Related papers: Dia-Lingle: A Gamified Interface for Dialectal Dat…
Recent advances in open-domain dialogue systems rely on the success of neural models that are trained on large-scale data. However, collecting large-scale dialogue data is usually time-consuming and labor-intensive. To address this data…
The objective of ontologies is to increase the compression of a given domain by eliminating interpretation problems. Among kinds of ontologies are linguistics ontologies which are ontologies used to simplify the interface between domain…
Current AI models often fail to account for local context and language, given the predominance of English and Western internet content in their training data. This hinders the global relevance, usefulness, and safety of these models as they…
This paper provides a roadmap that explores the question of how to imbue learning agents with the ability to understand and generate contextually relevant natural language in service of achieving a goal. We hypothesize that two key…
Long-tail class incremental learning (LT CIL) remains highly challenging because the scarcity of samples in tail classes not only hampers their learning but also exacerbates catastrophic forgetting under continuously evolving and imbalanced…
Many cultural institutions have made large digitized visual collections available online, often under permissible re-use licences. Creating interfaces for exploring and searching these collections is difficult, particularly in the absence…
With the rise of deep learning, large datasets and complex models have become common, requiring significant computing power. To address this, data distillation has emerged as a technique to quickly train models with lower memory and time…
This study addresses the interaction challenges encountered by spoken dialogue systems (SDSs) when engaging with users who exhibit distinct conversational behaviors, particularly minors, in scenarios where data are scarce. We propose a…
Discussions on Twitter involve participation from different communities with different dialects and it is often necessary to summarize a large number of posts into a representative sample to provide a synopsis. Yet, any such representative…
Vocabulary acquisition in early education often relies on rote memorization and passive screen-based tools, which can fail to engage students kinesthetically and collaboratively. This paper introduces Vocabuild, an augmented tangible…
Large language models (LLMs) have shown impressive promise in code generation, yet their progress remains limited by the shortage of large-scale datasets that are both diverse and well-aligned with human reasoning. Most existing resources…
This paper presents a dataset collected from natural dialogs which enables to test the ability of dialog systems to learn new facts from user utterances throughout the dialog. This interactive learning will help with one of the most…
Developing language model-based dialogue agents requires effective data to train models that can follow specific task logic. However, most existing data simulation methods focus on increasing diversity in language, topics, or dialogue acts…
Speaker diarization relies on the assumption that speech segments corresponding to a particular speaker are concentrated in a specific region of the speaker space; a region which represents that speaker's identity. These identities are not…
Popular language learning applications such as Duolingo use large language models (LLMs) to generate lessons for its users. Most lessons focus on general real-world scenarios such as greetings, ordering food, or asking directions, with…
Last year has witnessed the considerable interest of Large Language Models (LLMs) for their potential applications in recommender systems, which may mitigate the persistent issue of data sparsity. Though large efforts have been made for…
Large Language Models (LLMs) are known to lack cultural representation and overall diversity in their generations, from expressing opinions to answering factual questions. To mitigate this problem, we propose multilingual prompting: a…
We propose a novel approach to the problem of semantic heterogeneity where data are organized into a set of stratified and independent representation layers, namely: conceptual(where a set of unique alinguistic identifiers are connected…
Large language models (LLMs), such as GPT-3 and ChatGPT, have demonstrated remarkable results in various natural language processing (NLP) tasks with in-context learning, which involves inference based on a few demonstration examples.…
Dictation enables efficient text input on mobile devices. However, writing with speech can produce disfluent, wordy, and incoherent text and thus requires heavy post-processing. This paper presents Rambler, an LLM-powered graphical user…