Related papers: A Meaning-oriented Approach to Semantic Data Model…
We propose to extract meaning representations from autoregressive language models by considering the distribution of all possible trajectories extending an input text. This strategy is prompt-free, does not require fine-tuning, and is…
Current methods for textual analysis rely on data annotated within predefined ontologies, often embedding human bias within black-box models. Despite achieving near-perfect performance, these approaches exploit unstructured, linear pattern…
Story visualization aims to generate a sequence of images to narrate each sentence in a multi-sentence story, where the images should be realistic and keep global consistency across dynamic scenes and characters. Current works face the…
Interactive visual analytic systems enable users to discover insights from complex data. Users can express and test hypotheses via user interaction, leveraging their domain expertise and prior knowledge to guide and steer the analytic…
Similarly to other connectionist models, Graph Neural Networks (GNNs) lack transparency in their decision-making. A number of sub-symbolic approaches have been developed to provide insights into the GNN decision making process. These are…
This paper proposes a user semantic intent modeling algorithm based on Capsule Networks to address the problem of insufficient accuracy in intent recognition for human-computer interaction. The method represents semantic features in input…
We present a novel technique for learning semantic representations, which extends the distributional hypothesis to multilingual data and joint-space embeddings. Our models leverage parallel data and learn to strongly align the embeddings of…
We present a memory-based model for context-dependent semantic parsing. Previous approaches focus on enabling the decoder to copy or modify the parse from the previous utterance, assuming there is a dependency between the current and…
One major problem in Natural Language Processing is the automatic analysis and representation of human language. Human language is ambiguous and deeper understanding of semantics and creating human-to-machine interaction have required an…
Temporal graphs represent the dynamic relationships among entities and occur in many real life application like social networks, e commerce, communication, road networks, biological systems, and many more. They necessitate research beyond…
Traditional information retrieval systems represent documents and queries by keyword sets. However, the content of a document or a query is mainly defined by both keywords and named entities occurring in it. Named entities have ontological…
Understanding a visual scene incorporates objects, relationships, and context. Traditional methods working on an image mostly focus on object detection and fail to capture the relationship between the objects. Relationships can give rich…
In this work, we aim at equipping pre-trained language models with structured knowledge. We present two self-supervised tasks learning over raw text with the guidance from knowledge graphs. Building upon entity-level masked language models,…
Design representation is a common task in the design process to facilitate learning, analysis, redesign, communication, and other design activities. Traditional representation techniques rely on human expertise and manual construction and…
Representing structured text from complex documents typically calls for different machine learning techniques, such as language models for paragraphs and convolutional neural networks (CNNs) for table extraction, which prohibits drawing…
Distributed representations of words have been shown to capture lexical semantics, as demonstrated by their effectiveness in word similarity and analogical relation tasks. But, these tasks only evaluate lexical semantics indirectly. In this…
Semantic communication is viewed as a revolutionary paradigm that can potentially transform how we design and operate wireless communication systems. However, despite a recent surge of research activities in this area, the research…
Drawing connections between interesting groupings of data and their real-world meaning is an important, yet difficult, part of encountering a new dataset. A lay reader might see an interesting visual pattern in a chart but lack the domain…
Process mining focuses on the analysis of recorded event data in order to gain insights about the true execution of business processes. While foundational process mining techniques treat such data as sequences of abstract events, more…
Knowledge graphs and ontologies are becoming increasingly important in the context of making data and metadata findable, accessible, interoperable, and reusable (FAIR). We introduce the concept of Semantic Units for organizing Knowledge…