A semantic scattering model for the automatic interpretation of genitives

Moldovan, Dan; Badulescu, Adriana

doi:10.3115/1220575.1220687

Cited by 40 publications

(8 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus the learning and the validation procedures are generally applicable and we intend to generalize the method for the detection of other semantic relations, such as KINSHIP and PURPOSE. So far, we have obtained encouraging results for a list of 35 general-purpose semantic relations encoded by genitives (Moldovan and Badulescu 2005), by noun compounds (Girju et al 2005), and different noun phrase-level patterns including genitives, noun compounds, and the preposition patterns (Moldovan et al 2004).…”

Section: Limitations and Extensionsmentioning

confidence: 78%

“…A characteristic of the genitives is that they are very ambiguous, as the constructions can be given various interpretations (Moldovan and Badulescu 2005). For instance, genitives can encode relations such as PART-WHOLE (Mary's hand), POSSESSION (Mary's car), KINSHIP (Mary's sister), PROPERTY/ATTRIBUTE HOLDER (Mary's beauty), DEPICTION-DEPICTED (Mary's painting -if it depicts her), SOURCE-FROM (Mary's birth city), or Table 5 Examples of meronymic expressions based on their ambiguity.…”

Section: The Semantic Ambiguity Of Genitive Constructionsmentioning

confidence: 99%

See 1 more Smart Citation

Automatic Discovery of Part–Whole Relations

Gîrju¹,

Bădulescu²,

Moldovan³

2006

Computational Linguistics

Self Cite

113

View full text Add to dashboard Cite

An important problem in knowledge discovery from text is the automatic extraction of semantic relations. This paper presents a supervised, semantically intensive, domain independent approach for the automatic detection of part-whole relations in text. First an algorithm is described that identifies lexico-syntactic patterns that encode part-whole relations. A difficulty is that these patterns also encode other semantic relations, and a learning method is necessary to discriminate whether or not a pattern contains a part-whole relation. A large set of training examples have been annotated and fed into a specialized learning system that learns classification rules. The rules are learned through an iterative semantic specialization (ISS) method applied to noun phrase constituents. Classification rules have been generated this way for different patterns such as genitives, noun compounds, and noun phrases containing prepositional phrases to extract part-whole relations from them. The applicability of these rules has been tested on a test corpus obtaining an overall average precision of 80.95% and recall of 75.91%. The results demonstrate the importance of word sense disambiguation for this task. They also demonstrate that different lexico-syntactic patterns encode different semantic information and should be treated separately in the sense that different clarification rules apply to different patterns.

show abstract

Section: Limitations and Extensionsmentioning

confidence: 78%

Section: The Semantic Ambiguity Of Genitive Constructionsmentioning

confidence: 99%

Automatic Discovery of Part–Whole Relations

Gîrju¹,

Bădulescu²,

Moldovan³

2006

Computational Linguistics

Self Cite

113

View full text Add to dashboard Cite

show abstract

“…When using only language-internal supersense features, the average accuracy is 44.15%. Girju (2007) also trains and tests another state-of-the-art supervised model for English, namely Semantic Scattering (Moldovan and Badulescu, 2005), reporting an average accuracy of 59.07%.…”

Section: Discussionmentioning

confidence: 99%

Automatic identification of semantic relations in Italian complex nominals

Celli

Nissim

2009

Proceedings of the Eighth International Conference on Computational Semantics - IWCS-8 '09

View full text Add to dashboard Cite

This paper addresses the problem of the identification of the semantic relations in Italian complex nominals (CNs) of the type N+P+N. We exploit the fact that the semantic relation, which is underspecified in most cases, is partially made explicit by the preposition. We develop an annotation framework around five different semantic relations, which we use to create a corpus of 1700 Italian CNs, obtaining an inter-annotator agreement of K=.695. Exploiting this data, for each preposition p we train a classifier to assign one of the five semantic relations to any CN of the type N+p+N, by using both string and supersense features. To obtain supersenses, we experiment with a sequential tagger as well as a plain lookup in MultiWordNet, and find that using information obtained from the former yields better results.

show abstract

“…These instances were annotated with semantic relations and analyzed for inter-annotator agreement. The results are compared against two state-of-the-art approaches: a supervised machine learning model, semantic scattering (Moldovan and Badulescu 2005), and a Web-based unsupervised model (Lapata and Keller 2005). Moreover, we show that the Romanian linguistic features contribute more substantially to the overall performance than the features obtained for the other Romance languages.…”

Section: Introductionmentioning

confidence: 97%

The Syntax and Semantics of Prepositions in the Task of Automatic Interpretation of Nominal Phrases and Compounds: A Cross-Linguistic Study

Gîrju

2009

Computational Linguistics

View full text Add to dashboard Cite

In this article we explore the syntactic and semantic properties of prepositions in the context of the semantic interpretation of nominal phrases and compounds. We investigate the problem based on cross-linguistic evidence from a set of six languages: English, Spanish, Italian, French, Portuguese, and Romanian. The focus on English and Romance languages is well motivated. Most of the time, English nominal phrases and compounds translate into constructions of the form N P N in Romance languages, where the P (preposition) may vary in ways that correlate with the semantics. Thus, we present empirical observations on the distribution of nominal phrases and compounds and the distribution of their meanings on two different corpora, based on two state-of-the-art classification tag sets: Lauer's set of eight prepositions and our list of 22 semantic relations. A mapping between the two tag sets is also provided. Furthermore, given a training set of English nominal phrases and compounds along with their translations in the five Romance languages, our algorithm automatically learns classification rules and applies them to unseen test instances for semantic interpretation. Experimental results are compared against two state-of-the-art models reported in the literature.

show abstract

A semantic scattering model for the automatic interpretation of genitives

Cited by 40 publications

References 13 publications

Automatic Discovery of Part–Whole Relations

Automatic Discovery of Part–Whole Relations

Automatic identification of semantic relations in Italian complex nominals

The Syntax and Semantics of Prepositions in the Task of Automatic Interpretation of Nominal Phrases and Compounds: A Cross-Linguistic Study

Contact Info

Product

Resources

About