Word Sense Disambiguation (WSD) Task

A Word Sense Disambiguation (WSD) Task is a word mention to word sense resolution task that is restricted to the use of word sense inventory.

• Context:
  • Input:
    • a Text Item.
    • a Word Sense Inventory.
  • Optional Input:
    • a Training Set of Sense Tagged Expressions.
  • output:
    • a Sense Tagged Expression.
  • It can be solved by a Word Sense Disambiguation System (that implements a WSD algorithm).
  • It can range from being a Manual Word Sense Classification Task to being an Automated Word Sense Classification Task.
  • It can range from being a Heuristic Word Sense Classification Task to being an Data-Driven Word Sense Classification Task.
  • It can range from being an All-Words Sense Disambiguation Task to being Target-Word Sense Disambiguation Task (for some specified words in the input).
  • It can range from being a Coarse-Grained Word Sense Disambiguation Task (with dissimilar word senses) to being a Fine-Grained Word Sense Disambiguation Task (with overlapping word senses).
  • It can range from assuming that the Word Sense Inventory contains all Word Sense Records to only containing some Word Sense Records.
  • It can be supported by: Word Mention Detection and Word Mention Classification.
  • ...
• Example:
  • a Common Word Disambiguation Task.
    • WSDT("[The] [bank] [survived] [the] [flood] [].") ⇒ “The/1 bank/1,3 survived/1 the/1 flood/1”, where the number beside each word corresponds to the sense of the word. (For the Homographous Word “bank” there is some Word Sense Ambiguity).
    • SensEval Benchmark Task: SensEval-1 Benchmark Task, SensEval-2 Benchmark Task, SensEval-3 Benchmark Task.
    • WSDT("He fasted, and to hold fast to his fast he fastly rejected any fast food.”) ⇒ ...
  • a Term Sense Disambiguation Task.
    • WSDT("The semi-supervised transductive learning algorithm was empirically tested on synthetic data and the N20 corpus.”) ⇒ The [semi-supervised transductive learning algorithm] was [empirically tested] on [synthetic data] and the [N20 corpus].
  • ...
  • …
• Counter-Example(s):
  • A Word Mention Recognition Task, such as named entity recognition.
  • A Term Sense Disambiguation Task.
• See: Wikification; Homonym Relation; Entity Mention to Entity Record Resolution Task; Word Sense Clustering Task; Semi-supervised Text Processing, Semantic Annotation; Concept Mention Annotation.

---

---

References

2012

• (Wikipedia, 2012) ⇒ http://en.wikipedia.org/wiki/Word_sense_disambiguation
  • QUOTE: In computational linguistics, word-sense disambiguation (WSD) is an open problem of natural language processing, which governs the process of identifying which sense of a word (i.e. meaning) is used in a sentence, when the word has multiple meanings (polysemy). The solution to this problem impacts other computer-related writing, such as discourse, improving relevance of search engines, anaphora resolution, coherence, inference et cetera.

    Research has progressed steadily to the point where WSD systems achieve sufficiently high levels of accuracy on a variety of word types and ambiguities. A rich variety of techniques have been researched, from dictionary-based methods that use the knowledge encoded in lexical resources, to supervised machine learning methods in which a classifier is trained for each distinct word on a corpus of manually sense-annotated examples, to completely unsupervised methods that cluster occurrences of words, thereby inducing word senses. Among these, supervised learning approaches have been the most successful algorithms to date.

    Current accuracy is difficult to state without a host of caveats. In English, accuracy at the coarse-grained (homograph) level is routinely above 90%, with some methods on particular homographs achieving over 96%. On finer-grained sense distinctions, top accuracies from 59.1% to 69.0% have been reported in recent evaluation exercises (SemEval-2007, Senseval-2), where the baseline accuracy of the simplest possible algorithm of always choosing the most frequent sense was 51.4% and 57%, respectively.

2011

• (Mihalcea, 2011) ⇒ Rada Mihalcea. (2011). “Word Sense Disambiguation" In: (Sammut & Webb, 2011) p.1027

2009a

• (Navigli, 2009) ⇒ Roberto Navigli. (2009). “Word Sense Disambiguation: A survey.” In: ACM Computing Surveys (CSUR) 41(2). doi:10.1145/1459352.1459355
  • QUOTE: Word sense disambiguation (WSD) is the ability to identify the meaning of words in context in a computational manner. WSD is considered an AI-complete problem, that is, a task whose solution is at least as hard as the most difficult problems in artificial intelligence. We introduce the reader to the motivations for solving the ambiguity of words and provide a description of the task.

2009b

• http://www.cse.unsw.edu.au/~billw/nlpdict.html#wordsenseambig
  • QUOTE: A kind of ambiguity where what is in doubt is what sense of a word is intended. One classic example is in the sentence "John shot some bucks". Here there are (at least) two readings - one corresponding to interpreting "bucks" as meaning male deer, and "shot" meaning to kill, wound or damage with a projectile weapon (gun or arrow), and the other corresponding to interpreting "shot" as meaning "waste", and "bucks" as meaning dollars. Other readings (such as damaging some dollars) are possible but semantically implausible. Notice that all readings mentioned have the same syntactic structure, as in each case, "shot" is a verb and "bucks" is a noun.
  • See also structural ambiguity and referential ambiguity.

2009c

• (Lingpipe WSD Tutorial, 2009) LingPipe. (2009). “LingPipe: Word Sense Tutorial." LingPipe Homepage.
  • QUOTE: Word sense disambiguation (WSD) is the task of determining which meaning of a polysemous word is intended in a given context.

    Some words, such as English "run", are highly ambiguous. The American Heritage Dictionary, 4th Edition lists 28 intransitive verb senses, 31 transitive verb senses, 30 nominal senses and 46 adjectival senses. The word "gallop" has a mere 4 nominal senses, and the word "subroutine" only 1 nominal sense.

    Where Do Senses Come From?

    It would be convenient if we could trust dictionaries as the arbiter of word senses. Unfortunately, language presents harder problems than that. Words are fluid, living things that change meanings through metaphor, extension, adaptation, and just plain randomness. Attempting to carve the meaning of a word into a set of discrete categories with well-defined boundaries is doomed to fail for a number of reasons.

    • Words do not have well-defined boundaries between their senses. Dictionary definitions attempt to distinguish a discrete set of meanings with examples and definitions, which are themselves vague. Luckily, humans deal with vagueness in their language quite well, so this is not so much a problem with humans using dictionaries.
    • A related problem with dictionaries is that they don't agree. A quick glance at more than one dictionary (follow the link for "run", for example) will show that disagreement is not only possible, it's the norm. There is often overlap of meanings with subtle distinctions at the boundaries, which in practice, are actually vague.
    • Another problem with dictionaries is that they are incomplete. Today's newspaper or e-mail is likely to contain words or word senses that are not present in today's dictionary.
  • In practice, dictionaries can be useful. They might be good enough for practical purposes even if there are tail-of-the-distribution or boundary cases they don't adequately capture.
  • Supervised vs. Unsupervised WSD
    • We will assume for the rest of this tutorial that the words we care about will have finitely many disjoint senses. If we have training data, word sense disambiguation reduces to a classification problem. Additional training data may be supplied in the form of dictionary definitions, ontologies such as Medical Subject Headings (MeSH), or lexical resources like WordNet.
    • If there is no training data, word sense disambiguation is a clustering problem. Hierarchical clusterings may make sense; the dictionaries sited above break meanings of the word "run" down into senses and sub-senses.
    • For this demo, we will be doing supervised word sense disambiguation. That is, we will have training data consisting of examples of words in context and their meanings. We will compare several LingPipe classifiers on this task.

2008

• (Koehn, 2008) ⇒ Philipp Koehn. (2008). “Statistical Machine Translation." Cambridge University Press. ISBN:0521874157
  • QUOTE: ... 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.

2006

• (JoshiPPMC, 2006) ⇒ Mahesh Joshi, Serguei Pakhomov, Ted Pedersen, Richard Maclin, and Christopher Chute. (2006). “An End-to-end Supervised Target-Word Sense Disambiguation System.” In: Proceedings of AAAI-2006 (Intelligent System Demonstration).
  • QUOTE: Word Sense Disambiguation (WSD) is the task of automatically deciding the sense of an ambiguous word based on its surrounding context. The correct sense is usually chosen from a predefined set of senses, known as the sense inventory. In target-word sense disambiguation the scope is limited to assigning meaning to occurrences of a few predefined target words in the given corpus of text.

2005

• (Mihalcea & Petersen, 2005) ⇒ Rada Mihalcea, and Ted Pedersen. (2005). “Advances in Word Sense Disambiguation." Tutorial at ACL 2005.
• QUOTE: Word sense disambiguation is the problem of selecting a sense for a word from a set of predefined possibilities.
  • Sense Inventory usually comes from a dictionary or thesaurus.
  • Knowledge intensive methods, supervised learning, and (sometimes) bootstrapping approaches

2003

• (Mitkov, 2003) ⇒ Ruslan Mitkov, editor. (2003). “The Oxford Handbook of Computational Linguistics." Oxford University Press. ISBN:019927634X
  • QUOTE: word-sense disambiguation: The process of identifying the meanings of words in context.

1998

• (Nancy & Véronis, 1998) ⇒ Nancy Ide, and Jean Véronis. “Introduction to the special issue on word sense disambiguation: the state of the art.” In: Computational Linguistics, 24(1).
  • QUOTE: The problem of word sense disambiguation (WSD) has been described as “AI-complete," that is, a problem which can be solved only by first resolving all the difficult problems in artificial intelligence (AI), such as the representation of common sense and encyclopedic knowledge. The inherent difficulty of sense disambiguation was a central point in Bar-Hillel's well-known treatise on machine translation (Bar-Hillel 1960), where he asserted that he saw no means by which the sense of the word pen in the sentence The box is in the pen could be determined automatically.

1997

• (Kilgarriff, 1997) ⇒ Adam Kilgarriff (1997). “I Don't Believe in Word Senses.” In: Computers and the Humanities, 31(2).

---