An official website of the United States government
Shared gaze, where collaborators can see each other's point of gaze visualized on their screen in real time, is a novel non-verbal mechanism that augments remote collaborations and increases shared awareness and common grounding. While past studies have focused on well-structured tasks and analyzed task performance and efficiency, our study explores the domain of collaborative drawing for recreational purposes and focuses on collaborators' own perceptions. We surveyed 75 users of online collaborative drawing platforms who mostly drew collaboratively for recreation and artistic growth; they reported the importance of communication but also of retaining individual space despite the collaborative setting. Informed by this and prior research on shared gaze, we evaluate collaboration by allowing two collaborators to draw synchronously on a shared canvas and share their point of gaze. We conducted a study with 24 pairs that drew collaboratively under all combinations of shared gaze and voice communication. Combining voice and shared gaze was perceived to reach the best balance between tightly coupled collaboration and parallel individual execution. Shared gaze led to higher spatial awareness and less turn-taking was observed in conditions that shared gaze was present. Surprisingly, many participants found the lack of any communication medium to afford the highest degree of divergent thinking. Our findings provide guidelines for adaptive tools that consider individual preferences as well as the nature of the task to better support remote collaborations that are open-ended and prize creativity.
more »
« less
Findings of the SIGMORPHON 2023 Shared Task on Interlinear Glossing
This paper presents the findings of the SIGMORPHON 2023 Shared Task on Interlinear Glossing. This first iteration of the shared task explores glossing of a set of six typologically diverse languages: Arapaho, Gitksan, Lezgi, Natügu, Tsez and Uspanteko. The shared task encompasses two tracks: a resource-scarce closed track and an open track, where participants are allowed to utilize external data resources. Five teams participated in the shared task. The winning team Tü-CL achieved a 23.99%-point improvement over a baseline RoBERTa system in the closed track and a 17.42%-point improvement in the open track.
more »
« less
- Award ID(s):
- 2149404
- PAR ID:
- 10539620
- Publisher / Repository:
- Association for Computational Linguistics
- Date Published:
- Page Range / eLocation ID:
- 186 to 201
- Format(s):
- Medium: X
- Location:
- Toronto, Canada
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Large language models (LLMs) have become a dominant and important tool for NLP researchers in a wide range of tasks. Today, many researchers use LLMs in synthetic data generation, task evaluation, fine-tuning, distillation, and other model-in-the-loop research workflows. However, challenges arise when using these models that stem from their scale, their closed source nature, and the lack of standardized tooling for these new and emerging workflows. The rapid rise to prominence of these models and these unique challenges has had immediate adverse impacts on open science and on the reproducibility of work that uses them. In this ACL 2024 theme track paper, we introduce DataDreamer, an open source Python library that allows researchers to write simple code to implement powerful LLM workflows. DataDreamer also helps researchers adhere to best practices that we propose to encourage open science and reproducibility. The library and documentation are available at: https://github.com/datadreamer-dev/DataDreamer.more » « less
-
The ultimate goal of dialog research is to develop systems that can be effectively used in interactive settings by real users. To this end, we introduced the Interactive Evaluation of Dialog Track at the 9th Dialog System Technology Challenge. This track consisted of two sub-tasks. The first sub-task involved building knowledge-grounded response generation models. The second sub-task aimed to extend dialog models beyond static datasets by assessing them in an interactive setting with real users. Our track challenges participants to develop strong response generation models and explore strategies that extend them to back-and-forth interactions with real users. The progression from static corpora to interactive evaluation introduces unique challenges and facilitates a more thorough assessment of open-domain dialog systems. This paper provides an overview of the track, including the methodology and results. Furthermore, it provides insights into how to best evaluate open-domain dialog models.more » « less
-
As AI agents are increasingly used in the real open world with unknowns or novelties, they need the ability to (1) recognize objects that (a) they have learned before and (b) detect items that they have never seen or learned, and (2) learn the new items incrementally to become more and more knowledgeable and powerful. (1) is called novelty detection or out-of-distribution (OOD) detection and (2) is called class incremental learning (CIL), which is a setting of continual learning (CL). In existing research, OOD detection and CIL are regarded as two completely different problems. This paper first provides a theoretical proof that good OOD detection for each task within the set of learned tasks (called closed-world OOD detection) is necessary for successful CIL. We show this by decomposing CIL into two sub-problems: within-task prediction (WP) and task-id prediction (TP), and proving that TP is correlated with closed-world OOD detection. The key theoretical result is that regardless of whether WP and OOD detection (or TP) are defined explicitly or implicitly by a CIL algorithm, good WP and good closed-world OOD detection are necessary and sufficient conditions for good CIL, which unifies novelty or OOD detection and continual learning (CIL, in particular). We call this traditional CIL the closed-world CIL as it does not detect future OOD data in the open world. The paper then proves that the theory can be generalized or extended to open-world CIL, which is the proposed open-world continual learning, that can perform CIL in the open world and detect future or open-world OOD data. Based on the theoretical results, new CIL methods are also designed, which outperform strong baselines in CIL accuracy and in continual OOD detection by a large margin.more » « less
-
Recent research highlights the importance of figurative language as a tool for amplifying emotional impact. In this paper, we dive deeper into this phenomenon and outline our methods for Track 1, Empathy Prediction in Conversations (CONV-dialog) and Track 2, Empathy and Emotion Prediction in Conversation Turns (CONV-turn) of the WASSA 2024 shared task. We leveraged transformer-based large language models augmented with figurative language prompts, specifically idioms, metaphors and hyperbole, that were selected and trained for each track to optimize system performance. For Track 1, we observed that a fine-tuned BERT with metaphor and hyperbole features outperformed other models on the development set. For Track 2, DeBERTa, with different combinations of figurative language prompts, performed well for different prediction tasks. Our method provides a novel framework for understanding how figurative language influences emotional perception in conversational contexts. Our system officially ranked 4th in the 1st track and 3rd in the 2nd track.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.18653/v1/2023.sigmorphon-1.20
