By positing a relationship between naturalistic reading times and information-theoretic
surprisal, surprisal theory (Hale, 2001; Levy, 2008) provides a natural interface between …

The transformers that drive chatbots and other AI systems constitute large language models
(LLMs). These are currently the focus of a lively discussion in both the scientific literature …

Social media is a widely used platform that provides a huge amount of user-generated
content that can be processed to extract information about users' emotions. This has …

The application of deep learning methods to problems in natural language processing has
generated significant progress across a wide range of natural language processing tasks …

To harness the power of large language models in safety-critical domains we need to
ensure the explainability of their predictions. However, despite the significant attention to …

We examine the extent to which, in principle, linguistic graph representations can
complement and improve neural language modeling. With an ensemble setup consisting of …

This paper gives a general description of the ideas behind the Parallel Meaning Bank, a
framework with the aim to provide an easy way to annotate compositional semantics for texts …

In this work we build upon negative results from an attempt at language modeling with
predicted semantic structure, in order to establish empirical lower bounds on what could …

Data-to-text generation converts structured data into natural language text, simplifying
complex data interpretation and reducing manual effort. Traditional rule-based and neural …

Speakers display considerable variability in language use and representations: they may
have different pronunciations of the same word, different intended meanings for the same …