Tools
Sorted by:
Try your query at:
 |
 |
 |
 |
 |
 |
Results 1 - 10
of
32
Baseline experiments in the extraction of Polish valence frames
- Intelligent Information Processing and Web Mining, Advances in Soft Computing
, 2005
"... Abstract. Initial experiments in learning valence (subcategorisation) frames of Polish verbs from a morphosyntactically annotated corpus are reported here. The learning algorithm consists of a linguistic module, responsible for very simple shal-low parsing of the input text (nominal and prepositiona ..."
Abstract
-
Cited by 4 (3 self)
- Add to MetaCart
Abstract. Initial experiments in learning valence (subcategorisation) frames of Polish verbs from a morphosyntactically annotated corpus are reported here. The learning algorithm consists of a linguistic module, responsible for very simple shal-low parsing of the input text (nominal
Danish Verbs as Knowledge Probes in Corpus-based Terminology Work
"... The aim of this article is to present the first results of a project on the retrieval of terminological information from machine-readable Danish corpora in connection with practical terminology work. Works by Ahmad (1994), Bowker (1996), and Meyer & Mackintosh (1996) about linguistic signals, an ..."
Abstract
- Add to MetaCart
, and especially verbs, inspired me to study the use of such signals to extract terminological information from a Danish corpus. Ahmad uses the term ‘knowledge probe ’ to refer to lexical phrases and verbs which often occur together with terminological data in authentic texts and may thus be used as search
The Development of the Index Thomisticus Treebank Valency Lexicon
"... We present a valency lexicon for Latin verbs extracted from the Index Thomisticus Treebank, a syntactically annotated corpus of Medieval Latin texts by Thomas Aquinas. In our corpus-based approach, the lexicon reflects the empirical evidence of the source data. Verbal arguments are induced directly ..."
Abstract
-
Cited by 4 (4 self)
- Add to MetaCart
We present a valency lexicon for Latin verbs extracted from the Index Thomisticus Treebank, a syntactically annotated corpus of Medieval Latin texts by Thomas Aquinas. In our corpus-based approach, the lexicon reflects the empirical evidence of the source data. Verbal arguments are induced directly
RESEARCH ARTICLE Latent Semantics of Action Verbs Reflect Phonetic Parameters of Intensity and Emotional Content
, 1371
"... Conjuring up our thoughts, language reflects statistical patterns of word co-occurrences which in turn come to describe how we perceive the world. Whether counting how frequently nouns and verbs combine in Google search queries, or extracting eigenvectors from term document matrices made up of Wikip ..."
Abstract
- Add to MetaCart
Conjuring up our thoughts, language reflects statistical patterns of word co-occurrences which in turn come to describe how we perceive the world. Whether counting how frequently nouns and verbs combine in Google search queries, or extracting eigenvectors from term document matrices made up
PAPER Special Issue on Text Processing for Information Access Corpus Based Method of Transforming Nominalized Phrases into Clauses for Text Mining Application
"... SUMMARY Nominalization is a linguistic phenomenon in which events usually described in terms of clauses are expressed in the form of noun phrases. Extracting event structures is an important task in text mining applications. To achieve this goal, clauses are parsed and the argument structure of main ..."
Abstract
- Add to MetaCart
of main verbs are extracted from the parsed results. This kind of preprocessing has been commonly done in the past research. In order to extract event structure from nominalized phrases as well, we need to establish a technique to transform nominalized phrases into clauses. In this paper, we propose a
Robust Information Extraction From Spoken Language Data
- In Proceedings of Eurospeech-99
"... In this paper we address the problem of information extraction from speech data, particularly improving robustness to automatic recognition errors. We describe a baseline probabilistic model that uses wordclass smoothing in a phrase n-gram language model. The model is adjusted to the error character ..."
Abstract
-
Cited by 10 (1 self)
- Add to MetaCart
In this paper we address the problem of information extraction from speech data, particularly improving robustness to automatic recognition errors. We describe a baseline probabilistic model that uses wordclass smoothing in a phrase n-gram language model. The model is adjusted to the error
Automated detection and annotation of term definitions in german text corpora
- In LREC
, 2006
"... We describe an approach to automatically detect and annotate definitions for technical terms in German text corpora. This approach focuses on verbs that typically appear in definitions ( = definitor verbs). We specify search patterns based on the valency frames of these definitor verbs and use them ..."
Abstract
-
Cited by 18 (1 self)
- Add to MetaCart
We describe an approach to automatically detect and annotate definitions for technical terms in German text corpora. This approach focuses on verbs that typically appear in definitions ( = definitor verbs). We specify search patterns based on the valency frames of these definitor verbs and use them
Representing Textual Content in a Generic Extraction Model
"... The system described in this paper automatically extracts and stores information from documents. We have imple-mented a text processing system that uses shallow parsing techniques to extract information from sentences in text documents and stores frames of information in a knowledge base. We intend ..."
Abstract
-
Cited by 1 (0 self)
- Add to MetaCart
The system described in this paper automatically extracts and stores information from documents. We have imple-mented a text processing system that uses shallow parsing techniques to extract information from sentences in text documents and stores frames of information in a knowledge base. We intend
Information Retrieval with a Simplified Conceptual Graph-Like Representation
"... Abstract. We argue for that taking into account semantic relations between words in the text can improve information retrieval performance. We implemented the process of information retrieval with simplified Conceptual Graphlike structures and compare the results with those of the vector space model ..."
Abstract
-
Cited by 1 (0 self)
- Add to MetaCart
noun premodifiers and noun post-modifiers, as well as verb frames, extracted from VerbNet, as a source of definition of semantic roles. VerbNet was chosen since its definitions of semantic roles have much in common with the CG standard. We experimented on a subset of the ImageClef 2008 collection
Mining Subcategorization Information by Using Multiple Feature Loglinear Models
, 1999
"... In this paper we show how several nonindependent features can be conjugated for loglinear statistical modeling of subcategorization information. Having this in mind we will present a method for unsupervised learning of statistical loglinear models for words with the same subcategorization frame, usi ..."
Abstract
-
Cited by 2 (1 self)
- Add to MetaCart
in order to quantitatively characterize word subcategorization frames. Elsewhere, (Marques et. al. 1998a), (Marques et. al. 1998b) we have showed that loglinear modelling (Agresti 1990) can be used for clustering verbs (and other words), based on the occurrence of a single relevant feature extracted from
Results 1 - 10
of
32
