Compound Noun
Jump to navigation
Jump to search
A compound noun is a compound word that acts as a noun.
- AKA: Compound Nominal Phrase, Multiword Noun.
- Context:
- It can range from being a Noun-Noun Compound(“data-base”),
- an Adjective-Noun Compound, e.g. “whitewash”, “real-time”, “real estate”.
- an Noun-Adjective Compound, e.g. “snow-white”.
- an Noun-Verb Compound, e.g. “health care”.
- It can (typically) be Pluralized by:
- Adding -s to the last element if there is no head noun, such as “forget-me-not” ⇒ “forget-me-nots”.
- Adding -s to the headword if there is a head noun, such as “sister-in-law” ⇒ “sisters-in-law”,, and “male-driver” ⇒ “male-drivers”.
- which illustrates that Compound Noun cannot always be Morphologically treated as a “Noun-with-Spaces”;
- Its meaning/sense can (typically) be more than “the sum of its parts”, e.g. “rock 'n' roll”.
- e.g. sports team names with a determiner “The New York Yankees”: “A The New York Yankees spokesman” is invalid.
- It can be identified via a Noun Compound Bracketing Task.
- ??? It can be a Noun Group, e.g. “tea bag” (but not “high school”).
- It can range from being a Noun-Noun Compound(“data-base”),
- Example(s):
- Unspaced Compound Nouns, such as:
- “bedroom”, “boyfriend”, “laptop”, “loudmouth”,
- “rainfall”, “scarecrow”, “skateboard”, “whitewash”.
- Hyphenated Compound Nouns:
- “bumble-bee”,
- “Redmond-based”, is a Nominalized Noun.
- Spaced Compound Nouns.
- “absolute monarchy”, “answering machine”, “attorney general””, “automatic teller machine”, “bed and breakfast”,
- “bottom line”, “cross-platform application development”, “cruise missile”, “dining room”, “eating utensil”,
- “fast food restaurant”, “fortune cookie”, “health care”, “high school”, “high-definition television”,
- “king of the hill”, “law enforcement officer”, “microwave oven”, “milk chocolate”, “natural language”,
- “non rapid eye movement”, “rapid transit”, “real estate”, “red herring fallacy”, “rock 'n' roll”,
- “tea bag”, “terrace house”, “user interface”, “work in progress”, “yellow fever”.
- Separable Compound Nouns:
- “food additive”, “data mining”, “Redmond-based”.
- with Infix Pluralization.
- “sisters-in-law”, an Inflected Common Noun.
- “notary public”, “notary public's”, and “notaries public”.
- “jack-of-all-trades”, and “jacks-of-all-trades”.
- with conflicting lexical entries
- “life insurance company”, {"life insurance”, “insurance company”}.
- “personal data base” {"personal data”, “data base”}
- Proper Nouns???
- “Michael Jackson”, e.g. “Wayne pulled a [Michael Jackson] with his face.”
- “The United Kingdom of Great Britain and Northern Ireland”.
- “Al Jumahiriyah al Arabiyah al Libiyah ash Shabiyah al Ishtirakiyah al Uzma” (AKA: “Libya”).
- “Canadian Swallowtail Tiger Butterfly” and “Papilio glaucas” are two words that refer to the same Concept.
- “King of Peace Episcopal Church”
- “Black-crowned Central American Squirrel Monkey”
- “Finnegan, Henderson, Farabow, Garrett & Dunner, L.L.P.”
- “The Andes”
- “the New York Yankees”, illustrates that it can require different syntactic rules. E.g. “A The New York Yankees spokesman” is invalid.
- …
- Unspaced Compound Nouns, such as:
- Counter-Example(s):
- “liver cell”, because its components can be reordered without Semantic Loss E.g. “The cell from the liver was cancerous”.
- a Base Noun, such as: “apples” and “establishment”? (v.s. “antidis [establishment]arianism”).
- a noun phrase, such as “the five ripe apples”.
- a Collocation, such as “stiff breeze”.
- a Compound Adjective, such as “high performance”.
- See: Noun Phrase, Bound Morpheme, Compound Word Generation Process, Part-of-Speech Tagging, Entity Mention, Compound (Linguistics), Free Morpheme, Word Class.
References
2015
- (Wikipedia, 2015) ⇒ http://en.wikipedia.org/wiki/English_compound#Compound_nouns Retrieved:2015-12-8.
- Most English compound nouns are noun phrases (= nominal phrases) that include a noun modified by adjectives or noun adjuncts. Due to the English tendency towards conversion, the two classes are not always easily distinguished. Most English compound nouns that consist of more than two words can be constructed recursively by combining two words at a time. Combining "science" and "fiction", and then combining the resulting compound with "writer", for example, can construct the compound “science fiction writer”. Some compounds, such as salt and pepper or mother-of-pearl, cannot be constructed in this way,
2009
- http://en.wiktionary.org/wiki/compound#Noun_2
- 3. (linguistics) A lexeme that consists of more then one stem; for example laptop, formed from lap and top.
- (Wikipedia, 2009) ⇒ http://en.wikipedia.org/wiki/Compound_noun#Noun-noun_compounds
- Most natural languages have compound nouns. The positioning of the language, i.e. the most common order of constituents in phrases where nouns are modified by adjectives, by possessors, by other nouns, etc. While Germanic languages, for example, are left-branching when it comes to noun phrases (the modifiers come before the head), the Romance languages are usually right-branching. In French, compound nouns are often formed by left-hand heads with prepositional components inserted before the modifier, as in chemin-de-fer 'railway' lit. 'road of iron' and moulin à vent 'windmill', lit. 'mill (that works)-by-means-of wind'. In Turkish, one way of forming compound nouns is as follows: yeldeğirmeni ‘windmill’ (yel: wind, değirmen-i:mill-possessive); demiryolu 'railway'(demir: iron, yol-u: road-possessive).
2008
- (Crystal, 2008) ⇒ David Crystal. (2008). “A Dictionary of Linguistics and Phonetics, 6th edition." Blackwell Publishing.
- compound (n.) A term used widely in DESCRIPTIVE LINGUISTIC studies to refer to a linguistic UNIT which is composed of ELEMENTS that function independently in other circumstances. Of particular currency are the notions of compound found in 'compound WORDS' (consisting of two or more free MORPHEMES, as in such 'compound NOUNS' as bedroom, rainfall, and washing machine) and 'compound SENTENCES' (consisting of two or more main CLAUSES); but other application of the term exist, as in 'compound VERBS' (e.g. come in), 'compound TENSES' (those consisting of an AUXILIARY + LEXICAL verb), 'compound SUBJECTS/OBJECTS', etc. (where the clause elements consist of more than one noun PHRASE or PRONOUN, as in the boys and the girls shouted) and 'compound PREPOSITIONS' (e.g. in accordance with). See also BAHAVRUIHI, DVANDVA.
2006
- (Cortés & Verdejo, 2006) ⇒ Jesús Andrés Cortés, and Rafael Rigol Verdejo. (2006). “Teaching how to generate complex nominal phrases used to define new concepts or describe objects.” In: Proceedings of AELFE 2006.
2005
- (Nakov & Hearst, 2005) ⇒ Preslav Nakov, and Marti Hearst. (2005). “Search Engine Statistics Beyond the n-gram: Application to Noun Compound Bracketing.” In: Proceedings of CoNLL-2005.
- It proposes a Noun Compound Bracketing Algorithm.
2003
- (Sag et al., 2003) ⇒ Ivan A. Sag, Thomas Wasow, and Emily M. Bender. (2003). “Syntactic Theory: A Formal Introduction, 2nd edition." CSLI Publications.
- QUOTE: Compounds nouns can be constructed from pairs of nouns:
- 10a. car thief
- 10b. department chair
- 10c. community center
- 10d. Boston lawyer
- 10e. Oakland mayor
- As (10) shows, the first member of the compound can be either a common noun or a proper noun.
- If were were to treat names for mountain rantes and sports teams as 'words with spaces in them', we would incorrectly predict that compound nouns like the following be well formed:
- 13a {a/the} the Andes specialist]
- 13b {a/the} the Oakland Raiders spokesperson].
- Hence there is independent justification for our claims that these classes of proper noun are exceptional both in being plural and in selecting a specifier.
- QUOTE: Compounds nouns can be constructed from pairs of nouns:
1998
- (Starosta et al., 1998) ⇒ Stanley Starosta, Koenraad Kuiper, Siew-Ai Ng, and Zhi-Quian Wu. (1998). “On Defining the Chinese Compound Word: Headedness in Chinese compounding and Chinese vr compounds.” In: Jerome L. Packard, ed., New Approaches to Chinese Word Formation: Morphology, phonology and the lexicon in modern and ancient Chinese, Trends in Linguistics. Studies and Monographs.
- QUOTE: a compound has often been described as a combination of two or more bound morphemes. Nominal compounds present a well-documented set of problems [7, 11, 13] such as:
- 1. The interpretation of a nominal compound is not always a result of combining the meanings of its constituents as is commonly done in a strict compositional approach. In some cases, the meaning of a two-word phrase is formed by one meaning over-writing the meaning of the other word. For example, in our domain, the meaning of the phrase body height is that of the word height.
- 2. Nominal compounds exhibit structural ambiguity, which often coincides with semantic ambiguity. For instance, a machine may have diculties assigning the correct interpretation for the phrase: Smith’s blood pressure test.
- 3. Nominal compounds appear in paraphrase relations with other structures. For example, the result of blood pressure test for Smith and Smith’s blood pressure test result have the same meaning. Analysis of such phrases should yield the same interpretation
- QUOTE: a compound has often been described as a combination of two or more bound morphemes. Nominal compounds present a well-documented set of problems [7, 11, 13] such as:
1996
- (Fabre, 1996) ⇒ Cécile Fabre. (1996). “Interpretation of Nominal Compounds: combining domain-independent and domain-specific information.” In: Proceedings of the 16th Conference on Computational Linguistics
- ABSTRACT: A domain independent model is proposed for the automated interpretation of nominal compounds in English. This model is meant to account for productive rules of interpretation which are inferred from the morpho-syntactic and semantic characteristics of the nominal constituents. In particular, we make extensive use of pustejovsky's principles concerning the predicative information associated with nominals. We argue that it is necessary to draw a line between generalizable semantic principles and domain-specific semantic information. We explain this distinction and we show how this model may be applied to the interpretation of compounds in real texts, provided that complementary semantic information are retrieved.
- (McFetridge et al., 1996) ⇒ Paul McFetridge, Fred Popowich, and Dan Fass. (1996). “An Analysis of Compounds in HPSG (Head-Driven Phrase Structure Grammar) for Database Queries.” In: Data and Knowledge Engineering Journal, 20(2).
- QUOTE: We show that the distinction between head/complement compounding and head/adjunct compounding together with general semantic considerations eliminates ambiguity.
- QUOTE: A compound can be defined as a phrase, in our case a nominal phrase, in which nominals are joined together to form more complex nominals. Examples are phrases like truck driver or tree house or wild dog catcher. Syntactically, a focus of previous analyses has been the apparently high ambiguity of non-verbal compounds. These are structures formed by adjoining nominals in which the left member serves to modify the right member. At times, structural ambiguity correlates with semantic ambiguity, cf. student film society which can be interpreted as a film society for students -- [student [film society]] -- or a society for student films -- student film society].
1995
- (Lauer, 1995) ⇒ Mark Lauer. (1995). “Corpus Statistics Meet the Noun Compound: Some empirical results.” In: Proceedings of the 33rd Annual Meeting of the Association for Computational Linguistics. doi:10.3115/981658.981665
- NOTE: It uses the examples of:
- "[woman/N [aid/N worker/N]]"
- "[hydrogen/N ion/N] exchange/N]"
- QUOTE: If parsing is taken to be the first step in taming the natural language understanding task, then broad coverage NLP remains a jungle inhabited by wild beasts. For instance, parsing noun compounds appears to require detailed world knowledge that is unavailable outside a limited domain (Sparek Jones, 1983). Yet, far from being an obscure, endangered species, the noun compound is flourishing in modern language. It has already made five appearances in this paragraph and at least one diachronic study shows a veritable population explosion (Leonard, 1984). While substantial work on noun compounds exists in both linguistics (e.g. Levi, 1978; Ryder, 1994) and computational linguistics (Finin, 1980; McDonald, 1982; Isabelle, 1984), techniques suitable for broad coverage parsing remain unavailable. This paper explores the application of corpus statistics (Charniak, 1993) to noun compound parsing (other computational problems are addressed in Arens el al, 1987; Vanderwende, 1993 and Sproat, 1994).
- NOTE: It uses the examples of:
1989
- (Gazdar & Mellish, 1989) ⇒ G. Gazdar, and C. Mellish. (1989). “Natural Language Processing in Prolog: An Introduction to Computational Linguistics.” Addison-Wesley Publishing.
1988
- (Gay, 1988) ⇒ Linda S. Gay. (1988). “Interpreting Nominal Compounds for Information Retrieval.” Technical Report: UM-CS-1988-086
- ABSTRACT: A NOMINAL COMPOUND IS A GROUP OF TWO OR MORE NOUNS THAT TOGETHER FORMS A NOUN, SUCH AS `COMPUTER PERFORMANCE EVALUATION TECHNIQUES. INTERPRETING NOMINAL COMPOUNDS IS IMPORTANT FOR ANY NATURAL LANGUAGE PROGRAM BECAUSE COMPOUNDS OCCUR FREQUENTLY IN TEXT. IT IS ALSO IMPORTANT IN INFORMATION RETRIEVAL BECAUSE USER QUERIES CONTAIN MANY NOMINAL COMPOUNDS AND COMPOUNDS OCCUR IN DIFFERENT SURFACE FORMS IN DOCUMENTS. THIS REPORT ADDRESSES THE PROBLEM OF DETERMINING THE RELATIONSHIPS BE- TWEEN THE WORDS IN A COMPOUND. FOR EXAMPLE, THE RELATIONSHIP IN `DATA ANAL- YSIS IS THE `OBJECT RELATIONSHIP, WHILE IN `SILK SHIRT IT IS THE `MADE- OF RELATIONSHIP. KNOWLEDGE ABOUT THE WORLD IS ESSENTIAL IN DETERMINING THE RELATIONSHIPS. FOR INSTANCE, THE KNOWLEDGE THAT NEWSPAPERS ARE DELIVERED AND THAT A BOY IS ABLE TO DELIVER THINGS IS NECESSARY TO INTERPRET `NEWS- PAPER BOY AS: `A BOY WHO DELIVERS NEWSPAPERS. THIS REPORT ALSO INVESTIGATES THE POSSIBILITY OF USING THE INTERPRETA- TION OF NOMINAL COMPOUNDS TO IMPROVE THE PERFORMANCE OF INFORMATION RETRIE- VAL SYSTEMS. THE RESULTS INDICATE THAT TECHNIQUES USING SIMPLE EXTENSIONS TO STANDARD STATISTICAL RETRIEVAL METHODS MIGHT BE MORE COST-EFFECTIVE IN INCREASING PERFORMANCE THAN TECHNIQUES USING THE INTERPRETATION OF NOMINAL COMPOUNDS.
- (Hobbs et al, 1988) ⇒ Jerry R. Hobbs, Mark Stickel, Paul Martin, and Douglas Edwards. (1988). “Interpretation as Abduction.” In: Proceedings of the 26th annual meeting on Association for Computational Linguistics (ACL 1988).
- An approach to abductive inference developed in the TACITUS project has resulted in a dramatic simplification of how the problem of interpreting texts is conceptualized. Its use in solving the local pragmatics problems of reference, compound nominals, syntactic ambiguity, and metonymy is described and illustrated. It also suggests an elegant and thorough integration of syntax, semantics, and pragmatics.
1987
- (Pereira & Shieber, 1987) ⇒ F. C. N. Pereira, and S. M. Shieber. (1987). “Prolog and Natural Language Analysis. CSLI, Stanford University.
1983
- (Salager, 1983) ⇒ Francoise Salager. (1983). “Compound Nominal Phrases in Scientific-Technical Literature: Proportion and Rationale." "
- ABSTRACT: The frequency of occurrence of compound nominal phrases (CNP) in medical English literature was compared to the frequency of occurrence in general English. Ten medical English and 10 general English sample texts of 2,000 words each were selected to record and analyze the CNPs. CNPs were defined as those items made up of at least two individual lexical constituents separated by a space or a dash (e.g., vein catheter, maintenance infusion). The following data were recorded: (1) the number of CNPs consisting of 2, 3, 4, 5 and more individual lexical items; (2) the total number of CNPs; (3) the CNP average length; and (4) the proportion of CNPs. Findings include the following: the CNP average length was similar in medical English and general English; the frequency of occurrence of CNPs was significantly higher in medical English than in general English; the relative distributions of CNPs were quite different in the two types of prose; and the more specialized the text, the longer the CNPs. Because of difficulties experienced in reading material and technical English by foreign scientists, examples are included on the following: noun modification in English and Russian compounds; linking vowels in Russian word-compounds and their English equivalents; and compounds in English, Spanish, French, Russian, and German. Appended materials include a list of sample texts for medical English, general English, and technical English; a general bibliography; and examples of CNPs. (SW)
- (Spark Jones, 1983) ⇒ Karen Spärck Jones. (1983). “Compound Noun Interpretation Problems.” In: Fallside, F. and Woods, W.A., editors, Computer Speech Processing.” Prentice-Hall.
- It is well known that, in English at least, compound nouns It can be freely constructed, generating units of, in some cases, surprising length. Certainly pairs of nouns are very common (e.g. “basket lid"), triples occur frequently ("staff tearoom pinboard"), and in 'technical' contexts especially even longer compounds are not unusual ("satellite radio link transmitter", "horse race apprentice training establishment"). When proper names figure, compounds may reach the amazing length of the Gleitman's "Volume Feeding Management Success Formula Award" (Gleitman and Gleitman 1970; "Volume Feeding Management" is a name).
- It is not in fact possible to maintain a principled distinction between lexicalised and non-lexicalised compounds, even within specialised universes of discourse. Some compounds are clearly lexicalised, as may be shown in their becoming single words ("tearoom"), developing meaning extension having no reference to their underlying structure, etc. However, even those compounds canonised by entries in lexicons differ in the extend to which they are established, and are properly regarded only as representing one end of a spectrum from the firmly established to the totally novel. It may be convenient for the purposes of linguistic discussion to group compounds, and at the same time more satisfactory, to label compounds as established, non-established, or novel (as Warren 1978 does) rather than as simply lexicalised or non-lexicalised...
- Interpreting compound nouns, i.e. providing a meaning representation for them, has three elements. The senses of the constituent words have to be identified; the structure, i.e. syntactic bracketing, of the group has to be determined; and the semantic relations linking the words have to be established.
1980
- (Finin, 1980b) ⇒ Tim Finin. (1980). “The Semantic Interpretation of Nominal Compounds.” In: Proceedings of the First Annual National Conference on Artificial Intelligence (AAAI 1980).
- ABSTRACT: This paper briefly introduces an approach to the problem of building semantic interpretations of nominal compounds, i.e., sequences of two or more nouns related through modification. Examples of the kind of nominal compounds dealt with are: "engine repairs", "aircraft flight arrival", "aluminum water pipe" and "noun noun modification".
- (Finin, 1980a) ⇒ Tim Finin. (1980). “Semantic Interpretation of Compound Nominals." Phd Thesis, University of Illinois, Urbana Champaign, May 1980.
- ABSTRACT: This thesis deals with one aspect of enabling machines to communicate with people in a natural language. The particular problem which is the focus of this work is the interpretation of nominal compounds, i.e. sequences of two or more nouns related through modification. Examples of the kinds of nominal compounds dealt with are "engine repairs" "air craft flight arrival" "aluminum water pump", and "noun noun modification".
1978
- (Warren, 1978) ⇒ Beatrice Warren. (1978). “Semantic Patterns of Noun-Noun Compounds.” GOthenburg Studeis in English 41.
1977
- (Downing, 1977) ⇒ Pamela Downing. (1977). “On the Creation and Use of English Compound Nouns.” In: Language, (53).
- NOTES: It analyzes the properties of Comound Nouns, specifically N+N Compound Nouns.
- NOTES: It defines a N+N Compound Noun based on Li (1971:19)'s definition: “the simple concatenation of any two or more nouns functioning as a third nominal”.
- NOTES: It examines the more common relationships between the first and second noun in a nominal compound
- NOTES: It concludes that there are a large number of relationships and that can be unpredictable from the semantics of the two words.
1971
- (Li, 1971) ⇒ Charles Li. (1971). “Semantics and the Structure of Compounds in Chinese.” PhD thesis, University of California, Berkeley.
1968
- (Kooij, 1968) ⇒ Jan G. Kooij (1968). “Compounds and Idioms.” In: Lingua: International Review of General Linguistics, 21.
- NOTES: It distinguishes between Idiomatic Compounds and Non-Idiomatic Compounds.
- NOTES: It describes an Idiomatic Compound as being unexplainable from its constituents