相关论文: Epistemic NP Modifiers
Similarity-sensitive entropy measures the uncertainty of a probability law relative to a similarity kernel that encodes the distinguishability between states. We develop a measure-theoretic treatment covering both finite similarity matrices…
Documents in scientific newspapers are often marked by attitudes and opinions of the author and/or other persons, who contribute with objective and subjective statements and arguments as well. In this respect, the attitude is often…
In terminology work, natural language processing, and digital humanities, several studies address the analysis of variations in context and meaning of terms in order to detect semantic change and the evolution of terms. We distinguish three…
In this paper, we investigate the role of attention heads in Context-aware Machine Translation models for pronoun disambiguation in the English-to-German and English-to-French language directions. We analyze their influence by both…
The recognition and classification of Named Entities (NER) are regarded as an important component for many Natural Language Processing (NLP) applications. The classification is usually made by taking into account the immediate context in…
In attempts to "explain" predictions of machine learning models, researchers have proposed hundreds of techniques for attributing predictions to features that are deemed important. While these attributions are often claimed to hold the…
My doctoral research focuses on understanding semantic knowledge in neural network models trained solely to predict natural language (referred to as language models, or LMs), by drawing on insights from the study of concepts and categories…
We introduce a conditional generative model for learning to disentangle the hidden factors of variation within a set of labeled observations, and separate them into complementary codes. One code summarizes the specified factors of variation…
Event structures where the causality may explicitly change during a computation have recently gained the stage. In this kind of event structures the changes in the set of the causes of an event are triggered by modifiers that may add or…
The study of linguistic typology is rooted in the implications we find between linguistic features, such as the fact that languages with object-verb word ordering tend to have post-positions. Uncovering such implications typically amounts…
In this paper, we are mainly concerned with the ability to quickly and automatically distinguish word senses in dynamic semantic spaces in which new terms and new senses appear frequently. Such spaces are built '"on the fly" from constantly…
Live languages continuously evolve to integrate the cultural change of human societies. This evolution manifests through neologisms (new words) or \textbf{semantic changes} of words (new meaning to existing words). Understanding the meaning…
We introduce a new setting, the category of $\omega$PAP spaces, for reasoning denotationally about expressive differentiable and probabilistic programming languages. Our semantics is general enough to assign meanings to most practical…
Discrete temporal transitions occur in a variety of domains, but this work is mainly motivated by applications in molecular biology: explaining and analyzing observed transcriptome and proteome time series by literature and database…
Quantum information has suggested new forms of quantum logic, called quantum computational logics, where meanings of sentences are represented by pieces of quantum information (generally, density operators of some Hilbert spaces), which can…
Layer-wise Relevance Propagation (LRP) and saliency maps have been recently used to explain the predictions of Deep Learning models, specifically in the domain of text classification. Given different attribution-based explanations to…
A measure of similarity between text embeddings can be considered adequate only if it adheres to the human perception of similarity between texts. In this paper, we introduce the distance-to-distance ratio (DDR), a novel measure of…
TripAdvisor reviews and comparable data sources play an important role in many tasks in Natural Language Processing (NLP), providing a data basis for the identification and classification of subjective judgments, such as hotel or restaurant…
Epistemic logic programs constitute an extension of the stable models semantics to deal with new constructs called subjective literals. Informally speaking, a subjective literal allows checking whether some regular literal is true in all…
Human reading behavior is sensitive to surprisal: more predictable words tend to be read faster. Unexpectedly, this applies not only to the surprisal of the word that is currently being read, but also to the surprisal of upcoming…