Best-First Surface Realization
نویسنده
چکیده
Current work in surface realization concentrates on the use of general, abstract algorithms that interpret large, reversible grammars. Only little attention has been paid so far to the many small and simple applications that require coverage of a small sublanguage at different degrees of sophistication. The system TG/2 described in this paper can be smoothly integrated with deep generation processes, it integrates canned text, templates, and context-free rules into a single formalism, it allows for both textual and tabular output, and it can be parameterized according to linguistic preferences. These features are based on suitably restricted production system techniques and on a generic backtracking regime.
منابع مشابه
NIL-UCM: Most-Frequent-Value-First Attribute Selection and Best-Scoring-Choice Realization
The NIL entry for the challenge has been constructed upon the general architecture for developing Natural Language Generation systems provided by the TAP project (Gervás, 2007). TAP (Text Arranging Pipeline) is a set of interfaces that define generic functionality for a pipeline of tasks oriented toward natural language generation, from an initial conceptual input to surface realization as a st...
متن کاملDependency Based Chinese Sentence Realization
This paper describes log-linear models for a general-purpose sentence realizer based on dependency structures. Unlike traditional realizers using grammar rules, our method realizes sentences by linearizing dependency relations directly in two steps. First, the relative order between head and each dependent is determined by their dependency relation. Then the best linearizations compatible with ...
متن کاملA Simple Surface Realization Engine for Telugu
Telugu is a Dravidian language with nearly 85 million first language speakers. In this paper we report a realization engine for Telugu that automates the task of building grammatically well-formed Telugu sentences from an input specification consisting of lexicalized grammatical constituents and associated features. Our realization engine adapts the design approach of SimpleNLG family of surfac...
متن کاملTowards Surface Realization with CCGs Induced from Dependencies
• In this paper, inspired by recent work on converting dependency treebanks (Ambati et al., 2013) and semantic parsing (Kwiatkowski et al., 2010; Artzi & Zettlemoyer, 2013) with Combinatory Categorial Grammar (CCG), we pursue the alternative strategy of inducing a CCG from an enhanced version of the shared task dependencies, with initial experiments showing even better results, competitive with...
متن کاملReferring Expression Generation Using Speaker-based Attribute Selection and Trainable Realization (ATTR)
In the first REG competition, researchers proposed several general-purpose algorithms for attribute selection for referring expression generation. However, most of this work did not take into account: a) stylistic differences between speakers; or b) trainable surface realization approaches that combine semantic and word order information. In this paper we describe and evaluate several end-to-en...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
- CoRR
دوره cmp-lg/9605010 شماره
صفحات -
تاریخ انتشار 1996