Scalable Deep Linguistic Processing: Mind the Lexical Gap
نویسنده
چکیده
Coverage has been a constant thorn in the side of deployed deep linguistic processing applications, largely because of the difficulty in constructing, maintaining and domaintuning the complex lexicons that they rely on. This paper reviews various strands of research on deep lexical acquisition (DLA), i.e. the (semi-)automatic creation of linguistically-rich language resources, particularly from the viewpoint of DLA for precision grammars.
منابع مشابه
Baldwin, Timothy (2007) Scalable Deep Linguistic Processing: Mind the Lexical Gap, In Proceedings of the 21st Pacific Asia Conference on Language, Information and Computation (PACLIC21), Seoul, Korea, pp. 3-12
Coverage has been a constant thorn in the side of deployed deep linguistic processing applications, largely because of the difficulty in constructing, maintaining and domain-tuning the complex lexicons that they rely on. This paper reviews various strands of research on deep lexical acquisition (DLA), i.e. the (semi-)automatic creation of linguistically-rich language resources, particularly fro...
متن کاملProcessing of Lexical Bundles by Persian Speaking Learners of English
Formulaic sequence (FS) is a general term often used to refer to various types of recurrent clusters. One particular type of FSs common in different registers is lexical bundles (LBs). This study investigated whether LBs are stored and processed as a whole in the mind of language users and whether their functional discourse type has any effect on their processing. To serve these objectives, thr...
متن کاملLexical Entry Templates for Robust Deep Parsing
We report on the development and employment of lexical entry templates in a large–coverage unification–based grammar of Spanish. The aim of the work reported in this paper is to provide robust deep linguistic processing in order to make the grammar more adequate for industrial NLP applications.
متن کاملNooJ: a Linguistic Annotation System for Corpus Processing
One characteristic of NooJ is that its corpus processing engine uses large-coverage linguistic lexical and syntactic resources. This allows NooJ users to perform sophisticated queries that include any of the available morphological, lexical or syntactic properties. In comparison with INTEX, NooJ uses a new technology (.NET), a new linguistic engine, and was designed with a new range of applicat...
متن کاملRobust deep linguistic processing
This dissertation deals with the robustness problem of deep linguistic processing. Hand-crafted deep linguistic grammars provide precise modeling of human languages, but are deficient in their capability of handling ill-formed or extra-grammatical inputs. In this dissertation, we argue that with a series of robust processing techniques, improved coverage can be achieved without sacrificing effi...
متن کامل