This paper presents a semi-latent topic model for semantic domain detection in spoken language understanding systems. We use labeled utterance information to capture latent topics, which directly correspond to semantic domains. Additionally, we introduce an ’informative prior’ for Bayesian inference that can simultaneously segment utterances of known domains into classes and divide them from ou...

We use systematic functional method to analyze and try to find out the estimated correlation behind several different texts. Ideology makes great influences on translation expression and strategy, which thus, is the product of the ideology. Language understanding means to obtain a semantic network and conditional information from a text in a deep sense.

This paper describes the construction and use of language models specific to semantic concepts. A tolerance mechanism is introduced in order to design conceptual constituents that cover longer word patterns while remaining robust to spontaneous speech disfluencies and recognition errors. These models are obtained from sentence patterns which grow from essential information to longer sequences o...

Conveying information in a false or indirect manner in consideration of listeners’ wants (i.e. being polite) seemingly contradicts an important goal of a cooperative speaker: information transfer. We propose that a cooperative speaker considers both epistemic utility, or utility of providing the listener new and accurate information, and social utility, or utility of maintaining or boosting the...

In contrast to symbolic models of language understanding, embodied models of language comprehension suggest that language is closely connected with visual and motor processing. In the current study we show that motion words, such as rise or fall, are processed faster if displayed against a background of compatible motion (e.g., upward vs. downward random dot motion with 60% motion coherence). H...

The ubiquity of metaphor in our everyday communication makes it an important problem for natural language understanding. Yet, the majority of metaphor processing systems to date rely on handengineered features and there is still no consensus in the field as to which features are optimal for this task. In this paper, we present the first deep learning architecture designed to capture metaphorica...

In this paper we describe a method of classifying facts (information) into categories or levels; where each level signiies a diierent degree of diiculty of extracting the fact from a piece of text containing it. We use this method to analyze the performances of three MUC systems (BBN, NYU, and SRI) based on their ability to extract a set of standard facts (at diierent levels) from two diierent ...

We have begun a project to automatically create the lexico-syntactic resources for a microplanner as a side-effect of running a domain-specific language understanding system. The resources are parameterized synchronous TAG Derivation Trees. Since the KB is assembled from the information in the texts that these resources are abstracted from, it will decompose along those same lines when used for...

This paper describes OTTHO (On the Tip of my THOught), an artificial player able to solve a very popular language game, called “The Guillotine”, broadcast by the Italian National TV company. The game demands knowledge covering a broad range of topics, such as politics, literature, history, proverbs, and popular culture. The rule of the game is simple: the player observes five words, generally u...

 Towards Natural-Language Understanding and Automated Enforcement of Privacy Rules and Regulations in the Cloud: Survey and Bibliography Nick Papanikolaou, Siani Pearson, Marco Casassa Mont