Related papers: Modeling Bottom-up Information Quality during Lang…

In the field of spoken language processing, audio-visual speech processing is receiving increasing research attention. Key components of this research include tasks such as lip reading, audio-visual speech recognition, and visual-to-speech…

Previous studies show that incorporating external information could improve the translation quality of Neural Machine Translation (NMT) systems. However, there are inevitably noises in the external information, severely reducing the benefit…

Estimating the internal state of a robotic system is complex: this is performed from multiple heterogeneous sensor inputs and knowledge sources. Discretization of such inputs is done to capture saliences, represented as symbolic…

This paper proposes an information-theoretic representation learning framework, named conditional information flow maximization, to extract noise-invariant sufficient representations for the input data and target task. It promotes the…

Large Language Models~(LLMs) struggle with providing current information due to the outdated pre-training data. Existing methods for updating LLMs, such as knowledge editing and continual fine-tuning, have significant drawbacks in…

Word embeddings capture semantic relationships based on contextual information and are the basis for a wide variety of natural language processing applications. Notably these relationships are solely learned from the data and subsequently…

Language model fine-tuning is essential for modern natural language processing, but is computationally expensive and time-consuming. Further, the effectiveness of fine-tuning is limited by the inclusion of training examples that negatively…

When evaluating the performance of automatic speech recognition models, usually word error rate within a certain dataset is used. Special care must be taken in understanding the dataset in order to report realistic performance numbers. We…

Despite known differences between reading and listening in the brain, recent work has shown that text-based language models predict both text-evoked and speech-evoked brain activity to an impressive degree. This poses the question of what…

Recent language generative models are mostly trained on large-scale datasets, while in some real scenarios, the training datasets are often expensive to obtain and would be small-scale. In this paper we investigate the challenging task of…

Multilingual machine translation systems aim to make knowledge accessible across languages, yet learning effective cross-lingual representations remains challenging. These challenges are especially pronounced for low-resource languages,…

Large language models (LLMs) are demonstrably capable of cross-lingual transfer, but can produce inconsistent output when prompted with the same queries written in different languages. To understand how language models are able to…

Compositionality in language models presents a problem when processing idiomatic expressions, as their meaning often cannot be directly derived from their individual parts. Although fine-tuning and other optimization strategies can be used…

In hospitals, data are siloed to specific information systems that make the same information available under different modalities such as the different medical imaging exams the patient undergoes (CT scans, MRI, PET, Ultrasound, etc.) and…

This work addresses the buyer's inspection paradox for information markets. The paradox is that buyers need to access information to determine its value, while sellers need to limit access to prevent theft. To study this, we introduce an…

Machine Translation Quality Estimation is a notoriously difficult task, which lessens its usefulness in real-world translation environments. Such scenarios can be improved if quality predictions are accompanied by a measure of uncertainty.…

This paper describes the functioning of a broad-coverage probabilistic top-down parser, and its application to the problem of language modeling for speech recognition. The paper first introduces key notions in language modeling and…

During the pre-training step of natural language models, the main objective is to learn a general representation of the pre-training dataset, usually requiring large amounts of textual data to capture the complexity and diversity of natural…

Learning word embeddings using distributional information is a task that has been studied by many researchers, and a lot of studies are reported in the literature. On the contrary, less studies were done for the case of multiple languages.…

Ho et. al (2024) attempts to estimate the degree of algorithmic progress from language models. They collect observational data on language models' loss and compute over time, and argue that as time has passed, language models' algorithmic…