Word Sense

Jump to: navigation, search

A word sense is the concept with a set of referent words.



  1. N. Ide and J. Véronis Word Sense Disambiguation: The State of the Art, Computational Linguistics, 24, 1998, pp. 1-40.
  2. R. Navigli. Word Sense Disambiguation: A Survey, ACM Computing Surveys, 41(2), 2009, pp. 1-69.


  • (WordNet, 2009) ⇒ http://wordnetweb.princeton.edu/perl/webwn?s=word%20sense
    • S: (n) word meaning, word sense, acceptation (the accepted meaning of a word)
  • http://wordnet.princeton.edu/man/wngloss.7WN
    • sense: A meaning of a word in WordNet. Each sense of a word is in a different synset .
  • (Jurafsky & Martin, 2009) ⇒ Daniel Jurafsky, and James H. Martin. (2009). “Speech and Language Processing, 2nd edition." Pearson Education.
    • QUOTE: The meaning of a lexeme can very enormously given the context. Consider these two users of the lemma bank ... We represent some of this contextual variation by saying that the lemma bank has two senses (footnote: confusingly, the word "lemma" is itself ambiguous; it is also sometimes used to mean these separate senses, rather than the citation form of the word. You should be prepared to see both uses in the literature). A sense (or word sense) is a discrete representation of one aspect of the meaning of a word. Loosely following lexicographic tradition, we represent each sense by placing a superscript on the orthographic form of the lemma as in bank1 and bank2. The sense of a word might not have any particular relation between them; it may be almost coincident that they share an orthographic form. For example, the financial institution and sloping mound sense of bank seem relatively unrelated. In such cases we say that the two senses are homonyms, and the relation between the sense is on of homonymy When two senses are related semantically, we call the relationship between them polysemy rather than homonymy.
  • (Navigli, 2009) ⇒ Roberto Navigli. (2009). “Word Sense Disambiguation: A survey.” In: ACM Computing Surveys (CSUR) 41(2). doi:10.1145/1459352.1459355


  • (Koehn, 2008) ⇒ Philipp Koehn. (2008). “Statistical Machine Translation." Cambridge University Press. ISBN:0521874157
    • The definition of word senses, like everything else in semantics, is difficult business. How many senses does the word interest have? ... Fortunately, translation provides a clear basis for defining relevant word senses. A word has multiple senses, if it has multiple translations into another language. For instance, the three meanings of interest we listed above result in different translations into German: Interesse (curiosity sense), Anteil (stake sense) and Zins (money sense). ... The task of determining the right word sense for a word in a given context is called word sense disambiguation. Research in this area has shown that the word context such as closely neighboring words and content words in a larger window are good indicators for word sense.


  • (Matthews, 2007) ⇒ Peter H Matthews. (2007). “Oxford Concise Dictionary of Linguistics." Oxford University Press
    • QUOTE: reference ... Distinguished by philosophers from sense(2), and by Lyons especially from denotation. E.g. the man is a phrase that, in such as utterance, is used to refer to a man; the noun man, as a lexical unit, denotes a class of individuals that are thereby called 'men', and has a sense distinguished, in a network of sense relations, from those of woman, boy, elephant, etc.
    • sense
      • 1. A meaning of a lexical unit distinguished, e.g. in a dictionary, from other meanings. Thus chair has one sense when it is used to refer to a piece of furniture and another when used to refer to someones chairing a meeting. Cf. use for distinct meanings in grammar.
      • 2. The place of a lexical unit within the semantic system of a language: e.g. that of chair is defined by the relations that distinguish it from furniture, from armchair, from table, and so on.
      • 3. The meaning of expressions as distinct from its reference. Thus, in a famous example of the philosopher G. Frege, the morning star and the evening star have the same referent (the planet Venus) but differ in sense.
    • sense relation Any relation between lexical units within the semantic system of a language: cf. sense (2). ... antonymy; complementarity; converse terms; hyponymy; incompatibility; meronymy; synonymy.


  • (MohammadH, 2006) ⇒ Saif Mohammad, and Graeme Hirst. (2006). “Determining Word Sense Dominance Using a Thesaurus.” In: Proceedings of EACL-2006.
    • The occurrences of the senses of a word usually have skewed distribution in text. Further, the distribution varies in accordance with the domain or topic of discussion. For example, the ‘assertion of illegality’ sense of charge is more frequent in the judicial domain, while in the domain of economics, the ‘expense/cost’ sense occurs more often. Formally, the degree of dominance of a particular sense of a word (target word) in a given text (target text) may be defined as the ratio of the occurrences of the sense to the total occurrences of the target word. The sense with the highest dominance in the target text is called the predominant sense of the target word.


  • (Hanks, 2000) ⇒ Patrick Hanks. (2000). “Do Word Meanings Exist?.” In: Computers and the Humanities, 34(1-2).
    • NOTES: It suggests that the Word bank is not one word with more than one meaning, but separate words (with separate meanings) that happen to be spelled the same.
    • NOTES: It suggest an alternative question of "What is the unique contribution of this word to the meaning of this text?"
    • Question: If looked at from the perspective of the lexicographer's work, what part of the process is the focus on? Finding relevant new uses? Summarizing the use?
  • (Palmer, 2000) ⇒ Martha Palmer. (2000). “Consistent Criteria for Sense Distinctions.” In: Computers and the Humanities, 34(1-2).
    • NOTES: It analyzes Verb Polymemy.
    • NOTES: It analyzes the effectiveness of WordNet's Verb Sense divisions.
      • For example WordNet separate senses of “cut” cutting grain, trees, hair, and for separating into pieces of a concrete object.


  • (M-W Colleg. Dict., 1999) ⇒ Merriam-Webster. (1999). “Merriam-Webster's Collegiate Dictionary, 10th edition.
    • NOTES: It suggests that a Dictionary Entry focuses on the Denotation of Words rather than their Connotation.
    • QUOTE: If one function of a dictionary is more important than its many others, surely that function is to define the meaning of words.
    • QUOTE: ... our understanding of the semantic system is very imperfect, and much of what we do know about it does not come very obviously into play in a dictionary.
    • QUOTE: Perhaps the first thing that we need to remind ourselves of is that when we speak of the meaning of a word we are employing an artificial, if highly useful, convention. Meaning does not truly reside within the word but in the minds of those who hear or read it. This fact alone guarantees that the meaning will be to a great degree amorphous: no two people have had exactly the same experience with what a word refers to and so the meaning of the word will be slightly or greatly different for each of us.
    • QUOTE: So dictionary editors involve the traditional distinction between denotation - the direct and specific part of meaning which is sometimes indicated as the total of all the referents of a word and is shared by all or most people who use the word - and connotation - the more personal association and shades of meaning that gather about a word as a result of individual experience and which may not be widely shared. The dictionary concerns itself essentially with the denotations of words.


  • (Kilgarriff, 1997) ⇒ Adam Kilgarriff (1997). “I Don't Believe in Word Senses.” In: Computers and the Humanities, 31(2).
    • Following a description of the conflict between WSD and lexicological research, I examined the concept, ‘word sense’. It was not found to be sufficiently well-defined to be a workable basic unit of meaning.
    • I then presented an account of word meaning in which ‘word sense’ or ‘lexical unit’ is not a basic unit. Rather, the basic units are occurrences of the word in context (operationalised as corpus citations). In the simplest case, corpus citations fall into one or more distinct clusters and each of these clusters, if large enough and distinct enough from other clusters, forms a distinct word sense. But many or most cases are not simple, and even for an apparently straightforward common noun with physical objects as denotation, handbag, there are a significant number of aberrant citations.




  • (Gale et al., 1992) ⇒ William A. Gale, Kenneth W. Church, and David Yarowsky (1992). “One Sense per Discourse.” In: Proceedings of the DARPA Speech and Natural Language Workshop.
    • It is well-known that there are polysemous words like sentence whose "meaning" or "sense" depends on the context of use. We have recently reported on two new word-sense disambiguation systems, one trained on bilingual material (the Canadian Hansards) and the other trained on monolingual material (Roget's Thesaurus and Grolier's Encyclopedia). As this work was nearing completion, we observed a very strong discourse effect. That is, if a polysemous word such as sentence appears two or more times in a well-written discourse, it is extremely likely that they will all share the same sense. This paper describes an experiment which confirmed this hypothesis and found that the tendency to share sense in the same discourse is extremely strong (98%). This result can be used as an additional source of constraint for improving the performance of the word-sense disambiguation algorithm. In addition, it could also be used to help evaluate disambiguation algorithms that did not make use of the discourse constraint.


  • Charles Ruhl. (1989). “On Monosemy." SUNY Press.
    • NOTES: It reminds that the 'perceived meaning' of a word can vary so greatly from one context to another.
    • NOTES: It suggests that words are better conceived as having a single (mono) meaning, unlike the approach used in a dictionary.



  • (Wittgenstein, 1953) ⇒ Ludwig Wittgenstein. (1953). “Philosophical Investigations.
    • NOTES: It presents the challenge of Defining the Meaning of Wordgame”, and suggests that no (analytical?) definition is possible. It suggest a 'family' of relations approach ...
    • QUOTE: 66. Consider for example the proceedings that we call "games." I mean board-games, card-games, ball-games, Olympic games, and so on. What is common to them all?--Don't say: "There must be something common, or they would not be called 'games'"--but look and see whether there is anything common on all.--For if you look at them you will not see something that is common to all, but similarities, relationships, and a whole series of them at that.


  • (Odgen and Richards, 1923) ⇒ C. K. Ogden and I. A. Richards. (1923). “The Meaning of Meaning: A Study of the Influence of Language upon Thought and of the Science of Symbolism. University of Cambridge.


  • (Frege, 1892) ⇒ Gottlob Frege. (1892). “On Sense and Reference.” In: Zeitschrift für Philosophie und philosophische Kritik, C: 25-50.
    • NOTES: It includes his famous argument on the distinction between Sense and Reference.
    • NOTES: It presents the example of the two Greek WordsHesperus” and “Phosphorus” that in ancient Greece stood for (invoked the Sense of) the “evening star” and “morning star” which at that time were unknown to have the same Referent: i.e. Venus (a situation that allows for the False BeliefHesperus"≠"Phosphorus"=>True).