Related papers: Commutative Languages and their Composition by Con…
Contrastive vision-language models continue to be the dominant approach for image and text retrieval. Contrastive Language-Image Pre-training (CLIP) trains two neural networks in contrastive manner to align their image and text embeddings…
Abstract grammatical knowledge - of parts of speech and grammatical patterns - is key to the capacity for linguistic generalization in humans. But how abstract is grammatical knowledge in large language models? In the human literature,…
Structural generalization in semantic parsing requires systems to apply learned compositional rules to novel structural combinations. Existing approaches either rely on hand-written algebraic rules (AM-Parser) or fail to generalize…
A filtration of a formal language L by a sequence s maps L to the set of words formed by taking the letters of words of L indexed only by s. We consider the languages resulting from filtering by all arithmetic progressions. If L is regular,…
Vision-language models (VLMs) like CLIP have showcased a remarkable ability to extract transferable features for downstream tasks. Nonetheless, the training process of these models is usually based on a coarse-grained contrastive loss…
Consistency regularization describes a class of approaches that have yielded ground breaking results in semi-supervised classification problems. Prior work has established the cluster assumption - under which the data distribution consists…
An {\omega}-language is a set of infinite words over a finite alphabet X. We consider the class of recursive {\omega}-languages, i.e. the class of {\omega}-languages accepted by Turing machines with a B\"uchi acceptance condition, which is…
We discuss the computational complexity of context-free languages, concentrating on two well-known structural properties---immunity and pseudorandomness. An infinite language is REG-immune (resp., CFL-immune) if it contains no infinite…
An aggregative composition is a binary operation obeying the principle that the whole is determined by the sum of its parts. The development of graph algebras, on which the theory of formal graph languages is built, relies on aggregative…
In lexical semantics, full-sentence segmentation and segment labeling of various phenomena are generally treated separately, despite their interdependence. We hypothesize that a unified lexical semantic recognition task is an effective way…
The paper continues the investigation of Poincare and Russel's Vicious Circle Principle (VCP) in the context of the design of logic programming languages with sets. We expand previously introduced language Alog with aggregates by allowing…
Cross-lingual document alignment aims to identify pairs of documents in two distinct languages that are of comparable content or translations of each other. In this paper, we exploit the signals embedded in URLs to label web documents at…
Perceptually Aligned Gradients (PAG) refer to an intriguing property observed in robust image classification models, wherein their input gradients align with human perception and pose semantic meanings. While this phenomenon has gained…
We consider a computational model which is known as set automata. The set automata are one-way finite automata with an additional storage---the set. There are two kinds of set automata---the deterministic and the nondeterministic ones. We…
Classic grammars and regular expressions can be used for a variety of purposes, including parsing, intent detection, and matching. However, the comparisons are performed at a structural level, with constituent elements (words or characters)…
While reasoning in a logic extending a complete Boolean basis is coNP-hard, restricting to conjunctive fragments of modal languages sometimes allows for tractable reasoning even in the presence of greatest fixpoints. One such example is the…
Data-driven subword segmentation has become the default strategy for open-vocabulary machine translation and other NLP tasks, but may not be sufficiently generic for optimal learning of non-concatenative morphology. We design a test suite…
Despite the predominance of contextualized embeddings in NLP, approaches to detect semantic change relying on these embeddings and clustering methods underperform simpler counterparts based on static word embeddings. This stems from the…
We define a class of languages of infinite words over infinite alphabets, and the corresponding automata. The automata used for recognition are a generalisation of deterministic Muller automata to the setting of nominal sets. Remarkably,…
Cross-lingual Text Classification (CLC) consists of automatically classifying, according to a common set C of classes, documents each written in one of a set of languages L, and doing so more accurately than when naively classifying each…