Related papers: A Label Semantics Approach to Linguistic Hedges
The search for linguistic patterns, stylometry and forensic linguistics have in the theory of complex networks, their structures and associated mathematical tools, allies with which to model and analyze texts. In this paper we present a new…
The cost and scarcity of fully supervised labels in statistical machine learning encourage using partially labeled data for model validation as a cheaper and more accessible alternative. Effectively collecting and leveraging weakly…
This paper explores the automatic construction of a multilingual Lexical Knowledge Base from pre-existing lexical resources. We present a new and robust approach for linking already existing lexical/semantic hierarchies. We used a…
In recent years, central components of a new approach to linguistics, the Minimalist Program (MP) have come closer to physics. Features of the Minimalist Program, such as the unconstrained nature of recursive Merge, the operation of the…
Unsupervised word segmentation in audio utterances is challenging as, in speech, there is typically no gap between words. In a preliminary experiment, we show that recent deep self-supervised features are very effective for word…
Advances in topic modeling have yielded effective methods for characterizing the latent semantics of textual data. However, applying standard topic modeling approaches to sentence-level tasks introduces a number of challenges. In this…
This paper proposes to compute the meanings associated to sentences with generic NPs corresponding to the most of generalized quantifier. We call these generics specimens and they resemble stereotypes or prototypes in lexical semantics. The…
We investigate compositional structures in data embeddings from pre-trained vision-language models (VLMs). Traditionally, compositionality has been associated with algebraic operations on embeddings of words from a pre-existing vocabulary.…
Relational data sources are still one of the most popular ways to store enterprise or Web data, however, the issue with relational schema is the lack of a well-defined semantic description. A common ontology provides a way to represent the…
Categorical compositional distributional semantics is a model of natural language; it combines the statistical vector space models of words with the compositional models of grammar. We formalise in this model the generalised quantifier…
This paper introduces context algebras and demonstrates their application to combining logical and vector-based representations of meaning. Other approaches to this problem attempt to reproduce aspects of logical semantics within new…
Recently, the usefulness of self-supervised representation learning (SSRL) methods has been confirmed in various downstream tasks. Many of these models, as exemplified by HuBERT and WavLM, use pseudo-labels generated from spectral features…
In this paper, we aim to learn associations between visual attributes of fonts and the verbal context of the texts they are typically applied to. Compared to related work leveraging the surrounding visual context, we choose to focus only on…
In this paper, we present a comprehensive system for the treatment of the topic of limits--conceptually, computationally, and formally. The system addresses fundamental linguistic flaws in the standard presentation of limits, which attempts…
It is demonstrated that under the hypothesis of boundedness, the semantics appears as a property of spontaneous physical processes. It turns that both semantic structure and semantic meaning have their own physical agents each of which is…
We propose a unified neural network architecture and learning algorithm that can be applied to various natural language processing tasks including: part-of-speech tagging, chunking, named entity recognition, and semantic role labeling. This…
Rooting in the scarcity of most attributes, realistic pedestrian attribute datasets exhibit unduly skewed data distribution, from which two types of model failures are delivered: (1) label imbalance: model predictions lean greatly towards…
Considering that words with different characteristic in the text have different importance for classification, grouping them together separately can strengthen the semantic expression of each part. Thus we propose a new text representation…
Huge numbers of new words emerge every day, leading to a great need for representing them with semantic meaning that is understandable to NLP systems. Sememes are defined as the minimum semantic units of human languages, the combination of…
Deep neural networks based on layer-stacking architectures have historically suffered from poor inherent interpretability. Meanwhile, symbolic probabilistic models function with clear interpretability, but how to combine them with neural…