersection of robotics, human-robot interaction, and spoken dialogue systems research. T…
An Analysis of the Recent Visibility of the SigDial Conference Open
Automated speech and text interfaces are continuing to improve, resulting in increased research in the area of dialogue systems. Moreover, conferences and workshops from various fields are focusing more on language through speech and text …
Language Acquisition is Embodied, Interactive, Emotive: a Research Proposal Open
Humans' experience of the world is profoundly multimodal from the beginning, so why do existing state-of-the-art language models only use text as a modality to learn and represent semantic meaning? In this paper we review the literature on…