Related papers: Restricted Parallelism in Object-Oriented Lexical …
Scaling inference-time computation has substantially improved the reasoning capabilities of language models. However, existing methods have significant limitations: serialized chain-of-thought approaches generate overly long outputs,…
OCaml is an industrial-strength, multi-paradigm programming language, widely used in industry and academia. OCaml is also one of the few modern managed system programming languages to lack support for shared memory parallel programming.…
This paper presents generalized probabilistic models for high-order projective dependency parsing and an algorithmic framework for learning these statistical models involving dependency trees. Partition functions and marginals for…
Mixed packing and covering problems are problems that can be formulated as linear programs using only non-negative coefficients. Examples include multicommodity network flow, the Held-Karp lower bound on TSP, fractional relaxations of set…
A framework is proposed for the design and analysis of \emph{network-oblivious algorithms}, namely, algorithms that can run unchanged, yet efficiently, on a variety of machines characterized by different degrees of parallelism and…
We present an approach to Machine Translation that combines the ideas and methodologies of the Example-Based and Lexicalist theoretical frameworks. The approach has been implemented in a multilingual Machine Translation system.
Surprisal theory posits that the processing difficulty of a word is determined by its predictability in context, offering a potential link between human sentence processing and next-word predictions from language models. While language…
Data-Oriented Parsing (dop) ranks among the best parsing schemes, pairing state-of-the art parsing accuracy to the psycholinguistic insight that larger chunks of syntactic structures are relevant grammatical and probabilistic units. Parsing…
Correctness conditions for concurrent objects describe how atomicity of an abstract sequential object may be decomposed. Many different concurrent objects and proof methods for them have been developed. However, arguments about correctness…
Aldwych is proposed as the foundation of a general purpose language for parallel applications. It works on a rule-based principle, and has aspects variously of concurrent functional, logic and object-oriented languages, yet it forms an…
We investigate whether \emph{LLM-based agents} can develop task-oriented communication protocols that differ from standard natural language in collaborative reasoning tasks. Our focus is on two core properties such task-oriented protocols…
The pattern matching capabilities of neural networks can be used to locate syntactic constituents of natural language. This paper describes a fully automated hybrid system, using neural nets operating within a grammatic framework. It…
Transfer learning approaches for Neural Machine Translation (NMT) train a NMT model on the assisting-target language pair (parent model) which is later fine-tuned for the source-target language pair of interest (child model), with the…
The rapid advancement in Large Language Models has been met with significant challenges in their training processes, primarily due to their considerable computational and memory demands. This research examines parallelization techniques…
There are enormous amount of examples of Computation in nature, exemplified across multiple species in biology. One crucial aim for these computations across all life forms their ability to learn and thereby increase the chance of their…
We suggest a general oracle-based framework that captures different parallel stochastic optimization settings described by a dependency graph, and derive generic lower bounds in terms of this graph. We then use the framework and derive…
Typical spoken language understanding systems provide narrow semantic parses using a domain-specific ontology. The parses contain intents and slots that are directly consumed by downstream domain applications. In this work we discuss…
In this paper we present NLOMJ--a natural language object model in Java with English as the experiment language. This modal describes the grammar elements of any permissible expression in a natural language and their complicated relations…
We present a methodology for parallel acceleration of learning in the presence of matrix orthogonality and unitarity constraints of interest in several branches of machine learning. We show how an apparently sequential elementary rotation…
There is often a sort of a protocol associated to each class, stating when and how certain methods should be called. Given that this protocol is, if at all, described in the documentation accompanying the class, current mainstream…