Related papers: TBX goes TEI -- Implementing a TBX basic extension…
Many explainable AI (XAI) techniques strive for interpretability by providing concise salient information, such as sparse linear factors. However, users either only see inaccurate global explanations, or highly-varying local explanations.…
In speech-applications such as text-to-speech (TTS) or automatic speech recognition (ASR), \emph{text normalization} refers to the task of converting from a \emph{written} representation into a representation of how the text is to be…
EXplainable Artificial Intelligence (XAI) is a vibrant research topic in the artificial intelligence community, with growing interest across methods and domains. Much has been written about the subject, yet XAI still lacks shared…
Tokenization - the practice of converting strings of characters from an alphabet into sequences of tokens over a vocabulary - is a critical step in the NLP pipeline. The use of token representations is widely credited with increased model…
Text embedding is becoming an increasingly popular AI methodology, especially among businesses, yet the potential of text embedding models to be biased is not well understood. This paper examines the degree to which a selection of popular…
This paper presents a comprehensive comparative analysis of explainable artificial intelligence (XAI) ensembling methods. Our research brings three significant contributions. Firstly, we introduce a novel ensembling method, NormEnsembleXAI,…
Due in part to their discontinuous and discrete default encodings for numbers, Large Language Models (LLMs) have not yet been commonly used to process numerically-dense scientific datasets. Rendering datasets as text, however, could help…
AI is widely thought to be poised to transform business, yet current perceptions of the scope of this transformation may be myopic. Recent progress in natural language processing involving transformer language models (TLMs) offers a…
The field of Explainable AI (XAI) offers a wide range of techniques for making complex models interpretable. Yet, in practice, generating meaningful explanations is a context-dependent task that requires intentional design choices to ensure…
With Artificial Intelligence (AI) becoming ubiquitous in every application domain, the need for explanations is paramount to enhance transparency and trust among non-technical users. Despite the potential shown by Explainable AI (XAI) for…
Text-to-image (T2I) models can effectively capture the content or style of reference images to perform high-quality customization. A representative technique for this is fine-tuning using low-rank adaptations (LoRA), which enables efficient…
Language models (LMs) are increasingly extended with new learnable vocabulary tokens for domain-specific tasks, such as Semantic-ID tokens in generative recommendation. The standard practice initializes these new tokens as the mean of…
Text normalization (TN) and inverse text normalization (ITN) are essential preprocessing and postprocessing steps for text-to-speech synthesis and automatic speech recognition, respectively. Many methods have been proposed for either TN or…
The field of explainable AI (XAI) has quickly become a thriving and prolific community. However, a silent, recurrent and acknowledged issue in this area is the lack of consensus regarding its terminology. In particular, each new…
Language models lack the notion of interchangeable tokens: symbols that are semantically equivalent yet distinct, such as bound variables in formal logic. This limitation prevents generalization to larger vocabularies and hinders the…
In this paper, we investigate and experiment the notion of error correction memory applied to error correction in technical texts. The main purpose is to induce relatively generic correction patterns associated with more contextual…
We present a suite of experiments that allow us to understand the underlying challenges of language model adaptation to nonstandard text. We do so by designing interventions that approximate core features of user-generated text and their…
Text-to-image (T2I) customization aims to create images that embody specific visual concepts delineated in textual descriptions. However, existing works still face a main challenge, concept overfitting. To tackle this challenge, we first…
Transactional events (TE) are an extension of Concurrent ML (CML), a programming model for synchronous message-passing. Prior work has focused on TE's formal semantics and its implementation. This paper considers programming idioms,…
Sequential recommendation aims to choose the most suitable items for a user at a specific timestamp given historical behaviors. Existing methods usually model the user behavior sequence based on the transition-based methods like Markov…