Index of papers in Proc. ACL 2010 that mention
  • WordNet
Berant, Jonathan and Dagan, Ido and Goldberger, Jacob
Background
WordNet (Fellbaum, 1998), by far the most widely used resource, specifies relations such as hyponymy, derivation, and entailment that can be used for semantic inference (Budanitsky and Hirst, 2006).
Background
WordNet has also been exploited to automatically generate a training set for a hyponym classifier (Snow et al., 2005), and we make a similar use of WordNet in Section 5.1.
Background
Recently, Szpektor and Dagan (2009) presented the resource Argument-mapped WordNet, providing entailment relations for predicates in WordNet .
Learning Entailment Graph Edges
The first step is preprocessing: We use a large corpus and WordNet to train an entailment classifier that estimates the likelihood that one propositional template entails another.
Learning Entailment Graph Edges
We describe a procedure for learning an entailment classifier, given a corpus and a lexicographic resource ( WordNet ).
Learning Entailment Graph Edges
Last, we use WordNet to automatically generate a training set and train a classifier.
WordNet is mentioned in 15 sentences in this paper.
Topics mentioned in this paper:
Han, Xianpei and Zhao, Jun
Abstract
In recent years, the increasing availability of large-scale, rich semantic knowledge sources (such as Wikipedia and WordNet ) creates new opportunities to enhance the named entity disambiguation by developing algorithms which can exploit these knowledge sources at best.
Introduction
Fortunately, in recent years, due to the evolution of Web (e.g., the Web 2.0 and the Semantic Web) and many research efforts for the construction of knowledge bases, there is an increasing availability of large-scale knowledge sources, such as Wikipedia and WordNet .
Introduction
The key point of our method is a reliable semantic relatedness measure between concepts (including WordNet concepts, NEs and Wikipedia concepts), called Structural Semantic Relatedness, which can capture both the explicit semantic relations between concepts and the implicit semantic knowledge embedded in graphs and networks.
The Structural Semantic Relatedness Measure
We extract three types of semantic relations (semantic relatedness between Wikipedia concepts, lexical relatedness between WordNet concepts and social relatedness between NEs) correspondingly from three knowledge sources: Wikipedia, WordNet and NE Co-occurrence Corpus.
The Structural Semantic Relatedness Measure
WordNet 3.02 (Fellbaum et al., 1998), a lexical knowledge source includes over 110,000 WordNet concepts (word senses about English words).
The Structural Semantic Relatedness Measure
Various lexical relations are recorded between WordNet concepts, such as hyponyms, holonym and synonym.
WordNet is mentioned in 15 sentences in this paper.
Topics mentioned in this paper:
Hassan, Ahmed and Radev, Dragomir R.
Related Work
(2004) construct a network based on WordNet synonyms and then use the shortest paths between any given word and the words ’good’ and ’bad’ to determine word polarity.
Related Work
’ good’ and ’bad’ themselves are closely related in WordNet with a 5-long sequence “good, sound, heavy, big, bad”.
Related Work
Hu and Liu (2004) use WordNet synonyms and antonyms to predict the polarity of words.
Word Polarity
One such important source is WordNet (Miller, 1995).
Word Polarity
WordNet is a large lexical database of English.
Word Polarity
The simplest approach is to connect words that occur in the same WordNet synset.
WordNet is mentioned in 19 sentences in this paper.
Topics mentioned in this paper:
Ide, Nancy and Baker, Collin and Fellbaum, Christiane and Passonneau, Rebecca
Conclusion
In addition, by virtue of its WordNet and FrameNet annotations, MASC will be linked to parallel WordNets and FrameNets in languages other than English, thus creating a global resource for multilingual technologies, including machine translation.
MASC Annotations
The MASC project is itself producing annotations for portions of the corpus for WordNet senses and FrameNet frames and frame elements.
MASC Annotations
4This includes WordNet sense annotations, which are not listed in Table 2 because they are not applied to full texts; see Section 3.1 for a description of the WordNet sense annotations in MASC.
MASC Annotations
3.1 WordNet Sense Annotations
WordNet is mentioned in 11 sentences in this paper.
Topics mentioned in this paper:
Li, Linlin and Roth, Benjamin and Sporleder, Caroline
Experimental Setup
The data were annotated with coarse-grained senses which were obtained by clustering senses from the WordNet 2.1 sense inventory based on the procedure proposed by Navigli (2006).
Introduction
Previous approaches using topic models for sense disambiguation either embed topic features in a supervised model (Cai et al., 2007) or rely heavily on the structure of hierarchical lexicons such as WordNet (Boyd-Graber et al., 2007).
Related Work
(2007) enhance the basic LDA algorithm by incorporating WordNet senses as an additional latent variable.
Related Work
Instead of generating words directly from a topic, each topic is associated with a random walk through the WordNet hierarchy which generates the observed word.
Related Work
iosyncracies in the hierarchical structure of WordNet can harm performance.
The Sense Disambiguation Model
These paraphrases can be taken from an existing resource such as WordNet (Miller, 1995) or supplied by the user (see Section 4).
The Sense Disambiguation Model
In Model I and Model 11, the sense paraphrases are obtained from WordNet , and both the context and the sense paraphrases are treated as documents, 0 2 dc and s 2 d8.
The Sense Disambiguation Model
WordNet is a fairly rich resource which provides detailed information about word senses (glosses, example sentences, synsets, semantic relations between senses, etc.).
WordNet is mentioned in 16 sentences in this paper.
Topics mentioned in this paper:
Navigli, Roberto and Ponzetto, Simone Paolo
Abstract
The resource is automatically constructed by means of a methodology that integrates lexicographic and encyclopedic knowledge from WordNet and Wikipedia.
BabelNet
Concepts and relations in BabelNet are harvested from the largest available semantic lexicon of English, WordNet , and a wide-coverage collaboratively edited encyclopedia, the English Wikipedia (Section 3.1).
BabelNet
We collect (a) from WordNet , all available word senses (as concepts) and all the semantic pointers between synsets (as relations); (b) from Wikipedia, all encyclopedic entries (i.e.
BabelNet
their concepts in common) by establishing a mapping between Wikipedia pages and WordNet senses (Section 3.2).
Introduction
A pioneering endeavor was WordNet (Fellbaum, 1998), a computational lexicon of English based on psycholinguistic theories.
Introduction
Wikipedia represents the perfect complement to WordNet , as it provides multilingual lexical knowledge of a mostly encyclopedic nature.
Introduction
But while a great deal of work has been recently devoted to the automatic extraction of structured information from Wikipedia (Wu and Weld, 2007; Ponzetto and Strube, 2007; Suchanek et al., 2008; Medelyan et al., 2009, inter alia), the knowledge extracted is organized in a looser way than in a computational lexicon such as WordNet .
Methodology
WordNet .
Methodology
The most popular lexical knowledge resource in the field of NLP is certainly WordNet , a computational lexicon of the English language.
WordNet is mentioned in 73 sentences in this paper.
Topics mentioned in this paper:
Vickrey, David and Kipersztok, Oscar and Koller, Daphne
Abstract
Our system combines multiple preexisting sources of similarity data (a standard thesaurus, WordNet , contextual similarity), enabling it to capture many types of similarity groups (“synonyms of crash,” “types of car,” etc.).
Set Expansion
We consider three similarity data sources: the Moby thesaurus1 , WordNet (Fellbaum, 1998), and distributional similarity based on a large corpus of text (Lin, 1998).
Set Expansion
Unlike some other thesauri (such as WordNet and thesaurus.com), entries are not broken down by word sense.
Set Expansion
Unlike some other thesauri (including WordNet and thesaurus.com), the entries are not broken down by word sense or part of speech.
WordNet is mentioned in 11 sentences in this paper.
Topics mentioned in this paper:
Ritter, Alan and Mausam and Etzioni, Oren
Experiments
Finally, we report on the quality of a large database of Wordnet-based preferences obtained after manually associating our topics with Wordnet classes (Section 4.4).
Experiments
We then automatically filtered out any rules which contained a negation, or for which the antecedent and consequent contained a pair of antonyms found in WordNet (this left us with 85 rules).
Experiments
Table 3: Top 10 and Bottom 10 ranked inference rules ranked by LDA-SPafter automatically filtering out negations and antonyms (using WordNet ).
Introduction
Resnik (1996) presented the earliest work in this area, describing an information-theoretic approach that inferred selectional preferences based on the WordNet hypernym hierarchy.
Introduction
This avoids problems like WordNet’s poor coverage of proper nouns and is shown to improve performance.
Previous Work
WordNet ), or automatically generated (Pantel, 2003).
WordNet is mentioned in 10 sentences in this paper.
Topics mentioned in this paper:
Shutova, Ekaterina
Automatic Metaphor Interpretation
Talking Points are a set of characteristics of concepts belonging to source and target domains and related facts about the world which the authors acquire automatically from WordNet and from the web.
Automatic Metaphor Recognition
They mine WordNet (Fellbaum, 1998) for the examples of systematic polysemy, which allows to capture metonymic and metaphorical relations.
Automatic Metaphor Recognition
The authors search for nodes that are relatively high up in the WordNet hierarchy and that share a set of common word forms among their descendants.
Automatic Metaphor Recognition
They use hyponymy relation in WordNet and word bigram counts to predict metaphors at a sentence level.
Metaphor Annotation in Corpora
A number of metaphorical senses are included in WordNet , however without any accompanying semantic annotation.
Metaphor Resources
5EuroWordNet is a multilingual database with wordnets for several European languages (Dutch, Italian, Spanish, German, French, Czech and Estonian).
Metaphor Resources
The wordnets are structured in the same way as the Princeton WordNet for English.
Metaphor Resources
WordNet (Lonneker and Eilts, 2004), would undoubtedly provide a new platform for experiments and enable researchers to directly compare their results.
WordNet is mentioned in 10 sentences in this paper.
Topics mentioned in this paper:
Park, Keun Chan and Jeong, Yoonjae and Myaeng, Sung Hyon
Conclusion and Future Work
For verb classes, in particular, we devised a method for classifying all the verbs and verb phrases in WordNet into the activity and state classes.
Conclusion and Future Work
The experimental results show that verb and verb phrase classification method is reasonably accurate with 91% precision and 78% recall with manually constructed gold standard consisting of 80 verbs and 82% accuracy for a random sample of all the WordNet entries.
Experience Detection
We collected all hyponyms of words “do” and “act”, from WordNet (Fellbaum, 1998).
Experience Detection
Lastly, we removed all the verbs that are under the hierarchy of “move” from WordNet .
Experience Detection
In addition, the lexicon we constructed for the baseline (i.e., using the WordNet ) contains more errors than our activity lexicon for activity verbs.
Lexicon Construction
We consider all the verbs and verb phrases in WordNet (Fellbaum, 1998) which is the largest electronic lexical database.
Lexicon Construction
Based on the query matrix in table 2, we issued queries for all the verbs and verb phrases from WordNet to a search engine.
Lexicon Construction
We finally trained our model with the top 10 features and classified all WordNet verbs and verb phrases.
Related Work
Since our work is specifically geared toward domain-independent experience detection, we attempted to maximize the coverage by using all the verbs in WordNet , as opposed to the verbs appearing in a particular domain-specific corpus (e.g., medicine domain) as done in the previous work.
WordNet is mentioned in 9 sentences in this paper.
Topics mentioned in this paper:
Kozareva, Zornitsa and Hovy, Eduard
Introduction
(Pennacchiotti and Pantel, 2006) proposed an algorithm for automatically ontologizing semantic relations into WordNet .
Introduction
However, despite its high precision entries, WordNet’s limited coverage makes it impossible for relations whose arguments are not present in WordNet to be incorporated.
Related Work
They mapped each argument of the relation into WordNet and identified the senses for which the relation holds.
Related Work
Unfortunately, despite its very high precision entries, WordNet is known to have limited coverage, which makes it impossible for algorithms to map the content of a relation whose arguments are not present in WordNet .
Related Work
To surmount this limitation, we do not use WordNet , but employ a different method of obtaining superclasses of a filler term: the inverse doubly-anchored patterns DAP‘1 (Hovy et al., 2009), which, given two arguments, harvests its supertypes from the source corpus.
Results
Since our problem definition differs from available related work, and WordNet does not contain all harvested arguments as shown in (Hovy et al., 2009), it is not possible to make a direct comparison.
WordNet is mentioned in 7 sentences in this paper.
Topics mentioned in this paper:
Huang, Ruihong and Riloff, Ellen
Related Work
These features are typically obtained from external resources such as Wordnet (Miller, 1990).
Related Work
The first baseline searches for each head noun in WordNet and labels the noun as category Ck, if it has a hypernym synset corresponding to that category.
Related Work
We manually identified the WordNet synsets that, to the best of our ability, seem to most closely correspond
WordNet is mentioned in 6 sentences in this paper.
Topics mentioned in this paper:
Thater, Stefan and Fürstenau, Hagen and Pinkal, Manfred
Conclusion
We further showed that a weakly supervised heuristic, making use of WordNet sense ranks, can be significantly improved by incorporating information from our system.
Experiment: Ranking Word Senses
WordNet (Fellbaum, 1998) senses of w apply to this occurrence of w.
Experiment: Ranking Word Senses
The dataset contains ordinal judgments of the applicability of WordNet senses on a 5 point scale, ranging from completely difi‘er—ent to identical for eight different lemmas in 50 different sentential contexts.
Experiment: Ranking Word Senses
We apply the same method as in Section 4.3: For each instance in the dataset, we compute the second-order vector of the target verb, contextually constrain it by the first-order vectors of the verb’s arguments, and compare the resulting vector to the vectors that represent the different WordNet senses of the verb.
WordNet is mentioned in 6 sentences in this paper.
Topics mentioned in this paper:
Tratz, Stephen and Hovy, Eduard
Automated Classification
We use a Maximum Entropy (Berger et al., 1996) classifier with a large number of boolean features, some of which are novel (e. g., the inclusion of words from WordNet definitions).
Automated Classification
The WordNet gloss terms had a surprisingly strong influence.
Automated Classification
As far as we know, this is the first time that WordNet definition words have been used as features for noun compound interpretation.
Related Work
Kim and Baldwin (2005) and Turney (2006) use nearest neighbor approaches based upon WordNet (Fellbaum, 1998) and Tumey’s Latent Relational Analysis, respectively.
WordNet is mentioned in 4 sentences in this paper.
Topics mentioned in this paper:
de Marneffe, Marie-Catherine and Manning, Christopher D. and Potts, Christopher
Analysis and discussion
(2008) use WordNet to develop sentiment lexicons in which each word has a positive or negative value associated with it, representing its strength.
Analysis and discussion
The algorithm begins with seed sets of positive, negative, and neutral terms, and then uses the synonym and antonym structure of WordNet to expand those initial sets and refine the relative strength values.
Methods
We also replace the negation and the adjective by the antonyms given in WordNet (using the first sense).
WordNet is mentioned in 3 sentences in this paper.
Topics mentioned in this paper:
Ó Séaghdha, Diarmuid
Related work
Many approaches to the problem use lexical taxonomies such as WordNet to identify the semantic classes that typically fill a particular argument slot for a predicate (Resnik, 1993; Clark and Weir, 2002; Schulte im Walde et al., 2008).
Related work
(2007) integrate a model of random walks on the WordNet graph into an LDA topic model to build an unsupervised word sense disambiguation system.
Related work
Reisinger and Pasca (2009) use LDA-like models to map automatically acquired attribute sets onto the WordNet hierarchy.
WordNet is mentioned in 3 sentences in this paper.
Topics mentioned in this paper: