Extrinsic Parse Selection
نویسنده
چکیده
This paper reports on one aspect of Locutus, a natural language interface to databases (NLIDB) which uses the output of a highprecision broad-coverage grammar to build semantic representations and ultimately SQL queries. Rather than selecting just a subset of the parses provided by the grammar to use in further processing, Locutus uses all of them. If the meaning of a parse does not conform to the semantic domain of the database, no query is built for it. Thus, intended parses are chosen extrinsically. The parser gives an average of 3.01 parses to the sentences in the GEOQUERY250 corpus. Locutus generates an average of 1.02 queries per sentence for this corpus, all of them correct.
منابع مشابه
Response-based Learning for Machine Translation of Open-domain Database Queries
Response-based learning allows to adapt a statistical machine translation (SMT) system to an extrinsic task by extracting supervision signals from task-specific feedback. In this paper, we elicit response signals for SMT adaptation by executing semantic parses of translated queries against the Freebase database. The challenge of our work lies in scaling semantic parsers to the lexical diversity...
متن کاملUnsupervised Parse Selection for HPSG
Parser disambiguation with precision grammars generally takes place via statistical ranking of the parse yield of the grammar using a supervised parse selection model. In the standard process, the parse selection model is trained over a hand-disambiguated treebank, meaning that without a significant investment of effort to produce the treebank, parse selection is not possible. Furthermore, as t...
متن کاملPartial Parse Selection for Robust Deep Processing
This paper presents an approach to partial parse selection for robust deep processing. The work is based on a bottom-up chart parser for HPSG parsing. Following the definition of partial parses in (Kasper et al., 1999), different partial parse selection methods are presented and evaluated on the basis of multiple metrics, from both the syntactic and semantic viewpoints. The application of the p...
متن کاملExploiting Semantic Information for HPSG Parse Selection
In this paper we present a framework for experimentation on parse selection using syntactic and semantic features. Results are given for syntactic features, dependency relations and the use of semantic classes.
متن کاملEfficiency in Unification-Based N-Best Parsing
We extend a recently proposed algorithm for n-best unpacking of parse forests to deal efficiently with (a) Maximum Entropy (ME) parse selection models containing important classes of non-local features, and (b) forests produced by unification grammars containing significant proportions of globally inconsistent analyses. The new algorithm empirically exhibits a linear relationship between proces...
متن کامل