Related papers: Exploring Verbalization and Collaboration during U…
In a contemporary world, people become dependent on electronic devices. Technologies help to clarification and structure life in many ways to meet the need of the children oriented requirements. The children suffering from disabilities…
Children's agency plays a critical role in shaping children's autonomy, participation, and well-being in their interactions with digital systems, particularly in emerging child-AI contexts. However, how designers currently understand and…
Document-level translation models are usually evaluated using general metrics such as BLEU, which are not informative about the benefits of context. Current work on context-aware evaluation, such as contrastive methods, only measure…
Investigating child-computer interactions within their contexts is vital for designing technology that caters to children's needs. However, determining what aspects of context are relevant for designing child-centric technology remains a…
Key to tasks that require reasoning about natural language in visual contexts is grounding words and phrases to image regions. However, observing this grounding in contemporary models is complex, even if it is generally expected to take…
We develop models to classify desirable evidence and desirable reasoning revisions in student argumentative writing. We explore two ways to improve classifier performance - using the essay context of the revision, and using the feedback…
Context plays an important role in visual recognition. Recent studies have shown that visual recognition networks can be fooled by placing objects in inconsistent contexts (e.g., a cow in the ocean). To model the role of contextual…
Spoken language interaction is at the heart of interpersonal communication, and people flexibly adapt their speech to different individuals and environments. It is surprising that robots, and by extension other digital devices, are not…
Children in a large number of international and cross-cultural families in and outside of the US learn and speak more than one language. However, parents often struggle to acquaint their young children with their local language if the child…
The field of information retrieval often works with limited and noisy data in an attempt to classify documents into subjective categories, e.g., relevance, sentiment and controversy. We typically quantify a notion of agreement to understand…
Computational modeling of naturalistic conversations in clinical applications has seen growing interest in the past decade. An important use-case involves child-adult interactions within the autism diagnosis and intervention domain. In this…
The rapid adoption of large language models in AI-powered language education has created an urgent need for evaluations that assess pedagogical effectiveness, particularly in language learning--one of the most common LLM use cases (Tamkin…
Automated feedback systems have become increasingly integral to programming education, where learners engage in iterative cycles of code construction, testing, and refinement. Despite its wider integration in practices and technical…
This paper outlines the challenges and opportunities of research on conversational agents with children and young people across four countries, exploring the ways AI technologies can support children's well-being across social and cultural…
The present study aims to evaluate the efficiency of the computer assisted English classes and to emphasize the necessity of developing sound methodological strategies adjusted to the new technology. It also present the benefits of using…
State-of-the-art pretrained contextualized models (PCM) eg. BERT use tasks such as WiC and WSD to evaluate their word-in-context representations. This inherently assumes that performance in these tasks reflect how well a model represents…
Machine learning is an important tool for decision making, but its ethical and responsible application requires rigorous vetting of its interpretability and utility: an understudied problem, particularly for natural language processing…
Usability is a key quality attribute of successful software systems. Unfortunately, there is no common understanding of the factors influencing usability and their interrelations. Hence, the lack of a comprehensive basis for designing,…
Thinking aloud is an effective meta-cognitive strategy human reasoners apply to solve difficult problems. We suggest to improve the reasoning ability of pre-trained neural language models in a similar way, namely by expanding a task's…
This report explores the potential implications of rapidly integrating Artificial Intelligence (AI) applications into children's environments. The introduction of AI in our daily lives necessitates scrutiny considering the significant role…