Related papers: An Improved Neural Baseline for Temporal Relation …

Understanding temporal relations and answering time-sensitive questions is crucial yet a challenging task for question-answering systems powered by large language models (LLMs). Existing approaches either update the parametric knowledge of…

Pragmatics, the ability to infer meaning beyond literal interpretation, is crucial for social cognition and communication. While LLMs have been benchmarked for their pragmatic understanding, improving their performance remains…

Temporal common sense (e.g., duration and frequency of events) is crucial for understanding natural language. However, its acquisition is challenging, partly because such information is often not expressed explicitly in text, and human…

We propose Improved Memories Learning (IMeL), a novel algorithm that turns reinforcement learning (RL) into a supervised learning (SL) problem and delimits the role of neural networks (NN) to interpolation. IMeL consists of two components.…

Forecasting with multivariate time series, which aims to predict future values given previous and current several univariate time series data, has been studied for decades, with one example being ARIMA. Because it is difficult to measure…

This paper explores whether enhancing temporal reasoning capabilities in Large Language Models (LLMs) can improve the quality of timeline summarisation, the task of summarising long texts containing sequences of events, such as social media…

This study addresses the challenges of analyzing temporal discrepancies in large language models (LLMs) trained on data from different time periods. To facilitate the automatic exploration of these differences, we propose a novel system…

Natural language processing (NLP) enables the understanding and generation of meaningful human language, typically using a pre-trained complex architecture on a large dataset to learn the language and next fine-tune its weights to implement…

Fine-tuning large language models (LLMs) is intended to improve their reasoning capabilities, yet we uncover a counterintuitive effect: models often forget how to solve problems they previously answered correctly during training. We term…

Large Language Models~(LLMs) struggle with providing current information due to the outdated pre-training data.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…

Modelling and understanding time remains a challenge in contemporary video understanding models. With language emerging as a key driver towards powerful generalization, it is imperative for foundational video-language models to have a sense…

A distinction is often drawn between a model's ability to predict a label for an evaluation sample that is directly memorised from highly similar training samples versus an ability to predict the label via some method of generalisation. In…

Effectively searching time-series data is essential for system analysis; however, traditional methods often require domain expertise to define search criteria. Recent advancements have enabled natural language-based search, but these…

Research on time-series similarity measures has emphasized the need for elastic methods which align the indices of pairs of time series and a plethora of non-parametric have been proposed for the task. On the other hand, deep learning…

Neural processes (NPs) aim to stochastically complete unseen data points based on a given context dataset. NPs essentially leverage a given dataset as a context representation to derive a suitable identifier for a novel task. To improve the…

Adding linguistic information (syntax or semantics) to neural machine translation (NMT) has mostly focused on using point estimates from pre-trained models. Directly using the capacity of massive pre-trained contextual word embedding models…

Word embeddings are one of the most useful tools in any modern natural language processing expert's toolkit. They contain various types of information about each word which makes them the best way to represent the terms in any NLP task. But…

End-to-end (E2E) systems have shown comparable performance to hybrid systems for automatic speech recognition (ASR). Word timings, as a by-product of ASR, are essential in many applications, especially for subtitling and computer-aided…

We investigate the question of whether advances in NLP over the last few years make it possible to vastly increase the size of data usable for research in historical syntax. This brings together many of the usual tools in NLP - word…

Many promising-looking ideas in AI research fail to deliver, but their validation takes substantial human labor and compute. Predicting an idea's chance of success is thus crucial for accelerating empirical AI research, a skill that even…