Pragmatics and Natural Language Generation
نویسنده
چکیده
This paper addresses the question "why and how is it that we say the same thing differently to different people, or even to the same person in different circumstances?" We vary the content and form of our text in order to convey more information than is contained in the literal meanings of our words. This information expresses the speaker's interpersonal goals toward the hearer and, in general, his or her perception of the pragmatic aspects of the conversation. This paper discusses two insights that arise when one studies this question: the existence of a level of organization that mediates between communicative goals and generator decisions, and the interleaved planningrealization regime and associated monitoring required for generation. To illustrate these ideas, a computer program is described which contains plans and strategies to produce stylistically appropriate texts from a single representation under various settings that model pragmatic circumstances.
منابع مشابه
Автоматическое порождение фраз естественного языка по OWL-модели, семантике и прагматике (Automatic Natural Language Generation Using an OWL Model, Semantics and Pragmatics)
متن کامل
A Flexible Pragmatics-Driven Language Generator for Animated Agents
This paper describes the NECA MNLG; a fully implemented Multimodal Natural Language Generation module. The MNLG is deployed as part of the NECA system which generates dialogues between animated agents. The generation module supports the seamless integration of full grammar rules, templates and canned text. The generator takes input which allows for the specification of syntactic, semantic and p...
متن کاملReasoning about Pragmatics with Neural Listeners and Speakers
We present a model for contrastively describing scenes, in which context-specific behavior results from a combination of inferencedriven pragmatics and learned semantics. Like previous learned approaches to language generation, our model uses a simple featuredriven architecture (here a pair of neural “listener” and “speaker” models) to ground language in the world. Like inference-driven approac...
متن کاملLearning Spatial Knowledge for Text to 3D Scene Generation
We address the grounding of natural language to concrete spatial constraints, and inference of implicit pragmatics in 3D environments. We apply our approach to the task of text-to-3D scene generation. We present a representation for common sense spatial knowledge and an approach to extract it from 3D scene data. In text-to3D scene generation, a user provides as input natural language text from ...
متن کاملStrategies for Specifying Relations ∗
The generation perspective taken by optimality theoretic syntax has a lot in common with the insights gained in natural language generation. This paper explores how insights about NP generation (e.g. Reiter & Dale (2000), van Deemter (2004)) can be made fruitful for explaining the semantics and pragmatics of sentences with more than one plural NP by exploiting optimality theoretic pragmatics, a...
متن کاملPragmatics and Agent Communication Languages
With an eye to increased efficiency, agent communication language (ACL) designers have heeded the analogy with natural language and introduced elements from natural language pragmatics (NLP) into their designs. However, ACL pragmatics has not availed itself of NLP advances to the extent that it could. While a few aspects of pragmatics are incorporated, most notably speech acts, their inclusion ...
متن کاملذخیره 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 ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- Artif. Intell.
دوره 43 شماره
صفحات -
تاریخ انتشار 1990