Showing papers on "Natural language understanding published in 1981"
Book•
01 Jan 1981
TL;DR: This thesis is an extensive review of the reference and anaphor problem, and the approaches to it that NLU systems have taken, from early systems such as STUDENT through to current discourse-oriented ones such as PAL.
Abstract: A problem that all computer-based natural language understanding (NLU) systems encounter is that of linguistic reference, and in particular anaphora (abbreviated reference). For example, in a text as simple as: \begin{quote} Nadia showed Sue her new car. The seats were Day-Glo orange. \end{quote} knowing that ``her'''' probably means Nadia and not Sue and that ``the seats'''' means the seats of Nadia''s new car is not a simple task. .br This thesis is an extensive review of the reference and anaphor problem, and the approaches to it that NLU systems have taken, from early systems such as STUDENT through to current discourse-oriented ones such as PAL. .br The problem is first examined in detail, and examples are given of many different types of anaphor, some of which have been ignored by previous authors. The approaches taken in traditional systems are then described and abstracted and it is shown why they were inadequate, and why discourse theme and anaphoric focus need to be taken into account. The strengths and weaknesses of current anaphora theories and approaches are evaluated. The thesis closes with a list of some remaining research problems. .br The thesis has been written so as to be as comprehensible as possible to both AI workers who know no linguistics, and linguists who have not studied artificial intelligence.
157 citations
TL;DR: Relaxation techniques, developed within the Augmented Transition Network (ATN) model, are shown to be adequate to handle many of these cases of language phenomena either considered deviant by linguistic standards or insufficiently addressed by existing approaches.
Abstract: This paper investigates several language phenomena either considered deviant by linguistic standards or insufficiently addressed by existing approaches These include co-occurrence violations, some forms of ellipsis and extraneous forms, and conjunction Relaxation techniques for their treatment in Natural Language Understanding Systems are discussed These techniques, developed within the Augmented Transition Network (ATN) model, are shown to be adequate to handle many of these cases
80 citations
Proceedings Article•
24 Aug 1981TL;DR: A theory of natural language understanding within which two separate components are identified, a language centered one and a context centered one, which clarifies the meaning found by the first component and makes it more specific by attempting to reconcile it with the context of the utterance.
Abstract: We describe a theory of natural language understanding within which we identify two separate components, a language centered one and a context centered one. xn5 rdrme*1 component uses a knowledge Dase consisting of pairings of phrases with the concepts associated with them to determine the meaning of utterances. The latter component clarifies the meaning found by the first one and makes it more specific by attempting to reconcile it with the context of the utterance.
We have constructed a program called PHRAN (PHRasal ANalyzer) which performs the task of the language centered component.
9 citations
Proceedings Article•
24 Aug 1981TL;DR: Some of the consequences which arise when the same parser serves both tasks are explored, including that BORIS often knows the answer to a question before it has completely understood the question.
Abstract: BORIS is an integrated natural language understanding system for narratives. In an integrated system, processes of event assimilation, inference, and episodic memory search occur on a word-by-word basis as parsing proceeds. "Parsing" here refers to the task of building a conceptual representation for each natural language expression. In addition to being integrated, the BORIS parser is also a unified parser. The same parser is used both at story understanding time and question answering time. This paper explores some of the consequences which arise when the same parser serves both tasks. For instance, one such consequence is that BORIS often knows the answer to a question before it has completely understood the question.
6 citations
TL;DR: Whatever an AI worker’s chosen place on that spectrum, doing psychology is not his job: it is liable to miss the distinctively AI insights that come precisely from consideration of processing constraints.
3 citations
29 Jun 1981
TL;DR: Language is a system for encoding and transmitting ideas and a theory that seeks to explain linguistic phenomena in terms of this fact is a functional theory.
Abstract: Language is a system for encoding and transmitting ideas. A theory that seeks to explain linguistic phenomena in terms of this fact is a functional theory. One that does not misses the point. [10]
2 citations
TL;DR: The paper is organized as follows: the two-level modular architecture of DONAU is illustrated and the adopted linguistic models are presented and the understanding process is illustrated through selected examples.
Abstract: The paper is organized as follows: section 1 introduces the article; section 2 illustrates the two-level modular architecture of DONAU; in section 3 the adopted linguistic models are presented and the understanding process is illustrated through selected examples; section 4 is centered on the two aspects of incrementality and interactivity; and section 5 presents some concluding remarks and promising directions for future research.
2 citations
29 Jun 1981
TL;DR: The evaluation technique should yield consistent scores for multiple tests of one system, and the scores for several systems should serve as a means for comparison among systems.
Abstract: Ideally, an evaluation technique should describe an algorithm that an evaluator could use that would result in a score or a vector of scores that depict the level of performance of the natural language system under test. The scores should mirror the subjective evaluation of the system that a qualified judge would make. The evaluation technique should yield consistent scores for multiple tests of one system, and the scores for several systems should serve as a means for comparison among systems. Unfortunately, there is no such evaluation technique for natural language understanding systems. In the following sections, I will attempt to highlight some of the difficulties
1 citations