Related papers: Splitting the Reference Time: Temporal Anaphora an…
After stating the measurement problem, physicists usually assume the problem to be coming from the measurement part. Since classical probabilities also collapse when updating information, there is nothing special about quantum state…
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…
With the rise of large language models, the paradigm of training foundation models with massive parameter counts on vast datasets has been adopted in multiple domains to achieve remarkable success. Time series foundation models represent a…
We analyse and develop the recent suggestion that a temporal form of quantum logic provides the natural mathematical framework within which to discuss the proposal by Gell-Mann and Hartle for a generalised form of quantum theory based on…
Temporal relation classification is the task of determining the temporal relation between pairs of temporal entities in a text. Despite recent advancements in natural language processing, temporal relation classification remains a…
Anaphora resolution is envisaged in this paper as part of the reference resolution process. A general open architecture is proposed, which can be particularized and configured in order to simulate some classic anaphora resolution methods.…
We examine the role of textual data as study units when conducting causal inference by drawing parallels between human subjects and organized texts. %in human population research. We elaborate on key causal concepts and principles, and…
This report describes a minimalistic set of methods engineered to anchor clinical events onto a temporal space. Specifically, we describe methods to extract clinical events (e.g., Problems, Treatments and Tests), temporal expressions (i.e.,…
In this paper we discuss the notion of "bridging" in Discourse Representation Theory as a tool to account for discourse referents that have only been established implicitly, through the lexical semantics of other referents. In doing so, we…
Pretrained language models based on the transformer architecture have shown great success in NLP. Textual training data often comes from the web and is thus tagged with time-specific information, but most language models ignore this…
Time series forecasting has become increasingly critical in real-world scenarios, where future sequences are influenced not only by historical patterns but also by forthcoming events. In this context, forecasting must dynamically adapt to…
The advent of context-aware NMT has resulted in promising improvements in the overall translation quality and specifically in the translation of discourse phenomena such as pronouns. Previous works have mainly focused on the use of past…
The theory revision problem is the problem of how best to go about revising a deficient domain theory using information contained in examples that expose inaccuracies. In this paper we present our approach to the theory revision problem for…
Chain-of-thought (CoT) prompting reliably improves language-model accuracy, but which properties of a rationale text drive the improvement is poorly understood. Prior work has largely studied generation-time behavior. We instead ask a…
We present a monitoring approach for verifying systems at runtime. Our approach targets systems whose components communicate with the monitors over unreliable channels, where messages can be delayed or lost. In contrast to prior works,…
This paper studies how dependent typed events can be used to treat verb phrase anaphora. We introduce a framework that extends Dependent Type Semantics (DTS) with a new atomic type for neo-Davidsonian events and an extended @-operator that…
Qualitative relationships illustrate how changing one property (e.g., moving velocity) affects another (e.g., kinetic energy) and constitutes a considerable portion of textual knowledge. Current approaches use either semantic parsers to…
Since its introduction, the transformer has shifted the development trajectory away from traditional models (e.g., RNN, MLP) in time series forecasting, which is attributed to its ability to capture global dependencies within temporal…
Medical professionals evaluating alternative treatment plans for a patient often encounter time varying confounders, or covariates that affect both the future treatment assignment and the patient outcome. The recently proposed…
Inference tasks such as answer sentence selection (AS2) or fact verification are typically solved by fine-tuning transformer-based models as individual sentence-pair classifiers. Recent studies show that these tasks benefit from modeling…