We prove a theorem stating that any semantics can be encoded as a compositional semantics, which means that, essentially, the standard definition of compositionality is formally vacuous. We then show that when compositional semantics is required to be ”systematic” (that is, the meaning function cannot be arbitrary, but must belong to some class), it is possible to distinguish between compositio...

In distributional semantics studies, there is a growing attention in compositionally determining the distributional meaning of word sequences. Yet, compositional distributional models depend on a large set of parameters that have not been explored. In this paper we propose a novel approach to estimate parameters for a class of compositional distributional models: the additive models. Our approa...

Multi-agent systems can be successfully modelled and specified as interacting complex components in a compositional architecture. Compared to the specification of single agent compositional systems, the specification of multi-agent systems requires additional design (or modelling) choices. In this paper, design choices regarding interaction and autonomy of compositional models of intelligent ag...

carbon dioxide flooding is considered to be one of the most effective enhanced oil recovery methods for the light oil reservoirs. depending on the operating pressure, the process might be miscible or immiscible. minimum miscibility pressure (mmp) is the most important parameter for assessing the applicability of any miscible gas flood for an oil reservoir. the miscibility condition is determine...

Neural networks are very powerful learning systems, but they do not readily generalize from one task to the other. This is partly due to the fact that they do not learn in a compositional way, that is, by discovering skills that are shared by different tasks, and recombining them to solve new problems. In this paper, we explore the compositional generalization capabilities of recurrent neural n...

We study compositional inverses of permutation polynomials, complete map-pings, mutually orthogonal Latin squares, and bent vectorial functions. Recently it was obtained in [33] the compositional inverses of linearized permutation binomials over finite fields. It was also noted in [29] that computing inverses of bijections of subspaces have applications in determining the compositional inverses...

One of the tantalising remaining problems in compositional data analysis lies in how to deal with data sets in which there are components which are essential zeros. By an essential zero we mean a component which is truly zero, not something recorded as zero simply because the experimental design or the measuring instrument has not been sufficiently sensitive to detect a trace of the part. Such ...

It is a recent trend in the literature on verification to study the use of compositionality and abstraction to structure the process of verification; for example, see (Abadi and Lamport, 1993; Hooman, 1994; Dams, Gerth and Kelb, 1996). In (Cornelissen, Jonker and Treur, 1997) a compositional verification method was introduced for logic-based specifications of knowledge-based systems. The curren...

Tree-structured neural networks have proven to be effective in learning semantic representations by exploiting syntactic information. In spite of their success, most existing models suffer from the underfitting problem: they recursively use the same shared compositional function throughout the whole compositional process and lack expressive power due to inability to capture the richness of comp...