Related papers: Measuring non-trivial compositionality in emergent…
A recent study of bugs in real-world concurrent and distributed systems found that, while implementations of individual protocols tend to be robust, the composition of multiple protocols and its interplay with internal computation is the…
We study the weakest model of quantum nondeterminism in which a classical proof has to be checked with probability one by a quantum protocol. We show the first separation between classical nondeterministic communication complexity and this…
Most existing recursive neural network (RvNN) architectures utilize only the structure of parse trees, ignoring syntactic tags which are provided as by-products of parsing. We present a novel RvNN architecture that can provide dynamic…
Lexical chain consists of cohesion words in a document, which implies the underlying structure of a text, and thus facilitates downstream NLP tasks. Nevertheless, existing work focuses on detecting the simple surface lexicons with shallow…
One of the fundamental requirements for models of semantic processing in dialogue is incrementality: a model must reflect how people interpret and generate language at least on a word-by-word basis, and handle phenomena such as fragments,…
Cross-technology communication(CTC) enables seamless interactions between diverse wireless technologies. Most existing work is based on reversing the transmission path to identify the appropriate payload to generate the waveform that the…
The abstraction of musical structures (notes, melodies, chords, harmonic or rhythmic progressions, etc.) as mathematical objects in a geometrical space is one of the great accomplishments of contemporary music theory. Building on this…
Artificial agents have been shown to learn to communicate when needed to complete a cooperative task. Some level of language structure (e.g., compositionality) has been found in the learned communication protocols. This observed structure…
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…
Deep compositional models of meaning acting on distributional representations of words in order to produce vectors of larger text constituents are evolving to a popular area of NLP research. We detail a compositional distributional…
Principal component analysis (PCA) aims at estimating the direction of maximal variability of a high-dimensional dataset. A natural question is: does this task become easier, and estimation more accurate, when we exploit additional…
Tangent Model Composition (TMC) is a method to combine component models independently fine-tuned around a pre-trained point. Component models are tangent vectors to the pre-trained model that can be added, scaled, or subtracted to support…
Many neural nets appear to represent data as linear combinations of "feature vectors." Algorithms for discovering these vectors have seen impressive recent success. However, we argue that this success is incomplete without an understanding…
Computability theory is traditionally conceived as the theoretical basis of informatics. Nevertheless, numerous proposals transcend computability theory, in particular by emphasizing interaction of modules, or components, parts,…
Protocols do not work alone, but together, one protocol relying on another to provide needed services. Many of the problems in cryptographic protocols arise when such composition is done incorrectly or is not well understood. In this paper…
We investigate the ability of language models to perform compositional reasoning tasks where the overall solution depends on correctly composing the answers to sub-problems. We measure how often models can correctly answer all sub-problems…
End-to-end deep neural networks have achieved remarkable success across various domains but are often criticized for their lack of interpretability. While post hoc explanation methods attempt to address this issue, they often fail to…
Suppose that Alice and Bob are given each an infinite string, and they want to decide whether their two strings are in a given relation. How much communication do they need? How can communication be even defined and measured for infinite…
Many scientific datasets are compositional in nature. Important biological examples include species abundances in ecology, cell-type compositions derived from single-cell sequencing data, and amplicon abundance data in microbiome research.…
Beneficial to advanced computing devices, models with massive parameters are increasingly employed to extract more information to enhance the precision in describing and predicting the patterns of objective systems. This phenomenon is…