Clustering adjectives for class acquisition

Torrent, Gemma Boleda; Alemany, Laura Alonso

doi:10.3115/1067737.1067740

Cited by 6 publications

(3 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the future, the models need to be extended to identify not only verb-subject and verb-object metaphors, but also metaphorical expressions in other syntactic constructions (e.g., adjectival or nominal metaphors). Previous distributional clustering and lexical acquisition research has shown that it is possible to model the meanings of a range of word classes using similar techniques (Hatzivassiloglou and McKeown 1993;Boleda Torrent and Alonso i Alemany 2003;Brockmann and Lapata 2003;Zapirain, Agirre, and Màrquez 2009). We thus expect our methods to be equally applicable to metaphorical uses of other word classes and syntactic constructions.…”

Section: Discussionmentioning

confidence: 89%

Multilingual Metaphor Processing: Experiments with Semi-Supervised and Unsupervised Learning

Shutova

Sun²,

Gutiérrez

et al. 2017

Computational Linguistics

View full text Add to dashboard Cite

Highly frequent in language and communication, metaphor represents a significant challenge for Natural Language Processing (NLP) applications. Computational work on metaphor has traditionally evolved around the use of hand-coded knowledge, making the systems hard to scale. Recent years have witnessed a rise in statistical approaches to metaphor processing. However, these approaches often require extensive human annotation effort and are predominantly evaluated within a limited domain. In contrast, we experiment with weakly supervised and unsupervised techniques—with little or no annotation—to generalize higher-level mechanisms of metaphor from distributional properties of concepts. We investigate different levels and types of supervision (learning from linguistic examples vs. learning from a given set of metaphorical mappings vs. learning without annotation) in flat and hierarchical, unconstrained and constrained clustering settings. Our aim is to identify the optimal type of supervision for a learning algorithm that discovers patterns of metaphorical association from text. In order to investigate the scalability and adaptability of our models, we applied them to data in three languages from different language groups—English, Spanish, and Russian—achieving state-of-the-art results with little supervision. Finally, we demonstrate that statistical methods can facilitate and scale up cross-linguistic research on metaphor.

show abstract

Section: Discussionmentioning

confidence: 89%

Multilingual Metaphor Processing: Experiments with Semi-Supervised and Unsupervised Learning

Shutova

Sun²,

Gutiérrez

et al. 2017

Computational Linguistics

View full text Add to dashboard Cite

show abstract

“…One important task in lexical acquisition is the extraction of verb frames and subcategorization frames from corpora (see, e.g., [21]). There has also been a lot of work on clustering adjectives by their semantics [3,6]. Further work has addressed the extraction of hyponyms and hypernyms from corpora [14], and of identifying the particular meaning of adjectives in adjective-noun phrase compounds, e.g.…”

Section: Related Workmentioning

confidence: 99%

Automatic Acquisition of Adjective Lexicalizations of Restriction Classes: a Machine Learning Approach

2016

View full text Add to dashboard Cite

There is an increasing interest in providing common web users with access to structured knowledge bases such as DBpedia, for example by means of question answering systems. An essential task of such systems is transforming natural language questions into formal queries, e.g. expressed in SPARQL. To this end, such systems require knowledge about how the vocabulary elements used in the available ontologies and datasets are verbalized in natural language, covering different verbalization variants, possibly in multiple languages. An important part of such lexical knowledge is constituted by adjectives. In this paper we present and evaluate a machine learning approach to extract adjective lexicalizations from DBpedia. This is a challenge that so far has not been addressed. Our approach achieves an accuracy of 91.15% on a 10-fold cross validation regime. In addition to providing a first baseline system for the task of extracting adjective lexicalizations from DBpedia, we publish the extracted adjective lexicalizations in lemon format for free use by the community.

show abstract

“…1999, associative adjectives (Ferris 1993, Giegerich 2005, relational adjectives (Fellbaum κ.ά. 1993, McNally & Boleda 2004, Boleda Torrent & Alonso i Alemany 2003, denominal adjectives (Coates 1971, Quirk κ.ά. 1972, denominal (relative) adjectives (Raskin & Nirenburg 1998),…”

Section: κριτήρια κατηγοριοποίησηςmentioning

confidence: 99%

Ο Αξιολογικός Ρόλος Του Επιθέτου Και Η Χρήση Του Ως Δείκτη Ιδεολογίας

Fragaki¹,

Φραγκάκη²

View full text Add to dashboard Cite

Γεωργία Φραγκάκη Ο αξιολογικός ρόλος του επιθέτου και η χρήση του ως δείκτη ιδεολογίας: Μελέτη βασισµένη σε σώµατα κειµένων δηµοσιογραφικού λόγου ∆ιδακτορική ∆ιατριβή ΑΘΗΝΑ 2010 Επταµελής εξεταστική επιτροπή Τριµελής επιτροπή: Επόπτρια: Αµαλία Μόζερ, καθηγήτρια Μέλη: ∆ιονύσης Γούτσος, αναπληρωτής καθηγητής Μαρία Κακριδή, επίκουρη καθηγήτρια Αικατερίνη Μπακάκου-Ορφανού, καθηγήτρια Σταµατία Κουτσουλέλου-Μίχου, αναπληρώτρια καθηγήτρια Σπυριδούλα Μπέλλα, επίκουρη καθηγήτρια Ελένη Παναρέτου, επίκουρη καθηγήτρια vii ΚΕΦΑΛΑΙΟ 4: Ο ΑΞΙΟΛΟΓΙΚΟΣ ΡΟΛΟΣ ΤΟΥ ΕΠΙΘΕΤΟΥ 4.1. Η έννοια της αξιολόγησης 4.2. Επίθετα και αξιολόγηση 4.2.1. ∆ιαστάσεις αξιολόγησης 4.2.2. Μηχανισµοί αξιολόγησης 4.2.3. Εύρος αξιολόγησης 4.2.4. Στρατηγικές αξιολόγησης 4.3. Συµπεράσµατα ΚΕΦΑΛΑΙΟ 5: ΕΠΙΘΕΤΑ ΚΑΙ Ι∆ΕΟΛΟΓΙΑ 5.1. Γλωσσολογική προσέγγιση της ιδεολογίας 5.2. Η συχνότητα εµφάνισης των επιθέτων ως δείκτης ιδεολογίας 5.3. Το επίθετο ως δείκτης ιδεολογίας 5.3.1. Το επίθετο ως πόλος έλξης αξιολόγησης 5.3.2. Το επίθετο ως αξιολογητής 5.4. Άλλες γλωσσικές επιλογές και ιδεολογία 5.5.

show abstract

Clustering adjectives for class acquisition

Cited by 6 publications

References 10 publications

Multilingual Metaphor Processing: Experiments with Semi-Supervised and Unsupervised Learning

Multilingual Metaphor Processing: Experiments with Semi-Supervised and Unsupervised Learning

Automatic Acquisition of Adjective Lexicalizations of Restriction Classes: a Machine Learning Approach

Ο Αξιολογικός Ρόλος Του Επιθέτου Και Η Χρήση Του Ως Δείκτη Ιδεολογίας

Contact Info

Product

Resources

About