Content creators often draw inspiration from multiple visual sources, combining distinct elements to craft new compositions. Modern computational approaches now aim to emulate this fundamental creative process. Although recent diffusion models excel...
Identifying which Wikipedia articles are related to science fiction, fantasy, or their hybrids is challenging because genre boundaries are porous and frequently overlap. Wikipedia nonetheless offers machine-readable structure beyond text, including c...
Cross-domain object detection and semantic segmentation have witnessed impressive progress recently. Existing approaches mainly consider the domain shift resulting from external environments including the changes of background, illumination or weathe...
HEX-programs are an extension of the Answer Set Programming (ASP) paradigm incorporating external means of computation into the declarative programming language through so-called external atoms. Their semantics is defined in terms of minimal models o...
JSON Schema is a logical language used to define the structure of JSON values. JSON Schema syntax is based on nested schema objects. In all versions of JSON Schema until Draft-07, collectively known as Classical JSON Schema, the semantics of a schema...
Recent work has shown that a multilingual neural machine translation (NMT) model can be used to judge how well a sentence paraphrases another sentence in the same language (Thompson and Post, 2020); however, attempting to generate paraphrases from su...
Word representation is fundamental in NLP tasks, because it is precisely from the coding of semantic closeness between words that it is possible to think of teaching a machine to understand text. Despite the spread of word embedding concepts, still f...
Emojis come with prepacked semantics making them great candidates to create new forms of more accessible communications. Yet, little is known about how much of this emojis semantic is agreed upon by humans, outside of textual contexts. Thus, we colle...
The semantics of emoji has, to date, been considered from a static perspective. We offer the first longitudinal study of how emoji semantics changes over time, applying techniques from computational linguistics to six years of Twitter data. We identi...
We train word-emoji embeddings on large scale messaging data obtained from the Jodel online social network. Our data set contains more than 40 million sentences, of which 11 million sentences are annotated with a subset of the Unicode 13.0 standard E...
In this paper, we study a model relevant to semantics-aware goal-oriented communications. More specifically, observations from an external process are transmitted through status updates to a battery-powered receiver. From these updates, the receiver...
This paper concerns the question of how AI systems encode semantic structure into the geometric structure of their representation spaces. The motivating observation of this paper is that the natural geometry of these representation spaces should refl...
In recent years, researchers in the area of Computational Creativity have studied the human creative process proposing different approaches to reproduce it with a formal procedure. In this paper, we introduce a model for the generation of literary rh...
Neural language representation models such as GPT, pre-trained on large-scale corpora, can effectively capture rich semantic patterns from plain text and be fine-tuned to consistently improve natural language generation performance. However, existing...
Despite the conceptual simplicity of sequential consistency (SC), the semantics of SC atomic operations and fences in the C11 and OpenCL memory models is subtle, leading to convoluted prose descriptions that translate to complex axiomatic formalisati...
The connection between music and lyrics is far beyond semantic bonds. Conceptual pairs in the two modalities such as rhythm and rhyme, note duration and syllabic stress, and structure correspondence, raise a compelling yet seldom-explored direction i...
Denotational models should provide an opportunity for the revision of current practices seen in the manuals of programming languages. New styles should on one hand base on denotational models but on the other - do not assume that today readers are ac...
Stream processing and reasoning is getting considerable attention in various application domains such as IoT, Industry IoT and Smart Cities. In parallel, reasoning and knowledge-based features have attracted research into many areas of robotics, such...
The international database community refers to the manipulation of data with inaccuracy and uncertainty using the term fuzzy, which has been translated into Spanish as "borroso" and into French as "flou". Semantically, this term conveys two main idea...
We introduce JEDI, a test-time adaptation method that enhances subject separation and compositional alignment in diffusion models without requiring retraining or external supervision. JEDI operates by minimizing semantic entanglement in attention map...