UMBC Language Technology Seminar Series (LaTeSS)

Using Participatory Design and AI to Create Agency-increasing Augmentative and Alternative Communication Systems
Agency and communication are integral to personal development, enabling us to pursue and express our goals. However, agency in communication is not fixed–Many individuals who use speech-generating devices to communicate encounter social constraints and technical limitations that can restrict what they can say, how they can say it, and when they can contribute to a discussion. In this talk, I will delve into how an agency-centered design approach can foster more accessible communication experiences and help us uncover opportunities for design. Drawing from empirical research and collaborative co-design with people with disabilities, I will highlight how various technological tools—such as automated transcription, physical interaction artifacts, and AI-driven language generation—can impact conversational agency. Additionally, I will share practical design strategies and discuss existing challenges for co-designing communication technologies that enhance user agency and participation.

Confabulation: What Could LLM Hallucinations Do For Storytelling?
Are hallucinations always bad? Most of NLP research presumes a normative stance that they are, but it overlooks the cognitive and communicative affordances of a type of particularly story-like hallucinations (which we'll call confabulations). Consider two general categories of LLM applications: using them as tools, or interacting with them as viable cultural agents. The two have very different training objectives in terms of the tradeoff between factuality and alignment with the human behavior of storytelling, and when it comes to ensuring the latter, LLMs that could effectively confabulate would be especially useful. For instance, confabulations could enable LLMs to perform speculative narration and address omissions in history resulting from social injustice, in the hope of enacting what literary theorist Saidiya Hartman calls 'critical fabulation' at scale, and giving interactive storytelling a wider social impact.

Expanding Voices: Nonbinary Representation in Speech-Generating Devices
Synthetic voices used by Speech-Generating Device (SGD) users are predominantly shaped by binary gender norms, limiting the representation of nonbinary individuals. This talk begins by exploring the current landscape of gender in synthetic voices and nonbinary vocal characteristics, revealing how existing models, trained on cisgender male and female speech, fail to authentically represent nonbinary identities. I will then present a case study of a nonbinary SGD user who used three synthetic voices constructed from gender expansive speakers over the course of a week, documenting their experiences in daily journal entries. Finally, I’ll examine the impact of inclusive voice design and community-informed research on identity affirmation and communication efficacy, drawing from the case study’s findings. These insights underscore the critical need for gender expansive synthetic voices that prioritize both gender affirmation and expressiveness, with far-reaching implications for voice technology and user engagement.

Takeaways from the SCALE 2024 Workshop on Event-Centric Video Retrieval
Information dissemination for current events has traditionally consisted of professionally collected and produced materials, leading to large collections of well-written news articles and high-quality videos. As a result, most prior work in event analysis and retrieval has focused on leveraging this traditional news content, particularly in English. However, much of the event-centric content today is generated by non-professionals, such as on-the-scene witnesses to events who hastily capture videos and upload them to the internet without further editing; these are challenging to find due to quality variance, as well as a lack of text or speech overlays providing clear descriptions of what is occurring. To address this gap, SCALE 2024, a 10-week research workshop hosted at the Human Language Technology Center of Excellence (HLTCOE), focused on multilingual event-centric video retrieval, or the task of finding videos about specific current events. Around 50 researchers and students participated in this workshop and were split up into five sub-teams. The Infrastructure team focused on developing MultiVENT 2.0, a challenging new video retrieval dataset consisting of 20x more videos than prior work and targeted queries about specific world events across six languages. The other teams worked on improving models from specific modalities, specifically Vision, Optical Character Recognition (OCR), Audio, and Text. Overall, we came away with three primary findings: extracting specific text from a video allows us to take better advantage of powerful methods from the text information retrieval community; LLM summarization of initial text outputs from videos is helpful, especially for noisy text coming from OCR; and no one modality is sufficient, with fusing outputs from all modalities resulting in significantly higher performance.

AI Resilient Interfaces for Code Generation and Efficient Reading
AI is being integrated into virtually every computer system we use, but often in ways that mean we cannot see the decisions AI makes for us. If we don't see a decision, we cannot notice whether we agree with it, and what we don't notice, we cannot change. For example, using an AI summarization system means trusting that it has captured all the aspects of a document that are relevant to you. If the task is high stakes then the only way to check is to read the original document, but that significantly decreases the value of the summary. In this talk, I will present the concept of AI resilient interfaces: systems that use AI while giving users the information they need to notice and change its decisions. I will walk through two examples of novel systems that are more AI resilient than the typical solution to the problem, for (1) SQL generation, and (2) faster reading. I will conclude with thoughts on the potential and pitfalls of designing with AI resilience in mind.