Linguistic Structural Disambiguation Task

A Linguistic Structural Disambiguation Task is a Natural Language Processing Task that can resolve ambiguity in linguistic structures.

• AKA: Linguistic Disambiguation Task, NLP Disambiguation Task, Structural Disambiguation.
• Context:
  • Task Input: Text Item containing an ambiguous linguistic structure.
  • Task Output: ranked set of linguistic variants.
  • Task Requirement: Linguistic Disambiguation Mechanism.
  • It can be solved by a Linguistic Structural Disambiguation System that implements a Linguistic Structural Disambiguation Algorithm.
  • It can range from being a Syntactical Disambiguation Task, to being a Lexical Disambiguation Task, to being a Referential Disambiguation.
• Example(s):
  • a Sentence Disambiguation Task,
  • a Sentence Boundary Disambiguation Task,
  • a Verb Sense Disambiguation Task,
  • a Word Sense Disambiguation Task.
  • …
• Counter-Example(s):
  • Morphological Analysis Task,
  • Sentiment Analysis Task.
  • math counter-examples
• See: Parsing Task, Text Processing Task, Text Segmentation Task, Syntactic Analysis, Semantic Network, Machine Translation, Probabilistic Context-Free Grammar (CFG), Semantic Similarity.

---

---

References

2001a

• (Galicia-Haro et al., 2001) ⇒ Sofia N. Galicia-Haro, Alexander Gelbukh, and Igor A. Bolshakov (2001, February). "Three Mechanisms of Parser Driving for Structure Disambiguation". In: International Conference on Intelligent Text Processing and Computational Linguistics (CICLing 2001). DOI:10.1007/3-540-44686-9_19.
  • QUOTE: Structural ambiguity is one of the most difficult problems in natural language processing. Two disambiguation mechanisms for unrestricted text analysis are commonly used: lexical knowledge and context considerations. Our parsing method includes three different mechanisms to reveal syntactic structures and an additional voting module to obtain the most probable structures for a sentence.
    ...
    (...) The overall system is presented in Figure 1. Each module gives a set of weighted variants. Those weights are based on the satisfied characteristics in each method. So, each module gives a quantitative measure of the probability of each syntactic structure in a dependency structure format.

Figure 1: The model for syntactic disambiguation.

2001b

• (Jacquemin, 2001) ⇒ Christian Jacquemin. (2001). “Spotting and Discovering Terms Through Natural Language Processing." MIT Press. ISBN:0262100851
  • QUOTE: Structural disambiguation: If a term is structurally ambiguous, the structural disambiguation of term is the selection of the substructures that are linguistically plausible.

1998

• (Gelbukh, 1998) ⇒ Alexander F. Gelbukh (1998). "Lexical, Syntactic, and Referencial Disambiguation Using a Semantic Network Dictionary". In: Technical report. CIC, lPN.
  • QUOTE: The most unpleasant problem that nearly any algorithm dealing with the natural language faces is the curse of ambiguity. Be it just one word, or a phrase, or a text, there always are several possible interpretations of what it means or what structure it has. We consider ambiguity resolution at all the levels of the language the most important problem of natural language processing. In much larger number of cases than it seems at the first glance, to resolve the ambiguity complicated reasoning or deep knowledge is necessary, often of semantic, pragmatic, or extralinguistic nature.
    ...

    Consider an English phrase “John sees a cat with a telescope.” The phrase is syntactically ambiguous: Does it mean ‘John uses a telescope to see a cat’ or ‘John sees a cat that has a telescope’, or ‘John sees a cat and a telescope’, or maybe ‘John that has a telescope sees a cat’, etc.? This ambiguity cannot be resolved using only lexical or syntactical information, since all the interpretations are quite legal syntactically. On Fig. 3, the first two of above variants are represented.

Figure 3: Resolution of syntactic ambiguity.

1996

• (Chiang & Su, 1996) ⇒ TungHui Chiang and Keh-Yih Su (1996). "Statistical Models for Deep-structure Disambiguation". In: Fourth Workshop on Very Large Corpora.
  • QUOTE: The block diagram of the deep-structure disambiguation system is illustrated in Figure 1. As shown, the input word sequence is first tagged with the possible part-of-speech sequences. A word sequence would, in general, correspond to more than one part-of-speech sequence. The parser analyzes the part-of-speech sequences and then produces corresponding parse trees. Afterwards, the parse trees are analyzed by the semantic interpreter, and various interpretations represented by the normal form are generated. Finally, the proposed integrated score function is adopted to select the most plausible normal form as the output (...)

Figure 3: Block diagram of the deep-structure disambiguation system.

---