Related papers: Agentivit\`a e telicit\`a in GilBERTo: implicazion…

Recent advances in large language models have prompted researchers to examine their abilities across a variety of linguistic tasks, but little has been done to investigate how models handle the interactions in meaning across words and…

Does the effectiveness of neural language models derive entirely from accurate modeling of surface word co-occurrence statistics, or do these models represent and reason about the world they describe? In BART and T5 transformer language…

Language is typically modelled with discrete sequences. However, the most successful approaches to language modelling, namely neural networks, are continuous and smooth function approximators. In this work, we show that Transformer-based…

Representation of linguistic phenomena in computational language models is typically assessed against the predictions of existing linguistic theories of these phenomena. Using the notion of polarity as a case study, we show that this is not…

Transformer-based language models achieve high performance on various tasks, but we still lack understanding of the kind of linguistic knowledge they learn and rely on. We evaluate three models (BERT, RoBERTa, and ALBERT), testing their…

We investigate how word meanings are represented in the transformer language models. Specifically, we focus on whether transformer models employ something analogous to a lexical store - where each word has an entry that contains semantic…

A cell can be seen as an adaptive autonomous agent or as a society of adaptive autonomous agents, where each can exhibit a particular behaviour depending on its cognitive capabilities. We present an intracellular signalling model obtained…

Language models based on the Transformer architecture achieve excellent results in many language-related tasks, such as text classification or sentiment analysis. However, despite the architecture of these models being well-defined, little…

Transformer-based language models have recently achieved remarkable results in many natural language tasks. However, performance on leaderboards is generally achieved by leveraging massive amounts of training data, and rarely by encoding…

This work describes experiments which probe the hidden representations of several BERT-style models for morphological content. The goal is to examine the extent to which discrete linguistic structure, in the form of morphological features…

The era of Large Language Models (LLMs) presents a new opportunity for interpretability--agentic interpretability: a multi-turn conversation with an LLM wherein the LLM proactively assists human understanding by developing and leveraging a…

We address the issues of semantics and conversations for agent communication languages and the Knowledge Query Manipulation Language (KQML) in particular. Based on ideas from speech act theory, we present a semantic description for KQML…

While cross-linguistic model transfer is effective in many settings, there is still limited understanding of the conditions under which it works. In this paper, we focus on assessing the role of lexical semantics in cross-lingual transfer,…

Recent years have seen an increasing amount of work on embodied AI agents that can perform tasks by following human language instructions. However, most of these agents are reactive, meaning that they simply learn and imitate behaviors…

Lexical semantic change has primarily been investigated with observational and experimental methods; however, observational methods (corpus analysis, distributional semantic modeling) cannot get at causal mechanisms, and experimental…

As large language models (LLMs) advance in their linguistic capacity, understanding how they capture aspects of language competence remains a significant challenge. This study therefore employs psycholinguistic paradigms in English, which…

We present a systematic review of 337 articles evaluating the syntactic abilities of Transformer-based language models (TLMs), reporting on over 3,000 datapoints spanning a wide range of syntactic phenomena, languages, models, and methods.…

This thesis advances semantic representation learning to render language representations or models more semantically and geometrically interpretable, and to enable localised, quasi-symbolic, compositional control through deliberate shaping…

Recent breakthroughs in NLP research, such as the advent of Transformer models have indisputably contributed to major advancements in several tasks. However, few works research robustness and explainability issues of their evaluation…

Transformer-based Neural Language Models achieve state-of-the-art performance on various natural language processing tasks. However, an open question is the extent to which these models rely on word-order/syntactic or word…