BibSonomyburst/user/seandalai/compoundsBibSonomy RSS feed for /user/seandalai/compounds2012-02-16T18:13:20+01:00http://www.bibsonomy.org/bibtex/24dc663ec6e5b1847f20fce9c28fbe975/seandalaiseandalai2011-11-08T22:13:36+01:002011 compositionality compounds <span class="authorEditorList"><a href="/author/Reddy">Siva Reddy</a>, <a href="/author/McCarthy">Diana McCarthy</a>, and <a href="/author/Manandhar">Suresh Manandhar</a> </span><em>Proceedings of the 5th International Joint Conference on Natural Language Processing IJCNLP-11, </em><em>Chiang Mai, Thailand, </em>(<em>2011</em>)Tue Nov 08 22:13:36 CET 2011Chiang Mai, ThailandProceedings of the 5th International Joint Conference on Natural Language Processing (IJCNLP-11)An Empirical Study on Compositionality in Compound Nouns20112011 compositionality compounds A multiword is compositional if its meaning can be expressed in terms of the meaning of its constituents. In this paper, we collect and analyse the compositionality judgments for a range of compound nouns using Mechanical Turk. Unlike existing compositionality datasets, our dataset has judgments on the contribution of constituent words as well as judgments for the phrase as a whole. We use this dataset to study the relation between the judgments at constituent level to that for the whole phrase. We then evaluate two different types of distributional models for compositionality detection - constituent based models and composition function based models. Both the models show competitive performance though the composition function based models perform slightly better. In both types, additive models perform better than their multiplicative counterparts.http://www.bibsonomy.org/bibtex/255866e1811c3af5d8075a195c9a70cbc/seandalaiseandalai2011-10-08T04:19:44+02:002011 aphasia compounds psycholinguistics <span class="authorEditorList"><a href="/author/Eiesland">Eli Anne Eiesland</a>, and <a href="/author/Lind">Marianne Lind</a> </span><em>Clinical Linguistics and Phonetics</em> (<em>2011</em>)Sat Oct 08 04:19:44 CEST 2011Clinical Linguistics and PhoneticsCompound nouns in spoken language production by speakers with aphasia compared to neurologically healthy speakers: An exploratory study20112011 aphasia compounds psycholinguistics Compounds are words that are made up of at least two other words (lexemes), featuring lexical and syntactic characteristics and thus particularly interesting for the study of language processing. Most studies of compounds and language processing have been based on data from experimental single word production and comprehension tasks. To enhance the ecological validity of morphological processing research, data from other contexts, such as discourse production, need to be considered. This study investigates the production of nominal compounds in semi-spontaneous spoken texts by a group of speakers with fluent types of aphasia compared to a group of neurologically healthy speakers. The speakers with aphasia produce significantly fewer nominal compound types in their texts than the non-aphasic speakers, and the compounds they produce exhibit fewer different types of semantic relations than the compounds produced by the non-aphasic speakers. The results are discussed in relation to theories of language processing.http://www.bibsonomy.org/bibtex/27445cafc15337a81f6c9306b880cacb0/seandalaiseandalai2011-09-27T01:18:33+02:002011 compounds prosody <span class="authorEditorList"><a href="/author/Arndt-Lappe">Sabine Arndt-Lappe</a> </span><em>Journal of Linguistics</em> <em>47(3):549--585</em> (<em>2011</em>)Tue Sep 27 01:18:33 CEST 2011Journal of Linguistics3549--585Towards an exemplar-based model of stress in English noun-noun compounds4720112011 compounds prosody It is well known that stress assignment in English noun–noun compounds is non-uniform (compare e.g. left-prominent ópera glasses and right-prominent steel brídge), and recent corpus-based studies (e.g. Plag et al. 2007, 2008) have shown that categorical, rule-based approaches that make use of argument structure (e.g. Giegerich 2004) or semantics (e.g. Fudge 1984) are not able to account satisfactorily for the existing variability. Using data from the corpus studies by Plag and collegues, I argue in this paper that an exemplar-based approach is better-suited to accounting for stress assignment in English noun–noun compounds than a traditional, rule-based paradigm. Specifically, it is shown that two current implementations of exemplar-based algorithms, TiMBL (Daelemans et al. 2007) and AM::Parallel (Skousen & Stanford 2007), clearly outperform comparable rule models in terms of how well they predict stress assignment in the corpora. Furthermore, systematic testing reveals that the reasons for the differences between exemplar and rule models mainly lie in their ability to incorporate detailed, non-abstract information (specifically, constituent family information). The present study therefore adds to the growing evidence in favour of the importance of constituent family information in compounding (e.g. Gagné 2001, Krott, Schreuder & Baayen 2002).http://www.bibsonomy.org/bibtex/2730bf23c74c8965ec272dead674c0d2b/seandalaiseandalai2011-09-13T11:42:20+02:002011 acl compounds prosody <span class="authorEditorList"><a href="/author/Mishra">Taniya Mishra</a>, and <a href="/author/Bangalore">Srinivas Bangalore</a> </span><em>Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies ACL-11 Short Paper Session, </em><em>Portland, OR, </em>(<em>2011</em>)Tue Sep 13 11:42:20 CEST 2011Portland, ORProceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies (ACL-11) Short Paper SessionPredicting Relative Prominence in Noun-Noun Compounds.20112011 acl compounds prosody There are several theories regarding what influences prominence assignment in English noun-noun compounds. We have developed corpus-driven models for automatically predicting prominence assignment in noun-noun compounds using feature sets based on two such theories: the informativeness theory and the semantic composition theory. The evaluation of the prediction models indicate that though both of these theories are relevant, they account for different types of variability in prominence assignment.http://www.bibsonomy.org/bibtex/2c51b28f764c780a028fc4a740e078e02/seandalaiseandalai2011-09-13T11:39:31+02:002011 acl compounds splitting <span class="authorEditorList"><a href="/author/Macherey">Klaus Macherey</a>, <a href="/author/Dai">Andrew Dai</a>, <a href="/author/Talbot">David Talbot</a>, <a href="/author/Popat">Ashok Popat</a>, and <a href="/author/Och">Franz Och</a> </span><em>Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies ACL-11, </em><em>Portland, OR, </em>(<em>2011</em>)Tue Sep 13 11:39:31 CEST 2011Portland, ORProceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies (ACL-11)Language-independent compound splitting with morphological operations20112011 acl compounds splitting Translating compounds is an important problem in machine translation. Since many compounds have not been observed during training, they pose a challenge for translation systems. Previous decompounding methods have often been restricted to a small set of languages as they cannot deal with more complex compound forming processes. We present a novel and unsupervised method to learn the compound parts and morphological operations needed to split compounds into their compound parts. The method uses a bilingual corpus to learn the morphological operations required to split a compound into its parts. Furthermore, monolingual corpora are used to learn and filter the set of compound part candidates. We evaluate our method within a machine translation task and show significant improvements for various languages to show the versatility of the approach.http://www.bibsonomy.org/bibtex/298eb32ac8cbdfed15e356ec39c543293/seandalaiseandalai2011-09-13T11:36:14+02:002011 compounds japanese splitting <span class="authorEditorList"><a href="/author/Kaji">Nobuhiro Kaji</a>, and <a href="/author/Kitsuregawa">Masaru Kitsuregawa</a> </span><em>Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing EMNLP-11, </em><em>Edinburgh, UK, </em>(<em>2011</em>)Tue Sep 13 11:36:14 CEST 2011Edinburgh, UKProceedings of the 2011 Conference on Empirical Methods in Natural Language Processing (EMNLP-11)Splitting Noun Compounds via Monolingual and Bilingual Paraphrasing: A Study on Japanese Katakana Words20112011 compounds japanese splitting Word boundaries within noun compounds are not marked by white spaces in a number of languages, unlike in English, and it is beneficial for various NLP applications to split such noun compounds. In the case of Japanese, noun compounds made up of katakana words (i.e., transliterated foreign words) are particularly difficult to split, because katakana words are highly productive and are often out-of-vocabulary. To overcome this difficulty, we propose using monolingual and bilingual paraphrases of katakana noun compounds for identifying word boundaries. Experiments demonstrated that splitting accuracy is substantially improved by extracting such paraphrases from unlabeled textual data, the Web in our case, and then using that information for constructing splitting models.http://www.bibsonomy.org/bibtex/20e395633b17c901a64a87fd5bfb7e963/seandalaiseandalai2011-09-13T11:33:49+02:002011 compounds emnlp <span class="authorEditorList"><a href="/author/Nakov">Preslav Nakov</a>, and <a href="/author/Kim">Su Nam Kim</a> </span><em>Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing EMNLP-11, </em><em>Edinburgh, UK, </em>(<em>2011</em>)Tue Sep 13 11:33:49 CEST 2011Edinburgh, UKProceedings of the 2011 Conference on Empirical Methods in Natural Language Processing (EMNLP-11)Large-Scale Noun Compound Interpretation Using Bootstrapping and the Web as a Corpus20112011 compounds emnlp Responding to the need for semantic lexical resources in natural language processing applications, we examine methods to acquire noun compounds (NCs), e.g., orange juice, together with suitable fine-grained semantic interpretations, e.g., squeezed from, which are directly usable as paraphrases. We employ bootstrapping and web statistics, and utilize the relationship between NCs and paraphrasing patterns to jointly extract NCs and such patterns in multiple alternating iterations. In evaluation, we found that having one com- pound noun fixed yields both a higher number of semantically interpreted NCs and improved accuracy due to stronger semantic restrictions.http://www.bibsonomy.org/bibtex/28da0a9ed185bf658a8263458a06b6631/seandalaiseandalai2011-09-13T11:29:53+02:002011 compounds <span class="authorEditorList"><a href="/author/Wijaya">Derry Tanti Wijaya</a>, and <a href="/author/Gianfortoni">Philip Gianfortoni</a> </span><em>Proceedings of the 1st International Workshop on Search and Mining Entity-Relation Data SMER-11, </em><em>Glasgow, UK, </em>(<em>2011</em>)Tue Sep 13 11:29:53 CEST 2011Glasgow, UKProceedings of the 1st International Workshop on Search and Mining Entity-Relation Data (SMER-11)``Nut Case: What does It Mean?'': Understanding Semantic Relationship between Nouns in Noun Compounds through Paraphrasing and Ranking the Paraphrases20112011 compounds A noun compound (NC) is a sequence of two or more nouns (entities) acting as a single noun entity that encodes implicit semantic relation between its noun constituents. Given an NC such as `headache pills' and possible paraphrases such as: `pills that induce headache' or `pills that relieve head-ache' can we learn to choose which verb: `induce' or `relieve' that best describes the semantic relation encoded in `headache pills'? In this paper, we describe our approaches to rank human-proposed paraphrasing verbs of NCs. Our contribution is a novel approach that uses two- step process of clustering similar NCs and then labeling the best paraphrasing verb as the most prototypical verb in the cluster. The approach performs the best with an average Spearman’s rank correlation of 0.55. This approach, while being computationally simpler, gives a better ranking than the current state of the art. The result shows the potential of our approach for finding implicit relations between entities especially when the relations are not explicit in the context in which the entities appear, rather they are implicit in the relationship between its constituents.http://www.bibsonomy.org/bibtex/27ca1e1472d4e47b9f2d3073e20cd474b/seandalaiseandalai2011-08-26T13:31:09+02:002011 compounds psycholinguistics <span class="authorEditorList"><a href="/author/Ji">Hongbo Ji</a>, <a href="/author/Gagné">Christina L. Gagné</a>, and <a href="/author/Spalding">Thomas L. Spalding</a> </span><em>Journal of Memory and Language</em> <em>65(4):406-430</em> (<em>2011</em>)Fri Aug 26 13:31:09 CEST 2011Journal of Memory and Language4406-430Benefits and costs of lexical decomposition and semantic integration during the processing of transparent and opaque English compounds6520112011 compounds psycholinguistics Six lexical decision experiments were conducted to examine the influence of complex structure on the processing speed of English compounds. All experiments revealed that semantically transparent compounds (e.g., rosebud) were processed more quickly than matched monomorphemic words (e.g., giraffe). Opaque compounds (e.g., hogwash) were also processed more quickly than monomorphemic words. However, when the experimental materials and/or procedure encouraged decomposition/integration, this advantage disappeared. This research suggests that morphological decomposition initiated by the existence of complex structure results in the availability of both the lexical and semantic representations of compound constituents, regardless of whether the compounds are transparent or opaque, and that meaning composition is attempted. This meaning composition further speeds up transparent compound processing beyond lexical facilitation but slows down opaque compound processing because the computed meaning for opaque compounds conflicts with the retrieved meaning.http://www.bibsonomy.org/bibtex/29eb50d266311a3ddebcbe556ebc6d82c/seandalaiseandalai2011-06-30T12:58:43+02:002011 compounds <span class="authorEditorList"><a href="/author/Schlücker">Barbara Schlücker</a>, and <a href="/author/Plag">Ingo Plag</a> </span><em>Lingua</em> <em>121(9):1539--1551</em> (<em>2011</em>)Thu Jun 30 12:58:43 CEST 2011Lingua91539--1551Compound or phrase? Analogy in naming12120112011 compounds In German (and other Germanic languages) both phrases and compounds are used as names for concepts (e.g. Rotwein [`]red wine', grüner Daumen [`]green thumb/green fingers'). This study examines such kind-referring German A+N compounds and phrases. Whereas it is a widely accepted fact that compounds are inherently suitable for kind reference (or "naming"), due to their status as word formation entities, phrases used for kind reference are regarded as isolated, idiosyncratic cases. This paper presents the results of a production experiment which show that both A+N phrases and A+N compounds should be regarded as a productive means of coining names. The choice between the two constructions is largely dependent on the availability of similar constructions in the mental lexicon of the speakers. The larger the number of lexicalized compounds with the same adjective or noun, the higher the probability of the subjects choosing a compound. The larger the number of lexicalized phrases with the same adjective or noun, the higher the probability of the subjects choosing a phrase. Thus, the probability of using a compound to name a new concept positively correlates with the number of available other compounds (types) that feature one or both of the elements to be combined. This effect is stronger for adjectives than for nouns. These results cannot be accounted for in a rule-based approach to grammar and lexicon. Instead they support a constructionist approach in which differences in productivity directly relate to the (number of) existing instantiations of the respective constructions in the mental lexicon.http://www.bibsonomy.org/bibtex/264c0cb6a24d298485811573c3a306867/seandalaiseandalai2011-06-20T23:12:12+02:002011 compounds metonymy <span class="authorEditorList"><a href="/author/Benczes">Réka Benczes</a> </span><em>Defining Metonymy in Cognitive Linguistics: Towards a consensus view, </em><em>John Benjamins, </em><em>Amsterdam, </em>(<em>2011</em>)Mon Jun 20 23:12:12 CEST 2011AmsterdamDefining Metonymy in Cognitive Linguistics: Towards a consensus viewPutting the notion of "domain" back into metonymy: Evidence from compounds20112011 compounds metonymy This chapter explores the role that domains play in conceptual metonymy by examining the semantics of metonymical (and metaphorical) noun–noun compounds. It argues that the concept of "domain" is a necessary feature of any definition of metonymy (irrespective of the fact whether "domain" is referred to as a domain matrix, frame, or icm). The analysis of noun–noun compounds, such as couch potato and scarlet-collar worker, imply that the domains are best understood as networks of semantic associations, with links to further semantic domains or even other grammatical constructions. Therefore, the chapter proposes that metonymy operates within a domain network, where the domains form web-like semantic links of associations.http://www.bibsonomy.org/bibtex/2242ea47d4eec4a80ddbea2080b85567a/seandalaiseandalai2011-06-12T01:24:53+02:002011 compounds psycholinguistics <span class="authorEditorList"><a href="/author/Gagné">Christina L. Gagné</a>, and <a href="/author/Spalding">Thomas L. Spalding</a> </span><em>Journal of Memory and Language</em> <em>65(2):176--192</em> (<em>2011</em>)Sun Jun 12 01:24:53 CEST 2011Journal of Memory and Language2176--192Inferential processing and meta-knowledge as the bases for property inclusion in combined concepts6520112011 compounds psycholinguistics Past research has found that the judged likelihood of properties of modified nouns (baby ducks have webbed feet) is reduced relative to unmodified nouns (ducks have webbed feet). Experiments 1-3 replicate the modification effect and demonstrate that this effect is obtained when participants make dichotomous decisions about the truth of such statements. In addition, measures of processing time indicate that properties are not immediately inherited during the composition process, but rather must be inferred. Experiments 2-3 included statements containing content-free modifiers (chonk ducks have webbed feet) to examine the extent to which the modification effect is influenced by the content of the modifier and knowledge about the combined concepts. Taken together, these results argue in favor of an inferential process that operates at the level of logical forms or structures, which are content-free, as well as operating on the content of the head noun category. In this framework, properties are inferred after a structural interpretation has been derived.ScienceDirect - Journal of Memory and Language : Inferential processing and meta-knowledge as the bases for property inclusion in combined conceptshttp://www.bibsonomy.org/bibtex/2728f8e1570f808f18ca0ac999c0d11f0/seandalaiseandalai2011-04-05T03:33:20+02:002010 acl bracketing compounds <span class="authorEditorList"><a href="/author/Bergsma">Shane Bergsma</a>, <a href="/author/Pitler">Emily Pitler</a>, and <a href="/author/Lin">Dekang Lin</a> </span><em>Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics ACL-10, </em>(<em>2010</em>)Tue Apr 05 03:33:20 CEST 2011Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics (ACL-10)Creating Robust Supervised Classifiers via Web-Scale N-gram Data20102010 acl bracketing compounds In this paper, we systematically assess the value of using web-scale N-gram data in state-of-the-art supervised NLP classifiers. We compare classifiers that include or exclude features for the counts of various N-grams, where the counts are obtained from a web-scale auxiliary corpus. We show that including N-gram count features can advance the state-of-the-art accuracy on standard data sets for adjective ordering, spelling correction, noun compound bracketing, and verb part-of-speech disambiguation. More importantly, when operating on new domains, or when labeled training data is not plentiful, we show that using web-scale N-gram features is essential for achieving robust performance.http://www.bibsonomy.org/bibtex/25ac9b31fe079744febc290104e56ada8/seandalaiseandalai2011-02-22T01:34:48+01:002011 compounds psycholinguistics <span class="authorEditorList"><a href="/author/Wang">Min Wang</a>, <a href="/author/Lin">Candise Y. Lin</a>, and <a href="/author/Gao">Wei Gao</a> </span><em>Writing Systems Research</em> <em>2(2):117-137</em> (<em>2011</em>)Tue Feb 22 01:34:48 CET 2011Writing Systems Research2117-137Bilingual compound processing: The effects of constituent frequency and semantic transparency220112011 compounds psycholinguistics Two lexical decision experiments were designed to address the effects of frequency and semantic transparency of the constituent morphemes in bilingual compound processing. In Experiment 1, the frequency of the second constituent morphemes and the lexicality of the translated compounds in the non-target language were manipulated. A significant interaction in RT data between the constituent frequency and the lexicality of the non-target language was revealed: the lexicality effect of the non-target language was stronger for compounds with high-frequency second constituents compared to those with low-frequency ones. In Experiment 2, the semantic transparency of the constituents of the target language, the lexicality of the non-target language, and the second language (L2) proficiency of the participants were manipulated. A significant three-way interaction was found: for the high-proficient group, there was a lexicality effect for opaque words but not for transparent words. For the low-proficient group, no interaction was found between semantic transparency and the lexicality of the non-target language. Taken together, these findings provided evidence for compound decomposition, cross-language activation in bilingual mental lexicon, and for the mediator role of L2 proficiency. http://www.bibsonomy.org/bibtex/2e7aef3ea334b904974859cb80215dfee/seandalaiseandalai2011-02-18T23:51:47+01:002010 blending cogling compounds <span class="authorEditorList"><a href="/author/Benczes">Réka Benczes</a> </span><em>Windows to the Mind: Metaphor, Metonymy and Conceptual Blending, </em><em>De Gruyter, </em><em>Berlin, </em>(<em>2010</em>)Fri Feb 18 23:51:47 CET 2011BerlinWindows to the Mind: Metaphor, Metonymy and Conceptual BlendingBlending and creativity in metaphorical compounds: A diachronic investigation20102010 blending cogling compounds http://www.bibsonomy.org/bibtex/29b4ada794aa646898dc1a75616a0f234/seandalaiseandalai2011-02-18T23:49:03+01:002010 blending cogling compounds <span class="authorEditorList"><a href="/author/Schmid">Hans-Jörg Schmid</a> </span><em>Windows to the Mind: Metaphor, Metonymy and Conceptual Blending, </em><em>De Gruyter, </em><em>Berlin, </em>(<em>2010</em>)Fri Feb 18 23:49:03 CET 2011BerlinWindows to the Mind: Metaphor, Metonymy and Conceptual BlendingConceptual blending, relevance and novel N+N-compounds20102010 blending cogling compounds http://www.bibsonomy.org/bibtex/280ebe159ef0c5cc03472b4fe2d9a50b1/seandalaiseandalai2010-11-20T15:26:02+01:002010 compounds <span class="authorEditorList"><a href="/author/Nulty">Paul Nulty</a>, and <a href="/author/Costello">Fintan Costello</a> </span><em>Artificial Intelligence and Cognitive Science, </em>(<em>2010</em>)Sat Nov 20 15:26:02 CET 2010Artificial Intelligence and Cognitive ScienceA Comparison of Word Similarity Measures for Noun Compound Disambiguation20102010 compounds Noun compounds occur frequently in many languages, and the problem of semantic disambiguation of these phrases has many potential applications in natural language processing and other areas. One very common approach to this problem is to define a set of semantic relations which capture the interaction between the modifier and the head noun, and then attempt to assign one of these semantic relations to each compound. For example, the compound phrase flu virus could be assigned the semantic relation causal (the virus causes the flu); the relation for desert wind could be location (the wind is located in the desert). In this paper we investigate methods for learning the correct semantic relation for a given noun compound by comparing the new compound to a training set of hand-tagged instances, using the similarity of the words in each compound. The main contribution of this paper is to directly compare distributional and knowledge-based word similarity measures for this task, using various datasets and corpora. We find that the knowledge based system provides a much better performance when adequate training data is available.http://www.bibsonomy.org/bibtex/293fac5c898de3f15200b0bb0643f43f6/seandalaiseandalai2010-11-15T19:27:53+01:002011 compounds psycholinguistics <span class="authorEditorList"><a href="/author/Ramscar">Michael Ramscar</a>, and <a href="/author/Dye">Melody Dye</a> </span><em>Cognitive Psychology</em> <em>62(1):1--40</em> (<em>2011</em>)Mon Nov 15 19:27:53 CET 2010Cognitive Psychology11--40Learning language from the input: Why innate constraints can't explain noun compounding6220112011 compounds psycholinguistics Do the production and interpretation of patterns of plural forms in noun-noun compounds reveal the workings of innate constraints that govern morphological processing? The results of previous studies on compounding have been taken to support a number of important theoretical claims: first, that there are fundamental differences in the way that children and adults learn and process regular and irregular plurals, second, that these differences reflect formal constraints that govern the way the way regular and irregular plurals are processed in language, and third, that these constraints are unlikely to be the product of learning. In a series of seven experiments, we critically assess the evidence that is cited in support of these arguments. The results of our experiments provide little support for the idea that substantively different factors govern the patterns of acquisition, production and interpretation patterns of regular and irregular plural forms in compounds. Once frequency differences between regular and irregular plurals are accounted for, we find no evidence of any qualitative difference in the patterns of interpretation and production of regular and irregular plural nouns in compounds, in either adults or children. Accordingly, we suggest that the pattern of acquisition of both regular and irregular plurals in compounds is consistent with a simple account, in which children learn the conventions that govern plural compounding using evidence that is readily available in the distribution patterns of adult speech.http://www.bibsonomy.org/bibtex/2b8986a0ff6cb0db130b9841249af85c1/seandalaiseandalai2010-08-03T18:52:02+02:002010 compounds <span class="authorEditorList"><a href="/author/Maguire">Phil Maguire</a>, <a href="/author/Wisniewski">Edward J. Wisniewski</a>, and <a href="/author/Storms">Gert Storms</a> </span><em>Corpus Linguistics and Linguistic Theory</em> <em>6(1):49--73</em> (<em>2010</em>)Tue Aug 03 18:52:02 CEST 2010Corpus Linguistics and Linguistic Theory149--73A corpus study of semantic patterns in compounding620102010 compounds Studies of modifier-noun compounds have indicated that they tend to follow regular semantic patterns (e.g., Downing, Language 53: 810–842, 1977; Warren, Acta Universitatis Gothoburgensis. Gothenburg Studies in English Goteborg 41: 1–266, 1978). The results of several psycholinguistic studies have supported the hypothesis that people rely on statistical knowledge about how nouns tend to be used in combination in order to facilitate the interpretation of novel compounds (e.g., Gagné & Shoben, Journal of Experimental Psychology: Learning, Memory and Cognition 23: 71–87, 1997; Maguire, Maguire & Cater, Journal of Experimental Psychology: Learning, Memory, and Cognition 36: 288–297, 2010; Storms & Wisniewski, Memory and Cognition 33: 852–861, 2005). We conducted a series of corpus analyses in order to establish the salience and reliability of semantic patterns in English compounds. These analyses demonstrated that similar concepts tend to appear in combination with similar sets of nouns. In addition, categorizing combinations according to the semantic category of the modifier and head revealed consistent regularities in productivity reflecting the likelihood of plausible relationships. These findings support the idea that statistical knowledge about semantic patterns in compounding can be used to facilitate the interpretation of novel compounds. The implications for existing theories and models of conceptual combination are discussed.http://www.bibsonomy.org/bibtex/215bb3768933119f8e847aef194604303/seandalaiseandalai2010-08-03T18:50:48+02:002010 acl compounds <span class="authorEditorList"><a href="/author/Tratz">Stephen Tratz</a>, and <a href="/author/Hovy">Eduard Hovy</a> </span><em>Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics ACL-10, </em><em>Uppsala, Sweden, </em>(<em>2010</em>)Tue Aug 03 18:50:48 CEST 2010Uppsala, SwedenProceedings of the 48th Annual Meeting of the Association for Computational Linguistics (ACL-10)A Taxonomy, Dataset, and Classifier for Automatic Noun Compound Interpretation20102010 acl compounds The automatic interpretation of noun-noun compounds is an important subproblem within many natural language processing applications and is an area of increasing interest. The problem is difficult, with disagreement regarding the number and nature of the relations, low inter-annotator agreement, and limited annotated data. In this paper, we present a novel taxonomy of relations that integrates previous relations, the largest publicly-available annotated dataset, and a supervised classification method for automatic noun compound interpretation.