1 |
Méthode d’extraction d’informations géographiques à des fins d’enrichissement d’une ontologie de domaine / Geographical information extraction method in order to enrich a domain ontologyNguyen, Van Tien 15 November 2012 (has links)
Notre thèse se situe dans le contexte du projet ANR GEONTO qui porte sur la constitution, l’alignement, la comparaison et l’exploitation d’ontologies géographiques hétérogènes. Dans ce contexte, notre objectif est d'extraire automatiquement des termes topographiques à partir des récits de voyage afin d'enrichir une ontologie géographique initialement conçue par l'IGN. La méthode proposée permet de repérer et d'extraire des termes à connotation topographiques contenus dans un texte. Notre méthode est basée sur le repérage automatique de certaines relations linguistiques afin d'annoter ces termes. Sa mise en œuvre s'appuie sur le principe des relations n-aires et passe par l'utilisation de méthodes ou de techniques de TAL (Traitement Automatique de la Langue). Il s'agit de relations n-aires entre les termes à extraire et d'autres éléments du textes qui peuvent être repérés à l'aide de ressources externes prédéfinies, telles que des lexiques spécifiques: les verbes de récit de voyage (verbes de déplacement, verbes de perceptions, et verbes topographiques), les pré-positions (prépositions de lieu, adverbes, adjectifs), les noms toponymiques, des thésaurus génériques, des ontologies de domaine (ici l'ontologie géographique initialement conçue par l'IGN). Une fois marquées par des patrons linguistiques, les relations proposées nous permettent d'annoter et d'extraire automatiquement des termes dont les différents indices permettent de déduire qu'ils évoquent des concepts topographiques. Les règles de raisonnement qui permettent ces déductions s'appuient sur des connaissances intrinsèques (évocation du spatial dans la langue) et des connaissances externes contenues dans les ressources ci-dessus évoquées, ou leur combinaison. Le point fort de notre approche est que la méthode proposée permet d'extraire non seulement des termes rattachés directement aux noms toponymiques mais également dans des structures de phrase où d'autres termes s'intercalent. L'expérimentation sur un corpus comportant 12 récits de voyage (2419 pages, fournit par la médiathèque de Pau) a montré que notre méthode est robuste. En résultat, elle a permis d'extraire 2173 termes distincts dont 1191 termes valides, soit une précision de 0,55. Cela démontre que l'utilisation des relations proposées est plus efficace que celle des couples (termes, nom toponymique)(qui donne 733 termes distincts valides avec une précision de 0,38). Notre méthode peut également être utilisée pour d'autres applications telles que la reconnaissance des entités nommées géographiques, l'indexation spatiale des documents textuels. / This thesis is in the context of the ANR project GEONTO covering the constitution, alignment, comparison and exploitation of heterogeneous geographic ontologies. The goal is to automatically extract terms from topographic travelogues to enrich a geographical ontology originally designed by IGN. The proposed method allows identification and extraction of terms contained in a text with a topographical connotation. Our method is based on a model that relies on certain grammatical relations to locate these terms. The implementation of this model requires the use of methods or techniques of NLP (Processing of Language). Our model represents the relationships between terms to extract and other elements of the texts that can be identified by using external predefined resources, such as specific lexicons: verbs of travelogue (verbs of displacement, verbs of perceptions, topographical verbs), pre-positions (prepositions of place, adverbs, adjectives), place name, generic thesauri, ontologies of domain (in our case the geographical ontology originally designed by IGN). Once marked by linguistic patterns, the proposed relationships allow us to annotate and automatically retrieve terms. Then various indices help deduce whether the extracted terms evoke topographical concepts. It is through reasoning rules that deductions are made. These rules are based on intrinsic knowledge (evocation of space in the language) and external knowledge contained in external resources mentioned above, or their combination. The advantage of our approach is that the method can extract not only the terms related directly to place name but also those embedded in sentence structure in which other terms coexisted. Experiments on a corpus consisting of 12 travel stories (2419 pages, provided by the library of Pau) showed that our method is robust. As a result, it was used to extract 2173 distinct terms with 1191 valid terms, with a precision of 0.55. This demonstrates that the use of the proposed relationships is more effective than that of couples (term, place name) (which gives 733 distinct terms valid with an accuracy of 0.38). Our method can also be used for other applications such as geographic named entity recognition, spatial indexing of textual documents.
|
2 |
La formation agentive en français : les composés [VN/A/Adv/P]<sub>N/A</sub> et les dérivés V-<i>ant</i>, V-<i>eur</i> et V-<i>oir</i>(<i>e</i>)Rosenberg, Maria January 2008 (has links)
<p>This study addresses the French morphological construction [VN/A/Adv/P]<sub>N/A</sub>. The main objectives are to posit a single rule for its formation and to question the implications of the agent polysemy. The theoretical framework is lexeme-based morphology, which adheres to weak lexicalism.</p><p>The first part of our analysis is qualitative and concerns the availability aspect of productivity. The method is introspective. The internal semantic patterns of the French construction are examined. Our results give evidence for the claim that a single morphological construction rule, [VN/A/Adv/P]<sub>N/A</sub>, is responsible for the cases where the first constituent is a verb stem, and the second constituent may correspond to an internal argument, an external argument or a semantic adjunct. All cases manifest the same patterns, which are related to the denotative meanings included in the agent polysemy: Agent, Instrument, Locative, Action, Result and Cause. Our contrastive analysis shows that the same patterns are found in the four Swedish agentive formations, [N/A/Adv/PV-are]<sub>N</sub>, [N/A/Adv/PV]<sub>N</sub>, [N/A/Adv/PV-a]<sub>N</sub> and [VN]<sub>N</sub>, which correspond to the French [VN/A/Adv/P]<sub>N/A</sub> construction and which also contain a verbal constituent and its internal or external argument, or an adjunct.</p><p>The second part of our analysis is quantitative and concerns the profitability aspect of productivity. The method is inductive. The aim is to explore the polysemy of agent and its assumed hierarchical structure, in synchrony and diachrony. Four French agentive formations, [VN/A/Adv/P]<sub>N/A</sub> compounds and V-<i>ant</i>, V-<i>eur</i> and V-<i>oir</i>(<i>e</i>) derivations, are included in order to examine semantic competition and blocking effects. Our results give evidence for the existence of an agent polysemy but deny that it has a hierarchical structure valid for every agentive formation. The meanings in the agent polysemy are more or less profitable according to formation type: blocking effects could explain this behaviour.</p>
|
3 |
La formation agentive en français: les composés [VN/A/Adv/P]N/A et les dérivés V-ant, V-eur et V-oir(e)Rosenberg, Maria 04 June 2008 (has links) (PDF)
This study addresses the French morphological construction [VN/A/Adv/P]N/A. The main objectives are to posit a single rule for its formation and to question the implications of the agent polysemy. The theoretical framework is lexeme-based morphology, which adheres to weak lexicalism. The first part of our analysis is qualitative and concerns the availability aspect of productivity. The method is introspective. The internal semantic patterns of the French construction are examined. Our results give evidence for the claim that a single morphological construction rule, [VN/A/Adv/P]N/A, is responsible for the cases where the first constituent is a verb stem, and the second constituent may correspond to an internal argument, an external argument or a semantic adjunct. All cases manifest the same patterns, which are related to the denotative meanings included in the agent polysemy: Agent, Instrument, Locative, Action, Result and Cause. Our contrastive analysis shows that the same patterns are found in the four Swedish agentive formations, [N/A/Adv/PV-are]N, [N/A/Adv/PV]N, [N/A/Adv/PV-a]N and [VN]N, which correspond to the French [VN/A/Adv/P]N/A construction and which also contain a verbal constituent and its internal or external argument, or an adjunct. The second part of our analysis is quantitative and concerns the profitability aspect of productivity. The method is inductive. The aim is to explore the polysemy of agent and its assumed hierarchical structure, in synchrony and diachrony. Four French agentive formations, [VN/A/Adv/P]N/A compounds and V-ant, V-eur and V-oir(e) derivations, are included in order to examine semantic competition and blocking effects. Our results give evidence for the existence of an agent polysemy but deny that it has a hierarchical structure valid for every agentive formation. The meanings in the agent polysemy are more or less profitable according to formation type: blocking effects could explain this behaviour.
|
4 |
La formation agentive en français. Les composés [VN/A/Adv/P]N/A et les dérivés V-ant, V-eur et V-oir(e)Rosenberg, Maria 04 June 2008 (has links) (PDF)
This study addresses the French morphological construction [VN/A/Adv/P]N/A. The main objectives are to posit a single rule for its formation and to question the implications of the agent polysemy. The theoretical framework is lexeme-based morphology, which adheres to weak lexicalism. The first part of our analysis is qualitative and concerns the availability aspect of productivity. The method is introspective. The internal semantic patterns of the French construction are examined. Our results give evidence for the claim that a single morphological construction rule, [VN/A/Adv/P]N/A, is responsible for the cases where the first constituent is a verb stem, and the second constituent may correspond to an internal argument, an external argument or a semantic adjunct. All cases manifest the same patterns, which are related to the denotative meanings included in the agent polysemy: Agent, Instrument, Locative, Action, Result and Cause. Our contrastive analysis shows that the same patterns are found in the four Swedish agentive formations, [N/A/Adv/PV-are]N, [N/A/Adv/PV]N, [N/A/Adv/PV-a]N and [VN]N, which correspond to the French [VN/A/Adv/P]N/A construction and which also contain a verbal constituent and its internal or external argument, or an adjunct. The second part of our analysis is quantitative and concerns the profitability aspect of productivity. The method is inductive. The aim is to explore the polysemy of agent and its assumed hierarchical structure, in synchrony and diachrony. Four French agentive formations, [VN/A/Adv/P]N/A compounds and V-ant, V-eur and V-oir(e) derivations, are included in order to examine semantic competition and blocking effects. Our results give evidence for the existence of an agent polysemy but deny that it has a hierarchical structure valid for every agentive formation. The meanings in the agent polysemy are more or less profitable according to formation type: blocking effects could explain this behaviour.
|
5 |
La formation agentive en français : les composés [VN/A/Adv/P]N/A et les dérivés V-ant, V-eur et V-oir(e)Rosenberg, Maria January 2008 (has links)
This study addresses the French morphological construction [VN/A/Adv/P]N/A. The main objectives are to posit a single rule for its formation and to question the implications of the agent polysemy. The theoretical framework is lexeme-based morphology, which adheres to weak lexicalism. The first part of our analysis is qualitative and concerns the availability aspect of productivity. The method is introspective. The internal semantic patterns of the French construction are examined. Our results give evidence for the claim that a single morphological construction rule, [VN/A/Adv/P]N/A, is responsible for the cases where the first constituent is a verb stem, and the second constituent may correspond to an internal argument, an external argument or a semantic adjunct. All cases manifest the same patterns, which are related to the denotative meanings included in the agent polysemy: Agent, Instrument, Locative, Action, Result and Cause. Our contrastive analysis shows that the same patterns are found in the four Swedish agentive formations, [N/A/Adv/PV-are]N, [N/A/Adv/PV]N, [N/A/Adv/PV-a]N and [VN]N, which correspond to the French [VN/A/Adv/P]N/A construction and which also contain a verbal constituent and its internal or external argument, or an adjunct. The second part of our analysis is quantitative and concerns the profitability aspect of productivity. The method is inductive. The aim is to explore the polysemy of agent and its assumed hierarchical structure, in synchrony and diachrony. Four French agentive formations, [VN/A/Adv/P]N/A compounds and V-ant, V-eur and V-oir(e) derivations, are included in order to examine semantic competition and blocking effects. Our results give evidence for the existence of an agent polysemy but deny that it has a hierarchical structure valid for every agentive formation. The meanings in the agent polysemy are more or less profitable according to formation type: blocking effects could explain this behaviour.
|
Page generated in 0.0657 seconds