Localist Approach to Natural Language Processing

نویسندگان

  • MLADEN STANOJEVIĆ
  • SANJA VRANEŠ
چکیده

Determining the meaning of a sentence in a natural language requires an efficient search mechanism to find the corresponding point in a very large space of sentence meanings. Examination of large search spaces must rely on constraints to guide the search process and provide satisfactory performance. However, existing knowledge representation techniques used in AI, both classical and connectionist, do not satisfy all the requirements needed to represent adequately the semantics, whereby neither of these techniques meet satisfactorily the most important requirement – proper context representation. We propose a knowledge representation technique named Hierarchical Semantic Form that can be used, together with the Space Of Universal Links (SOUL) algorithm, to represent the semantics adequately. To check the viability of the proposed solution we have implemented a prototype Semantic Web service that provides information about flight timetables, defined in a natural language within an ordinary HTML page, using natural language queries. Key-Words: Natural Language Processing, Localist Approach, Connectionist Model, Knowledge Representation

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Dynamic, Non-Local Role Bindings and Inferencing in a Localist Network for Natural Language Understanding

This paper introduces a means to handle the critical problem of nonlocal role-bindings in localist spreading-activation networks. Every conceptual node in the network broadcasts a stable, uniquely-identifying activation pattern, called its signature. A dynamic role-binding is created when a role's binding node has an activation that matches the bound concept's signature. Most importantly, signa...

متن کامل

Challenging the widespread assumption that connectionism and distributed representations go hand-in-hand.

One of the central claims associated with the parallel distributed processing approach popularized by D.E. Rumelhart, J.L. McClelland and the PDP Research Group is that knowledge is coded in a distributed fashion. Localist representations within this perspective are widely rejected. It is important to note, however, that connectionist networks can learn localist representations and many connect...

متن کامل

Integration of Semantic and Syntactic Constraints for Structural Noun Phrase Disambiguation

A fundamental problem in Natural Language Processing is the integration of syntactic and semantic constraints. In this paper we describe a new approach for the integration of syntactic and semantic constraints which takes advantage of a learned memory model. Our model combines localist representations for the integration of constraints and distributed representations for learning semantic const...

متن کامل

Ambiguity resolution and the retrieval of idioms: two approaches

When an idiomatic expression is encountered during natural language processing, the ambiguity between its idiomatic ~md non-idiomatic meaning has to be resolved. Rather than including both meanings in further processing, a conventionality-principle could be applied. This results in best-first processing of the idiomatic analysis. Two models are discussed fot the lexical representation of idioms...

متن کامل

روش جدید متن‌کاوی برای استخراج اطلاعات زمینه کاربر به‌منظور بهبود رتبه‌بندی نتایج موتور جستجو

Today, the importance of text processing and its usages is well known among researchers and students. The amount of textual, documental materials increase day by day. So we need useful ways to save them and retrieve information from these materials. For example, search engines such as Google, Yahoo, Bing and etc. need to read so many web documents and retrieve the most similar ones to the user ...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2006