DOCSLIB.ORG

Detecting the Countability of English Compound Nouns Using Web-Based Models

Total Page：16

File Type：pdf, Size：1020Kb

Download full-text PDF Read full-text
Detecting the Countability of English Compound Nouns Using Web-Based Models Detecting the Countability of English Compound Nouns Using Web-based Models Jing Peng Kenji Araki Language Media Laboratory Language Media Laboratory Hokkaido University Hokkaido University Kita-14, Nishi-9, Kita-ku, Kita-14, Nishi-9, Kita-ku, Sapporo, JAPAN Sapporo, JAPAN [email protected] [email protected] Baldwin and Bond, 2003). However, all the pro- Abstract posed approaches focused on learning the countability of individual nouns. In this paper, we proposed an approach A compound noun is a noun that is made up for detecting the countability of English of two or more words. Most compound nouns in compound nouns treating the web as English are formed by nouns modified by other a large corpus of words. We classified nouns or adjectives. In this paper, we concen- compound nouns into three classes: trate solely on compound nouns made up of only countable, uncountable, plural only. two words, as they account for the vast majority Our detecting algorithm is based on of compound nouns. There are three forms of simple, viable n-gram models, whose compound words: the closed form, in which the parameters can be obtained using the words are melded together, such as “songwriter”, WWW search engine Google. The de- “softball”, “scoreboard”; the hyphenated form, tecting thresholds are optimized on the such as “daughter-in-law”, “master-at-arms”; small training set. Finally we and the open form, such as “post office”, “real experimentally showed that our estate”, “middle class”. algorithm based on these simple Compound words create special problems models could perform the promising when we need to know their countability. Ac- results with a precision of 89.2% on the cording to “Guide to English Grammar and total test set. Writing”, the base element within the compound noun will generally function as a regular noun 1 Introduction for the countability, such as “Bedrooms”. How- ever this rule is highly irregular. Some uncount- In English, a noun can be countable or uncount- able nouns occur in their plural forms within able. Countable nouns can be "counted", they compound nouns, such as “mineral waters” (wa- have a singular and plural form. For example: an ter is usually considered as uncountable noun). apple, two apples, three apples. Uncountable The countability of some words changes when nouns cannot be counted. This means they have occur in different compound nouns. “Rag” is only a singular form, such as water, rice, wine. countable noun, while “kentish rag” is uncount- Countability is the semantic property that de- able; “glad rags” is plural only. “Wages” is plu- termines whether a noun can occur in singular ral only, but “absolute wage” and “standard and plural forms. We can obtain the information wage” are countable. So it is obvious that de- about countability of individual nouns easily termining countability of a compound noun from grammar books or dictionaries. Several should take all its elements into account, not researchers have explored automatically learn- consider solely on the base word. ing the countability of English nouns (Bond and The number of compound nouns is so large Vatikiotis-Bateson, 2002; Schwartz, 2002; that it is impossible to collect all of them in one 103 dictionary, which also need to be updated fre- only distinguish between countable and un- quently, for newcoined words are being created countable for individual nouns. The best model continuously, and most of them are compound is the determiner-noun model, which achieves nouns, such as “leisure sickness”, “Green fam- 88.62% on countable and 91.53% on uncount- ine”. able nouns. Knowledge of countability of compound In section 2 of the paper, we describe The nouns is very important in English text genera- main approach used in the paper. The prepara- tion. The research is motivated by our project: tion of the training and test data is introduced in post-edit translation candidates in machine section 3. The details of the experiments and translation. In Baldwin and Bond (2003), they results are presented in section 4. Finally, in sec- also mentioned that many languages, such as tion 5 we list our conclusions. Chinese and Japanese, do not mark countability, so how to determine the appropriate form of 2 Our approach translation candidates is depend on the knowl- edge of countability. For example, the correct We classified compound nouns into three 1 translation for “发育性痛 ” is “growing pains”, classes, countable, uncountable and plural only. not “growing pain”. In Baldwin and Bond (2003), they classified In this paper, we learn the countability of individual nouns into four possible classes. Be- English compound nouns using WWW as a sides the classes mentioned above, they also large corpus. For many compound nouns, espe- considered bipartite nouns. These words can cially the relatively new words, such as genetic only be plural when they head a noun phrase pollution, have not yet reached any dictionaries. (trousers), but singular when used as a modifier we believe that using the web-scale data can be (trouser leg). We did not take this class into ac- a viable alternative to avoid the sparseness prob- count in the paper, for the bipartite words is lem from smaller corpora. We classified com- very few in compound nouns. pound nouns into three classes: countable (eg., bedroom), uncountable (eg,. cash money), plural C-noun only (eg,. crocodile tears). To detect which class a compound noun is, we proposed some simple, viable n-gram models, such as freq(N) (the fre- F(Ns)>>F(N) Y quency of the singular form of the noun) whose plural only parameters’ values (web hits of literal queries) N can be obtained with the help of WWW search Y engine Google. The detecting thresholds (a noun F(N)>>F(Ns) uncountablity whose value of parameter is above the threshold N is considered as plural only) are estimated on the small countability-tagged training set. Finally countablity we evaluated our detecting approach on a test set and showed that our algorithm based on the simple models performed the promising results. Figure 1. Detecting processing flow Querying in WWW adds noise to the data, For plural only compound noun, we assume we certainly lose some precision compared to that the frequency of the word occurrence in the supervised statistical models, but we assume that plural form is much larger than that in the singu- the size of the WWW will compensate the rough lar form, while for the uncountable noun, the queries. Keller and Lapata (2003) also showed frequency in the singular form is much larger the evidence of the reliability of the web counts than that in the plural form. The main processing for natural language processing. In (Lapata and flow is shown in Figure 1. In the figure, “C- Keller, 2005), they also investigated the count- noun” and “Ns” mean compound noun and the ability leaning task for nouns. However they plural form of the word respectively. “F(Ns)>>F(N)” means that the frequency of the 1 “发育性痛”(fa yu xing tong) which is Chinese compound plural form of the noun is much larger than that noun means “growing pains”. of the singular form. 104 Our approach for detecting countability is ralize the last word. Eg,. grown-ups, based on some simple unsupervised models. stand-bys. f() Ns Although the rules cannot adapt for each ≥ θ (1) f() N compound noun, in our experimental data, all the countable compound nouns follow the rules. In (1), we use the frequency of a word in the We are sure that the rules are viable for most plural form against that in the singular form. θ countable compound nouns. is the detecting threshold above which the word Although we used Google as our search en- can be considered as a plural only. gine, we did not use Google Web API service f(,) much N ≥ θ (2) for programme realization, for Google limits to f(,) many Ns 1000 automated queries per day. As we just In (2), we use the frequency of a word in the need web hits returned for each search query, we singular form co-occurring with the determiner extracted the numbers of hits from the web “much” against the frequency of the word in the pages found directly. plural form with many, if above θ , the word can be considered as uncountable word. (2) is used 3 Experimental Data to distinguish between countable and uncount- The main experimental data is from Webster’s able compound nouns. New International Dictionary (Second Edition). f(,) Ns are ≥θ (3) The list of compound words of the dictionary is f(,) N is available in the Internet2. We selected the com- The model 3 that compares the frequencies pound words randomly from the list and keep of noun-be pairs (eg,. f(“account books are”), the nouns, for the word list also mixes com- f(“account book is”) is used to distinguish plural pound verbs and adjectives with nouns together. only and countable compound nouns. We repeated the process several times until got With the help of WWW search engine our experimental data. We collected 3000 words Google, the frequencies (web hits) in the models for the training which is prepared for optimizing can be obtained using quoted n-gram queries the detecting thresholds, and 500 words for the (“soft surroundings”). Although in Keller and test set which is used to evaluate our approach. Lapata (2002), they experimentally showed that In the sets we added 180 newcoined compound web-based approach can overcome data sparse- nouns (150 for training; 30 for test). These rela- ness for bigrams, but the problem still exists in tively new words that were created over the past seven years have not yet reached any dictionari- our experiments.
Load more

Recommended publications
  • This Chapter Provides a Historical Framework For
    Chapter One Introductions 1.0 Background: This chapter provides a historical framework for the study specifically it will provide description of the context of the study and gives short account of history of English language in Sudan. It is also provide a description of the study problem and formulates the question and hypotheses of the study. The significance of the study was shown. The scope and limitation of the study. Finally, the study unfolds the methodology to be adopted for conducting the empirical part of study. 1.1 Context of the Study problem: During the British colonial period of Sudan (1898- 1956). English language was the official language of the state. It was the medium of instruction in the educational institution during that period. It is worth mentioning that most of teachers at that time were native speakers of English and that allowed a wide exposure of English language for Sudanese students. Late after Sudan gained its independence in 1956 Arabic language began gradually to replace English as medium of instruction. Consequently, English language comes to be taught as a foreign language. 1 The current status of this language in the context of Sudan shows that it is declining and losing its significance in the education environment in this country because the purposes of learning this language have been changed. Upon considering its characteristics, English is a language which is rich in what are calls phrasal verbs are the most frequently used types of figurative language in discourse. For Sudanese secondary schools students these guises of language (i.e. phrasal verbs) are difficult to deal with because they are not relevant of the culture of the target language.
    [Show full text]
  • Compound Word Formation.Pdf
    Snyder, William (in press) Compound word formation. In Jeffrey Lidz, William Snyder, and Joseph Pater (eds.) The Oxford Handbook of Developmental Linguistics . Oxford: Oxford University Press. CHAPTER 6 Compound Word Formation William Snyder Languages differ in the mechanisms they provide for combining existing words into new, “compound” words. This chapter will focus on two major types of compound: synthetic -ER compounds, like English dishwasher (for either a human or a machine that washes dishes), where “-ER” stands for the crosslinguistic counterparts to agentive and instrumental -er in English; and endocentric bare-stem compounds, like English flower book , which could refer to a book about flowers, a book used to store pressed flowers, or many other types of book, as long there is a salient connection to flowers. With both types of compounding we find systematic cross- linguistic variation, and a literature that addresses some of the resulting questions for child language acquisition. In addition to these two varieties of compounding, a few others will be mentioned that look like promising areas for coordinated research on cross-linguistic variation and language acquisition. 6.1 Compounding—A Selective Review 6.1.1 Terminology The first step will be defining some key terms. An unfortunate aspect of the linguistic literature on morphology is a remarkable lack of consistency in what the “basic” terms are taken to mean. Strictly speaking one should begin with the very term “word,” but as Spencer (1991: 453) puts it, “One of the key unresolved questions in morphology is, ‘What is a word?’.” Setting this grander question to one side, a word will be called a “compound” if it is composed of two or more other words, and has approximately the same privileges of occurrence within a sentence as do other word-level members of its syntactic category (N, V, A, or P).
    [Show full text]
  • Syntactic-Words.Pdf
    Yearbook ofmorphology 3 (1990),201-216 Syntactic words and n*"1orphological words, simple and composite Arnold M. Zwicky 1. SYNTAGMATIC UNITS AND PARADIGMATIC UNITS What is the relationship between the simple or elementary objects of grammar, word- like things, and its composite or complex objects, phrase-like things? I focus here on a small piece of this gargantuan topic, having to do specifically with the elementary objects of morphosyntax, rather than with the grammar as a whole: ‘syntactic words’, the syntagmatic units I will call Ws; and ‘morphological words’, the paradigmatic units I will call moremes. The distinction at issue is a familiar one - it is made clearly, though not with this terminology, in careful discussions of the notion of word, such as those in Lyons (1968: sec. 5.4) and Matthews (1974) - but for some reason generative grammarians have for the most part failed to take the distinction seriously, preferring instead to use references to ‘X°’ units as if the small objects of syntax and the large objects of morphology have the same status, in fact, as if they coincided with one another. But they are objects ofquite different character - the fonner are expression tokens, the latter are expression types -and the question of whether they are in some sense coincident with one another is an empirical question, to be decided by considering a wide range of problematic data, not via a terminological or notational stipulation. Indeed, familiar data suggest quite strongly that coincidence is merely the default relationship between
    [Show full text]
  • Compositionality in English Deverbal Compounds
    Chapter 3 Compositionality in English deverbal compounds: The role of the head Gianina Iordăchioaia University of Stuttgart Lonneke van der Plas University of Malta Glorianna Jagfeld Lancaster University This paper is concerned with the compositionality of deverbal compounds such as budget assessment in English. We present an interdisciplinary study on how the morphosyntactic properties of the deverbal noun head (e.g., assessment) can pre- dict the interpretation of the compound, as mediated by the syntactic-semantic relationship between the non-head (e.g., budget) and the head. We start with Grim- shaw’s (1990) observation that deverbal nouns are ambiguous between composi- tionally interpreted argument structure nominals, which inherit verbal structure and realize arguments (e.g., the assessment of the budget by the government), and more lexicalized result nominals, which preserve no verbal properties or arguments (e.g., The assessment is on the table.). Our hypothesis is that deverbal compounds with argument structure nominal heads are fully compositional and, in our system, more easily predictable than those headed by result nominals, since their composi- tional make-up triggers an (unambiguous) object interpretation of the non-heads. Linguistic evidence gathered from corpora and human annotations, and evaluated with machine learning techniques supports this hypothesis. At the same time, it raises interesting discussion points on how different properties of the head con- tribute to the interpretation of the deverbal compound. Gianina Iordăchioaia, Lonneke van der Plas & Glorianna Jagfeld. 2020. Compositionality in English deverbal compounds: The role of the head. In Sabine Schulte im Walde & Eva Smolka (eds.), The role of constituents in multiword expressions: An interdisciplinary, cross-lingual perspec- tive, 61–106.
    [Show full text]
  • Using the Web As an Implicit Training Set: Application to Noun Compound
    Using the Web as an Implicit Training Set: Application to Noun Compound Syntax and Semantics by Preslav Ivanov Nakov Magistar (Sofia University, Bulgaria) 2001 A dissertation submitted in partial satisfaction of the requirements for the degree of Doctor of Philosophy in Computer Science in the GRADUATE DIVISION of the UNIVERSITY OF CALIFORNIA, BERKELEY arXiv:1912.01113v1 [cs.CL] 23 Nov 2019 Committee in charge: Professor Marti Hearst, Co-chair Professor Dan Klein, Co-chair Professor Jerome Feldman Professor Lynn Nichols Fall 2007 The dissertation of Preslav Ivanov Nakov is approved: Professor Marti Hearst, Co-chair Date Professor Dan Klein, Co-chair Date Professor Jerome Feldman Date Professor Lynn Nichols Date University of California, Berkeley Fall 2007 Using the Web as an Implicit Training Set: Application to Noun Compound Syntax and Semantics Copyright 2007 by Preslav Ivanov Nakov 1 Abstract Using the Web as an Implicit Training Set: Application to Noun Compound Syntax and Semantics by Preslav Ivanov Nakov Doctor of Philosophy in Computer Science University of California, Berkeley Professor Marti Hearst, Co-chair Professor Dan Klein, Co-chair An important characteristic of English written text is the abundance of noun compounds – sequences of nouns acting as a single noun, e.g., colon cancer tumor suppressor protein. While eventually mastered by domain experts, their interpretation poses a major challenge for automated analysis. Understanding noun compounds’ syntax and semantics is important for many natural language applications, including question answering, machine translation, information retrieval, and information extraction. For example, a question answering system might need to know whether ‘protein acting as a tumor suppressor’ is an acceptable paraphrase of the noun compound tumor suppressor protein, and an information extraction system might need to decide if the terms neck vein thrombosis and neck thrombosis can possibly co-refer when used in the same document.
    [Show full text]
  • The Challenges of Translating English Compounds Into Arabic - for Better Or for Worse
    الجنان Al Jinan Volume 11 Article 19 2020 The challenges of Translating English Compounds into Arabic - For Better or for Worse Walid M. Amer Islamic University of Gaza, [email protected] Karim Menacere Liverpool Business School, [email protected] Follow this and additional works at: https://digitalcommons.aaru.edu.jo/aljinan Part of the Language Interpretation and Translation Commons Recommended Citation Amer, Walid M. and Menacere, Karim (2020) "The challenges of Translating English Compounds into .Vol. 11 , Article 19 :الجنان Arabic - For Better or for Worse," Al Jinan Available at: https://digitalcommons.aaru.edu.jo/aljinan/vol11/iss1/19 This Article is brought to you for free and open access by Arab Journals Platform. It has been accepted for .by an authorized editor. The journal is hosted on Digital Commons, an Elsevier platform الجنان inclusion in Al Jinan For more information, please contact [email protected], [email protected], [email protected]. -19- Author Corresponding author Dr. Walid M. Amer Dr. Karim Menacere Associate Professor of Linguistics Senior Lecturer Islamic University of Gaza. Liverpool Business School The challenges of Translating English Compounds into Arabic - For Better or for Worse. DOI: 10.33986/0522-000-011-022 Abstract English: This paper examines the main challenges of translating English compounds into Arabic. Compounding is linguistically a common process across many languages where compounds are frequently formed. In English, compounding is highly creative and innovative, and often used as a means of introducing new phrases or coining new words into the lexicon. In contrast, Arabic is less resourceful.
    [Show full text]
  • Verbal Compounding in English: a Challenge for Usage-Based Models of Word-Formation?
    DOI 10.1515/anglia-2013-0066 Anglia 2013, 131 (4): 591–626 Angela Lamberty and Hans-Jörg Schmid Verbal Compounding in English: A Challenge for Usage-Based Models of Word-Formation? Abstract: Usage-based models of grammar claim that, in a nutshell, speakers glean their tacit knowledge about language from their linguistic experience in communicative exchanges. Verbal compounding can be considered a challenge to usage-based models: on the one hand, genuine verbal compounding is gen- erally regarded as not being a productive pattern for the formation of new Eng- lish words; on the other hand, complex lexemes which could very well be the result of such a process, but were created by means of back-formation or con- version, e.g. to dry-clean, to babysit or to house-train, exist in non-negligible quantities. From a usage-based perspective, then, the question arises as to why speakers of English apparently do not have a productive schema for the crea- tion of genuine verbal compounds at their disposal, even though they are con- fronted with linguistic input that seems to suggest, at least on the surface, that verbal compounding is indeed a productive process. Given that speakers with no training in linguistics are unlikely to be aware of the formation history of existing verbal compounds, what is the nature of the tacit knowledge they do seem to have that generally prevents them from creating new genuine verbal compounds and from judging them as acceptable when they come across them? This is the question addressed in the present paper. We offer findings from a systematic dictionary-cum-corpus analysis and from an acceptability and comprehension task which strongly suggest that hearers actually do not process novel genuine verbal compounds as compounds, but rely on different processing strategies instead, trying to take recourse to possible base nouns or adjectives and interpreting meanings on the basis of analogies to similar lexical items in the network.
    [Show full text]
  • A Morphological Comparative Study Between Albanian and English Language
    European Scientific Journal A morphological comparative study between Albanian and English language Aida Kurani Anita Muho University “Aleksander Moisiu”, Durres, Albania Abstract: The aim of this study is to point out similarities and differences of English and Albanian language in the morphological level, trying to compare different parts of speech of both languages. Many languages do not distinguish between adjectives and adverbs or adjectives and names etc, i.e. the Albanian language differs in terms of gender and plural adjectives, while English has not such a feature. Therefore formal distinctions between parts of speech should be done within the framework of a given language and should not be applied in other languages .In this study we have analyzed nouns, verbs, adverbs, adjective structures, the use of articles, pronouns etc. in Albanian and English. In the light of modern linguistics, comparative method plays an important role in the acquisition of languages comparing the first language with the target language. Comparative method is also considered as a key factor in the scientific research of modern linguistics, so it can be used successfully in teaching. Keywords; Albanian, English, differences, morphology, similarities, teaching. 28 European Scientific Journal Introduction In Albanian language, the comparative studies in linguistics are very rare. Considering the fact that language is closely related to culture, a linguistic comparative study is also a cultural comparison. Although all languages mainly play a similar role, there are similarities and differences between them. Knowing the differences between the two languages also helps in identifying students' linguistic errors in the process of teaching the grammar.
    [Show full text]
  • A Morphological Analysis on English Compound Words in Five Articles of BBC News 1
    Rahayu et al., A Morphological Analysis on English Compound Words in Five Articles of BBC News 1 A Morphological Analysis on English Compound Words in Five Articles of BBC News (Analisis Morfologi Kata Campuran Bahasa Inggris di Lima Artikel Pilihan Berita BBC) Kurinta Septi Dwi Rahayu, Sukarno, Dewianti Khazanah English Department, Faculty of Letters, Jember University Jln. Kalimantan 37, Jember 68121 E-mail: [email protected] Abstract This study aimed to analyse English compound words based on the morphological aspects. The morphological aspects are the types, the orthographic features, and the meanings of compounds. The data of this research are taken from five selected articles of BBC news on its website. This study uses qualitative research with descriptive method to analysed the data because the data are in the form of words. This research uses Bauer's theory of the types of compounds, Plag et al.,'s theory of the orthographic features of compounds, and McCarthy's theory of the meanings of compounds as the main theories. The result of the study shows that there are five types of compounds in the selected articles, they are: compound nouns, compound verbs, compound adjectives, neo-classical compounds, and other form classes. Compound nouns become the most dominant types of compounds. When the compounds are complex and longer, they tend to be written separately rather than as a one word or hyphenated. Compounds which are written as a one word, tend to be classified as exocentric compounds. Whereas compounds which are written separately, tend to be classified as endocentric compounds. Keywords: English compound words, BBC news, types of compounds, orthographic features of compounds, meanings of compounds Abstrak Studi ini bertujuan untuk menganalisis kata campuran Bahasa Inggris berdasarkan aspek morfologinya.
    [Show full text]
  • English for Practical Purposes 9
    ENGLISH FOR PRACTICAL PURPOSES 9 CONTENTS Chapter 1: Introduction of English Grammar Chapter 2: Sentence Chapter 3: Noun Chapter 4: Verb Chapter 5: Pronoun Chapter 6: Adjective Chapter 7: Adverb Chapter 8: Preposition Chapter 9: Conjunction Chapter 10: Punctuation Chapter 11: Tenses Chapter 12: Voice Chapter 1 Introduction to English grammar English grammar is the body of rules that describe the structure of expressions in the English language. This includes the structure of words, phrases, clauses and sentences. There are historical, social, and regional variations of English. Divergences from the grammardescribed here occur in some dialects of English. This article describes a generalized present-dayStandard English, the form of speech found in types of public discourse including broadcasting,education, entertainment, government, and news reporting, including both formal and informal speech. There are certain differences in grammar between the standard forms of British English, American English and Australian English, although these are inconspicuous compared with the lexical andpronunciation differences. Word classes and phrases There are eight word classes, or parts of speech, that are distinguished in English: nouns, determiners, pronouns, verbs, adjectives,adverbs, prepositions, and conjunctions. (Determiners, traditionally classified along with adjectives, have not always been regarded as a separate part of speech.) Interjections are another word class, but these are not described here as they do not form part of theclause and sentence structure of the language. Nouns, verbs, adjectives, and adverbs form open classes – word classes that readily accept new members, such as the nouncelebutante (a celebrity who frequents the fashion circles), similar relatively new words. The others are regarded as closed classes.
    [Show full text]
  • The Case of Past Participle-Based Compound Adjectives In
    ASp la revue du GERAS 72 | 2017 Normes et usages en anglais de spécialité An appraisal of recent breakthroughs in machine translation: the case of past participle-based compound adjectives in ESP Évaluation des récentes avancées de la traduction automatique : le cas des adjectifs composés formés à partir d'un participe passé en anglais de spécialité François Maniez Electronic version URL: http://journals.openedition.org/asp/5059 DOI: 10.4000/asp.5059 ISSN: 2108-6354 Publisher Groupe d'étude et de recherche en anglais de spécialité Printed version Date of publication: 1 November 2017 Number of pages: 29-48 ISSN: 1246-8185 Electronic reference François Maniez, « An appraisal of recent breakthroughs in machine translation: the case of past participle-based compound adjectives in ESP », ASp [Online], 72 | 2017, Online since 01 November 2018, connection on 01 November 2020. URL : http://journals.openedition.org/asp/5059 ; DOI : https://doi.org/10.4000/asp.5059 This text was automatically generated on 1 November 2020. Tous droits réservés An appraisal of recent breakthroughs in machine translation: the case of past... 1 An appraisal of recent breakthroughs in machine translation: the case of past participle-based compound adjectives in ESP Évaluation des récentes avancées de la traduction automatique : le cas des adjectifs composés formés à partir d'un participe passé en anglais de spécialité François Maniez 1. Introduction 1 While the problems posed by the translation of denominal adjectives from French into English and vice-versa are well documented (Maniez 2009), the translation into Romance languages of compound adjectives consisting of a past participle preceded by a noun phrase (e.g.
    [Show full text]
  • On the Compositionality and Semantic Interpretation of English Noun Compounds
    On the Compositionality and Semantic Interpretation of English Noun Compounds Corina Dima Collaborative Research Center 833 University of Tubingen,¨ Germany [email protected] Abstract multi-token expressions, in particular adjective- word phrases (Baroni and Zamparelli, 2010), de- In this paper we present a study cover- terminer phrases (Dinu et al., 2013b) or verb ing the creation of compositional distri- phrases (Yin and Schutze,¨ 2014). butional representations for English noun Studying the semantics of multiword units, and compounds (e.g. computer science) using in particular the semantic interpretation of noun two compositional models proposed in the compounds has been an active area of research literature. The compositional representa- in both theoretical and computational linguistics. tions are first evaluated based on their sim- Here, one train of research has focused on under- ilarity to the corresponding corpus-learned standing the mechanism of compounding by pro- representations and then on the task of au- viding a label for the relation between the con- tomatic classification of semantic relations stituents (e.g. in finger nail, the nail is PART OF the for English noun compounds. Our experi- finger) as in (OS´ eaghdha,´ 2008; Tratz and Hovy, ments show that compositional models are 2010) or by identifying the preposition in the pre- able to build meaningful representations ferred paraphrase of the compound (e.g. nail for more than half of the test set com- of the finger) as in (Lauer, 1995). pounds. However, using pre-trained com- In this paper, we explore compositional distri- positional models does not lead to the ex- butional models for English noun compounds, and pected performance gains for the semantic analyze the impact of such models on the task of relation classification task.
    [Show full text]