This paper describes a novel method of representing semantic networks of stories (and other text) as a two-mode graph. This method has some advantages over traditional one-mode semantic networks, but has the potential drawback (shared with n-gram text networks) that it contains paths that are not present in the text. An empirical study was devised using a false memory paradigm to determine whet...

We present graph-theoretic analyses of three types of semantic networks: word associations, WordNet, and

This paper attempts to systematize natural language analysis process by (I) use of a partitioned semantic network formalism as the meaning representation and (2) stepwise translation based on Montague Grammar. The meaning representation is obtained in two steps. The first step translates natural language into logical expression. The second step interprets logical expression to generate network ...

A recent trend in network systems is the advanced technology to dynamically handle changes in the system. An important basis relies on the integration of capability and status representation and their semantic descriptions, which is currently not expressive enough. In this paper, we propose a Unified Capability and Status Representation Framework (UniCS) for handling several aspects related to ...

We introduce Deep Semantic Embedding (DSE), a supervised learning algorithm which computes semantic representation for text documents by respecting their similarity to a given query. Unlike other methods that use singlelayer learning machines, DSE maps word inputs into a lowdimensional semantic space with deep neural network, and achieves a highly nonlinear embedding to model the human percepti...

This paper describes a general architecture SCAN for hybrid symbolic connectionist processing of natural language phrases. SCAN's architecture shows how learned connectionist domain-dependent semantic representations can be combined with encoded symbolic syntactic representations. Within this general architecture we focus on a connectionist model for semantic classiication based on a scanning u...

This paper describes some common semantic representations and compares them with the semantic structure, which is introduced as a semantic representation level within a speech processing system. The semantic structure is especially designed to facilitate semantic decoding using exclusively stochastic knowledge within a maximum-a-posteriori decoding algorithm.

This paper describes a quantitative indicator for segmenting narrative text into coherent scenes. The indicator, called the lexical cohesion pro le (LCP), records lexical cohesiveness of words in a xed-length window moving word by word on the text. The cohesiveness of words, which represents their coherence, is computed by spreading activation on a semantic network. The basic idea of LCP is: (1...

Latent representation learned from multi-layered neural networks via hierarchical feature abstraction enables recent success of deep learning. Under the deep learning framework, generalization performance highly depends on the learned latent representation which is obtained from an appropriate training scenario with a taskspecific objective on a designed network model. In this work, we propose ...

Clinical practice guidelines are important instruments to support clinical care. We have analyzed guidelines according to their semantic relations in order to generate a formal representation. We used the UMLS Semantic Network as a basis for our analysis. We defined relations that will be used to automatically identify the control flow described in guidelines for generating a computerinterpreta...