Abstract | To train the system, we extract substructures of WordNet and dis-criminatively learn to reproduce them, using adaptive subgradient stochastic optimization. |
Abstract | On the task of reproducing sub-hierarchies of WordNet , our approach achieves a 51% error reduction over a chance baseline, including a 15% error reduction due to the non-hypernym—factored sibling features. |
Experiments | We considered two distinct experimental setups, one that illustrates the general performance of our model by reproducing various medium-sized WordNet domains, and another that facilitates comparison to previous work by reproducing the much larger animal subtree provided by Kozareva and Hovy (2010). |
Experiments | General setup: In order to test the accuracy of structured prediction on medium-sized full-domain taxonomies, we extracted from WordNet 3.0 all bottomed-out full subtrees which had a tree-height of 3 (i.e., 4 nodes from root to leaf), and contained (10, 50] terms.11 This gives us 761 non-overlapping trees, which we partition into |
Experiments | To project WordNet synsets to terms, we used the first (most frequent) term in each synset. |
Introduction | However, currently available taxonomies such as WordNet are incomplete in coverage (Pennacchiotti and Pantel, 2006; Hovy et al., 2009), unavailable in many domains and languages, and |
Introduction | Figure 1: An excerpt of WordNet’s vertebrates taxonomy. |
Introduction | First, on the task of recreating fragments of WordNet , we achieve a 51% error reduction on ancestor-based F1 over a chance baseline, including a 15% error reduction due to the non-hypernym-factored sibling features. |
Abstract | Our approach leverages a similarity measure that enables the structural comparison of senses across lexical resources, achieving state-of-the-art performance on the task of aligning WordNet to three different collaborative resources: Wikipedia, Wiktionary and OmegaWiki. |
Experiments | To enable a comparison with the state of the art, we followed Matuschek and Gurevych (2013) and performed an alignment of WordNet synsets (WN) to three different collaboratively-constructed resources: Wikipedia |
Experiments | As mentioned in Section 2.1.1, we build the WN graph by including all the synsets and semantic relations defined in WordNet (e.g., hypernymy and meronymy) and further populate the relation set by connecting a synset to all the other synsets that appear in its disambiguated gloss. |
Introduction | Notable examples are WordNet , Wikipedia and, more recently, collaboratively-curated resources such as OmegaWiki and Wiktionary (Hovy et al., 2013). |
Introduction | When a lexical resource can be viewed as a semantic graph, as with WordNet or Wikipedia, this limit can be overcome by means of alignment algorithms that exploit the network structure to determine the similarity of concept pairs. |
Introduction | We report state-of-the-art performance when aligning WordNet to Wikipedia, OmegaWiki and Wiktionary. |
Related Work | A good example is WordNet , which has been exploited as a semantic network in dozens of NLP tasks (Fellbaum, 1998). |
Resource Alignment | For instance, WordNet can be readily represented as an undirected graph G whose nodes are synsets and edges are modeled after the relations between synsets defined in WordNet (e. g., hypernymy, meronymy, etc. |
Resource Alignment | Any semantic network with a dense relational structure, providing good coverage of the words appearing in the definitions, is a suitable candidate for H. For this purpose we used the WordNet (Fellbaum, 1998) graph which was further enriched by connecting |
Resource Alignment | As an example, assume we are given two semantic signatures computed for two concepts in WordNet and Wiktionary. |
Abstract | We conduct a thorough evaluation of the proposed methodology both manually as well as through comparison with WordNet . |
Abstract | Remarkably, in 44% cases the birth of a novel sense is attested by WordNet, while in 46% cases and 43% cases split and join are respectively confirmed by WordNet . |
Evaluation framework | 6.2 Automated evaluation with WordNet |
Evaluation framework | We chose WordNet for automated evaluation because not only does it have a wide coverage of word senses but also it is being maintained and updated regularly to incorporate new senses. |
Evaluation framework | For our evaluation, we developed an aligner to align the word clusters obtained with WordNet senses. |
Introduction | Remarkably, comparison with the English WordNet indicates that in 44% cases, as identified by our algorithm, there has been a birth of a completely novel sense, in 46% cases a new sense has split off from an older sense and in 43% cases two or more older senses have merged in to form a new sense. |
Related work | A few approaches suggested by (Bond et al., 2009; Paakko' and Linden, 2012) attempt to augment WordNet synsets primarily using methods of annotation. |
Background and Related Work | Typically, word frequency distributions are estimated with respect to a sense-tagged corpus such as SemCor (Miller et al., 1993), a 220,000 word corpus tagged with WordNet (Fellbaum, 1998) senses. |
Background and Related Work | The distributional similarity scores of the nearest neighbours are associated with the respective target word senses using a WordNet similarity measure, such as those proposed by J iang and Conrath (1997) and Banerjee and Pedersen (2002). |
Introduction | (2004b) to remove low-frequency senses from WordNet , we focus on finding senses that are unattested in the corpus on the premise that, given accurate disambiguation, rare senses in a corpus contribute to correct interpretation. |
Macmillan Experiments | For the purposes of this research, the choice of Macmillan is significant in that it is a conventional dictionary with sense definitions and examples, but no linking between senses.11 In terms of the original research which gave rise to the sense-tagged dataset, Macmillan was chosen over WordNet for reasons including: (l) the well-documented difficulties of sense tagging with fine-grained WordNet senses (Palmer et al., 2004; Navigli et al., 2007); (2) the regular update cycle of Macmillan (meaning it contains many recently-emerged senses); and (3) the finding in a preliminary sense-tagging task that it better captured Twitter usages than WordNet (and also OntoNotes: Hovy et al. |
Macmillan Experiments | The average sense ambiguity of the 20 target nouns in Macmillan is 5.6 (but 12.3 in WordNet ). |
Macmillan Experiments | We first notice that, despite the coarser-grained senses of Macmillan as compared to WordNet , the upper bound WSD accuracy using Macmillan is comparable to that of the WordNet-based datasets over the balanced BNC, and quite a bit lower than that of the two domain corpora of Koeling et al. |
Methodology | the WordNet hierarchy). |
WordNet Experiments | For each domain, annotators were asked to sense-annotate a random selection of sentences for each of 40 target nouns, based on WordNet v1.7. |
WordNet Experiments | For each dataset, we use HDP to induce topics for each target lemma, compute the similarity between the topics and the WordNet senses (Equation (1)), and rank the senses based on the prevalence scores (Equation (2)). |
WordNet Experiments | It is important to bear in mind that MKWC in these experiments makes use of full-text parsing in calculating the distributional similarity thesaurus, and the WordNet graph structure in calculating the similarity between associated words and different senses. |
Abstract | Manually constructing a Wordnet is a difficult task, needing years of experts’ time. |
Abstract | As a first step to automatically construct full Wordnets, we propose approaches to generate Wordnet synsets for languages both resource-rich and resource-poor, using publicly available Wordnets , a machine translator and/or a single bilingual dictionary. |
Abstract | Our algorithms translate synsets of existing Wordnets to a target language T, then apply a ranking method on the translation candidates to find best translations in T. Our approaches are applicable to any language which has at least one existing bilingual dictionary translating from English to it. |
Introduction | Wordnets are intricate and substantive repositories of lexical knowledge and have become important resources for computational processing of natural languages and for information retrieval. |
Introduction | Good quality Wordnets are available only for a few "resource-rich" languages such as English and Japanese. |
Introduction | Published approaches to automatically build new Wordnets are manual or semiautomatic and can be used only for languages that already possess some lexical resources. |
Abstract | The key aspect of our method is that it is the first unified approach that assigns the polarity of both word- and sense-level connotations, exploiting the innate bipartite graph structure encoded in WordNet . |
Conclusion | We have introduced a novel formulation of lexicon induction operating over both words and senses, by exploiting the innate structure between the words and senses as encoded in WordNet . |
Evaluation 11: Human Evaluation on ConnotationWordNet | 7Because senses in WordNet can be tricky to understand, care should be taken in designing the task so that the Turkers will focus only on the corresponding sense of a word. |
Evaluation 11: Human Evaluation on ConnotationWordNet | Therefore, we provided the part of speech tag, the WordNet gloss of the selected sense, and a few examples as given in WordNet . |
Introduction | We introduce ConnotationWordNet, a connotation lexicon over the network of words in conjunction with senses, as defined in WordNet . |
Introduction | For example, consider “abound”, for which lexicographers of WordNet prescribe two different senses: |
Introduction | Especially if we look up the WordNet entry for “bristle”, there are noticeably more negatively connotative words involved in its gloss and examples. |
Network of Words and Senses | Another benefit of our approach is that for various WordNet relations (e.g., antonym relations), which are defined over synsets (not over words), we can add edges directly between corresponding synsets, rather than projecting (i.e., approximating) those relations over words. |
Comparative Evaluation | As regards recall, we note that in two cases (i.e., DBpedia returning page super-types from its upper taxonomy, YAGO linking categories to WordNet synsets) the generalizations are neither pages nor categories and that MENTA returns heterogeneous hypernyms as mixed sets of WordNet synsets, Wikipedia pages and categories. |
Comparative Evaluation | MENTA seems to be the closest resource to ours, however, we remark that the hypernyms output by MENTA are very heterogeneous: 48% of answers are represented by a WordNet synset, 37% by Wikipedia categories and 15% are Wikipedia pages. |
Introduction | However, unlike the case with smaller manually-curated resources such as WordNet (Fellbaum, 1998), in many large automatically-created resources the taxonomical information is either missing, mixed across resources, e.g., linking Wikipedia categories to WordNet synsets as in YAGO, or coarse-grained, as in DBpedia whose hypernyms link to a small upper taxonomy. |
Introduction | (2005) provide a general vector-based method which, however, is incapable of linking pages which do not have a WordNet counterpart. |
Introduction | Higher coverage is provided by de Melo and Weikum (2010) thanks to the use of a set of effective heuristics, however, the approach also draws on WordNet and sense frequency information. |
Related Work | However, these methods do not link terms to existing knowledge resources such as WordNet , whereas those that explicitly link do so by adding new leaves to the existing taxonomy instead of acquiring wide-coverage taxonomies from scratch (Pan-tel and Ravichandran, 2004; Snow et al., 2006). |
Related Work | Other approaches, such as YAGO (Suchanek et al., 2008; Hoffart et al., 2013), yield a taxonomical backbone by linking Wikipedia categories to WordNet . |
Related Work | However, the categories are linked to the first, i.e., most frequent, sense of the category head in WordNet , involving only leaf categories in the linking. |
Abstract | This paper presents experiments with WordNet semantic classes to improve dependency parsing. |
Experimental Framework | Base WordNet WordNet Clusters |
Experimental Framework | WordNet . |
Experimental Framework | (2011), based on WordNet 2.1. |
Introduction | Broadly speaking, we can classify the methods to incorporate semantic information into parsers in two: systems using static lexical semantic repositories, such as WordNet or similar ontologies (Agirre et al., 2008; Agirre et al., 2011; Fujita et al., 2010), and systems using dynamic semantic clusters automatically acquired from corpora (Koo et al., 2008; Suzuki et al., 2009). |
Introduction | 0 Does semantic information in WordNet help |
Introduction | 0 How does WordNet compare to automatically obtained information? |
Related work | Broadly speaking, we can classify the attempts to add external knowledge to a parser in two sets: using large semantic repositories such as WordNet and approaches that use information automatically acquired from corpora. |
Related work | The results showed a signi-cant improvement, giving the first results over both WordNet and the Penn Treebank (PTB) to show that semantics helps parsing. |
Related work | (201 1) successfully introduced WordNet classes in a dependency parser, obtaining improvements on the full PTB using gold POS tags, trying different combinations of semantic classes. |
Introduction | WordNet (Fellbaum, 2010) has been used in numerous natural language processing tasks such as word sense disambiguation and information extraction with considerable success. |
Introduction | Kurdish is a less-resourced language for which, among other resources, no wordnet has been built yet. |
KurdNet: State-of-the-Art | 1. highlighted the main challenges in building a wordnet for the Kurdish language (including its inherent diversity and morphological complexity), |
KurdNet: State-of-the-Art | 2. built the first prototype of KurdNet, the Kurdish WordNet (see a summary below), and |
KurdNet: State-of-the-Art | There are two well-known models for building wordnets for a language (Vossen, 1998): |
Methodology | mantic categories originating in WordNet . |
Methodology | 7Supersenses are called “lexicographer classes” in WordNet documentation (Fellbaum, 1998), http: / /worolnet . |
Methodology | English adjectives do not, as yet, have a similar high-level semantic partitioning in WordNet , thus we use a 13-class taxonomy of adjective supersenses constructed by Tsvetkov et al. |
Model and Feature Extraction | WordNet lacks coarse-grained semantic categories for adjectives. |
Model and Feature Extraction | For example, the top-level classes in GermaNet include: adj.feeling (e.g., willing, pleasant, cheerful); adj.sabstance (e.g., dry, ripe, creamy); adj.spatial (e.g., adjacent, gigantic).12 For each adjective type in WordNet , they produce a vector with a classifier posterior probabilities corresponding to degrees of membership of this word in one of the 13 semantic classes,13 similar to the feature vectors we build for nouns and verbs. |
Model and Feature Extraction | Consider an example related to projection of WordNet supersenses. |
Related Work | (2013) describe a Concrete Category Overlap algorithm, where co-occurrence statistics and Turney’s abstractness scores are used to determine WordNet supersenses that correspond to literal usage of a given adjective or verb. |
Related Work | To implement this idea, they extend MRC imageability scores to all dictionary words using links among WordNet supersenses (mostly hypernym and hyponym relations). |
Related Work | Because they heavily rely on WordNet and availability of imageability scores, their approach may not be applicable to low-resource languages. |
Abstract | The features make extensive use of WordNet . |
Assessment of Lexical Resources | Since the PDEP system enables exploration of features from WordNet , FrameNet, and VerbNet, we are able to make some assessment of these resources. |
Assessment of Lexical Resources | WordNet played a statistically significant role in the systems developed by Tratz (2011) and Srikumar and Roth (2013). |
Assessment of Lexical Resources | This includes the WordNet lexicographer’s file name (e.g., noun.time), synsets, and hypernyms. |
Class Analyses | We are examining the WordNet detour to FrameNet, as described in Burchardt et al. |
Introduction | Section 4 describes how we are able to investigate the relationship of WordNet , FrameNet, and VerbNet to this effort and how this examination of preposition behavior can be used in working with these resources. |
See http://clg.wlv.ac.uk/proiects/DVC | The feature extraction rules are (1) word class (we), (2) part of speech (pos), (3) lemma (1), (4) word (w), (5) WordNet lexical name (In), (6) WordNet synonyms (s), (7) WordNet hypernyms (h), (8) whether the word is capitalized (c), and (9) affixes (af). |
See http://clg.wlv.ac.uk/proiects/DVC | For features such as the WordNet lexical name, synonyms and hypernyms, the number of values may be much larger. |
Abstract | Frequently, such resources are constructed through automatic mergers of complementary resources, such as WordNet and Wikipedia. |
Introduction | Semantic knowledge bases such as WordNet (Fellbaum, 1998), YAGO (Suchanek et al., 2007), and BabelNet (Navigli and Ponzetto, 2010) provide ontological structure that enables a wide range of tasks, such as measuring semantic relatedness (Budanitsky and Hirst, 2006) and similarity (Pilehvar et al., 2013), paraphrasing (Kauchak and Barzilay, 2006), and word sense disambiguation (Navigli and Ponzetto, 2012; Moro et al., 2014). |
Introduction | extend WordNet using distributional or structural features to identify novel semantic connections between concepts. |
Introduction | The recent advent of large semistructured resources has enabled the creation of new semantic knowledge bases (Medelyan et al., 2009; Hovy et al., 2013) through automatically merging WordNet and Wikipedia (Suchanek et al., 2007; Navigli and Ponzetto, 2010; Nie-mann and Gurevych, 2011). |
Related Work | Rzeniewicz and Szymanski (2013) extend WordNet with commonsense knowledge using a 20 Questions-like game. |
Video Game with a Purpose Design | Knowledge base As the reference knowledge base, we chose BabelNet2 (Navigli and Ponzetto, 2010), a large-scale multilingual semantic ontology created by automatically merging WordNet with other collaboratively-constructed resources such as Wikipedia and OmegaWiki. |
Video Game with a Purpose Design | First, by connecting WordNet synsets to Wikipedia pages, most synsets are associated with a set of pictures; while often noisy, these pictures sometimes illustrate the target concept and are an ideal case for validation. |
Video Game with a Purpose Design | Second, BabelNet contains the semantic relations from both WordNet and hyperlinks in Wikipedia; these relations are again an ideal case of validation, as not all hyperlinks connect semantically-related pages in Wikipedia. |
Background | Some have established concept hierarchies based on manually-built semantic resources such as WordNet (Miller, 1995). |
Background | Such hierarchies have good structures and high accuracy, but their coverage is limited to fine-grained concepts (e.g., “Ranunculaceae” is not included in WordNet .). |
Background | (2008) link the categories in Wikipedia onto WordNet . |
Introduction | In the WordNet hierarchy, senses are organized according to the “isa” relations. |
Related Work | (2006) provides a global optimization scheme for extending WordNet , which is different from the above-mentioned pairwise relationships identification methods. |
Experiments | CCG parser, WordNet |
Experiments | hypernyms, WordNet |
Experiments | head word, parser SVM hypernyms, WordNet |
Automatic Alignments | We use WordNet to generate candidate lemmas, and we also use a fuzzy match of a concept, defined to be a word in the sentence that has the longest string prefix match with that concept’s label, if the match length is Z 4. |
Automatic Alignments | WordNet lemmas and fuzzy matches are only used if the rule explicitly uses them. |
Training | Strips off trailing ‘-[0-9]+’ from the concept (for example run—01 —> run), and matches any exact matching word or WordNet lemma. |
Introduction | If the node is a preterminal node, we capture its lexical semantic by adding features indicating its WordNet sense information. |
Introduction | Specifically, the first WordNet sense of the terminal word, and all this sense’s hyponym senses will be added as features. |
Introduction | For example, WordNet senses {New Y0rk#], city#], district#], |
Baselines | One is word co-occurrence (if word w and word wj occur in the same sentence or in the adjacent sentences, Sim(wi,wj) increases 1), and the other is WordNet (Miller, 1995) based similarity. |
Baselines | 3 Total weight of words in the focus candidate using the WordNet similarity. |
Baselines | 4 Max weight of words in the focus candidate using the WordNet similarity. |