Session 2: Natural Language I
نویسنده
چکیده
The first paper, by L. Schubert and C. Hwang, concentrated on compositionally defining the mapping between a sentence and an appropriate meaning representation that takes tense and aspect into account. In order to derive non-indexical formulae from indexical ones as a function of context, they make use of a novel type of context component, a tense tree which evolves throughout the discourse. Occurrences of tense-aspect operators are represented as tree branches corresponding to episode (event) relationships. An interesting feature of these trees is that one can "read off" the tree the relationships implicit in the tense-aspect operators and surface ordering of sentences.
منابع مشابه
Session 11 - Natural Language III
The five papers in this session, as well as the ten papers in the other two natural language sessions, can be classified into three broad categories: (1) statistical approaches to natural language processing and the automatic acquisition of linguistic structure (2 out of 5 papers in this session; 8 out of 15 overall); (2) robust processing of texts by combining multiple partial analyses (2 out ...
متن کاملSession 4: Statistical Language Modeling
Corpus based Natural Language Processing (NLP) is now a well established paradigm in NLP. The availability of large corpora, often annotated in various way has led to the development of a variety of approaches to statistical language modeling. The papers in this session represent many of these important approaches. I will try to classify these papers along different dimensions, thus providing t...
متن کاملKnowledge Organization and Application: Brief Comments on Papers in the Session
Brackman describes a l a t t i ce l i ke structured inheritance network (KLONE) as a language for exp l i c i t representation of natural language conceptual information. Multiple descriptions can be represented. How does the f a c i l i t y d i f fe r from a similar one in KRL? Belief representations appear to be only impl ic i t . Quantification is handled through a set of "structural descrip...
متن کاملSession 2: Language Modeling
This session presented four interesting papers on statistical language modeling aimed for improved large-vocabulary speech recognition. The basic problem in language modeling is to derive accurate underlying representations from a large amount of training data, which shares the same fundamental problem as acoustic modeling. As demonstrated in this session, many techniques used for acoustic mode...
متن کاملSession 1: Spoken Language Systems
Without the ability to interpret natural language, speech recognition is suited only for a subset of tasks (though certainly not trivial ones), such as data entry, simple commands or dictation. Similarly, without speech recognition natural language is restricted to the interpretation of written language, a stylized form of human communication. Spoken language systems thus represent an attempt t...
متن کاملA Linguistics Oriented Programming Language
A programming language fo r natural language processing programs is descr ibed. Examples of the output of programs w r i t t e n using it are g iven. The reasons fo r various design decisions are discussed. An actual session wi th the system is presented, in which a small fragment of an Engl ish-to-French t r ans la to r is devel oped. Some of the l i m i t a t i o n s of the system are d i s c...
متن کامل