What can be learned from raw texts?

Basili, Roberto; Pazienza, Maria Teresa; Velardi, Paola

doi:10.1007/bf00982637

Cited by 11 publications

(2 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…this is actually a variant of the preceding point: a corpus where each word is marked for semantic category can be used to learn selectional restrictions or taxonomies [22]. The same idea lies behind some statistical approaches to MLP, which learn word to code associations on the basis of a manually provided training sample.…”

Section: Annotated Corpora As a Precious Resourcementioning

confidence: 99%

From Text to Knowledge: a Unifying Document-Centered View of Analyzed Medical Language

Zweigenbaum¹,

Bouaud²,

Bachimont³

et al. 1998

Methods Inf Med

View full text Add to dashboard Cite

Although medical language processing (MLP) has achieved some success, the actual use and dissemination of data extracted from free text by MLP systems is still very limited. We claim that the adoption of an ‘enricheddocument’ paradigm (or ‘document-centered’ view) can help to address this issue. We present this paradigm and explain how it can be implemented, then discuss its expected benefits both for end-users and MLP researchers.

show abstract

Section: Annotated Corpora As a Precious Resourcementioning

confidence: 99%

From Text to Knowledge: a Unifying Document-Centered View of Analyzed Medical Language

Zweigenbaum¹,

Bouaud²,

Bachimont³

et al. 1998

Methods Inf Med

View full text Add to dashboard Cite

show abstract

“…Purely statistical ones, such as [15] often obtain groups of words that characterize a sense of a target word. Other approaches ( [1], [6], [10], [11], [14]) are more syntactical and obtain classes of words with similar meanings 1 : ARIOSTO [1] and STARTEX [14] use manual semantic tagging and next classification, but while STARTEX uses not tagged repeated text segments, ARIOSTO uses syntactically parsed text. On the contrary ASIUM [6] applies a cooperative clustering algorithm on classes obtained from syntactically parsed texts.…”

Section: Introductionmentioning

confidence: 99%

SVETLAN’ Or How to Classify Words Using Their Context

Chalendar

Grau

2000

Knowledge Engineering and Knowledge Management Methods, Models, and Tools

View full text Add to dashboard Cite

Abstract. Using semantic knowledge in NLP applications always improves their competence. Broad lexicons have been developed, but there are few resources which contain semantic information available for words and which are non-dedicated to specialized domains. In order to build such a base, we designed a system, SVETLAN', able to learn categories of nouns from texts, whatever their domain. In order to avoid general classes mixing all the meanings of words, they are learned taking into account the contextual use of words.

show abstract

Lexical acquisition and information extraction

Basili¹,

Pazienza²

1997

Information Extraction a Multidisciplinary Approach to an Emerging Information Technology

View full text Add to dashboard Cite

What can be learned from raw texts?

Cited by 11 publications

References 26 publications

From Text to Knowledge: a Unifying Document-Centered View of Analyzed Medical Language

From Text to Knowledge: a Unifying Document-Centered View of Analyzed Medical Language

SVETLAN’ Or How to Classify Words Using Their Context

Lexical acquisition and information extraction

Contact Info

Product

Resources

About