We describe a combination of a statistical and symbolic approaches for automated scoring of student utterances according to their semantic content. The proposed semantic classifier overcomes the limitations of bag-of-wordsmethods by mapping natural language sentences into predicate representations and matching them against the automatically generated deductive closure of the domain givens, bugg...

We have been developing a general symbolic-statistical modeling language [6, 19, 20] based on the logic programming framework that semantically uni es (and extends) major symbolic-statistical frameworks such as hidden Markov models (HMMs) [18], probabilistic contextfree grammars (PCFGs) [23] and Bayesian networks [16]. The language, PRISM, is intended to model complex symbolic phenomena governe...

This paper examines the implications of connectionist models of cognition for second language theory. Connectionism offers a challenge to the symbolic models which dominate cognitive science. In connectionist models all knowledge is embodied in a network of simple processing units joined by connections which are strengthened or weakened in response to regularities in input patterns. These model...

Discourse in formal domains, such as mathematics, is characterized by a mixture of telegraphic natural language and embedded (semi-)formal symbolic mathematical expressions. We present language phenomena observed in a corpus of dialogs with a simulated tutorial system for proving theorems as evidence for the need for deep syntactic and semantic analysis. We propose an approach to input understa...

MXNet is a multi-language machine learning (ML) library to ease the development of ML algorithms, especially for deep neural networks. Embedded in the host language, it blends declarative symbolic expression with imperative tensor computation. It offers auto differentiation to derive gradients. MXNet is computation and memory efficient and runs on various heterogeneous systems, ranging from mob...

The concurrent functional language Erlang [1] has a number of distinguishing features, like dynamic typing, concurrency via asynchronous message passing or hot code loading, that make it especially appropriate for distributed, faulttolerant, soft real-time applications. The success of Erlang is witnessed by the increasing number of its industrial applications. For instance, Erlang has been used...

Harnessing the statistical power of neural networks to perform language understanding and symbolic reasoning is difficult, when it requires executing efficient discrete operations against a large knowledge-base. In this work, we introduce a Neural Symbolic Machine (NSM), which contains (a) a neural “programmer”, i.e., a sequence-to-sequence model that maps language utterances to programs and ut...

We evaluated formation of simple symbolic categories from initial learning of specific dictated word-picture relations through emergence of untaught or derived relations. Participants were 10 individuals with severe intellectual and language limitations. Three experimental categories were constructed, each containing 1 spoken word (Set A), 1 photograph (Set B), and 1 visual-graphic "lexigram" (...

In this paper we describe a new approach for learning spontaneous language for multiple domains using artificial neural networks. This approach is based on a novel use of flat syntactic and semantic representations, fault-tolerant processing of noisy spontaneous language, and learning of individual domain-dependent subtasks. This approach has been implemented in our parallel and incremental arc...

Semiotic Cognitive Information Processing (SCIP) is inspired by information systems theory and grounded in (natural/artificial) system-environment situations. SCIP systems’ knowledge-based natural language processing (NLP) of information makes it cognitive, their sign and symbol generation, manipulation, and understanding capabilities render it semiotic. Based upon structures whose representati...