[ad_1]
Anaphor resolution is the process of determining which noun or object a pronoun refers to. Linguists use statistical models to determine the most likely referent, but common sense is also important. Anaphora can refer to a third person pronoun referring to a noun that has already been mentioned, or to any pronoun. Linguists use algorithms to predict the resolution of anaphora, but no algorithm has the same level of common sense as an intelligent human reader.
In linguistics, anaphor resolution is the process of determining which real-world noun or object a pronoun refers to. It can be used to discuss the process by which the human mind understands reference, or it can mean the statistical models devised by linguists to determine the most likely referent. The term “anaphora resolution” can cause some confusion due to the array of possible meanings of the word anaphora, which comes from the Greek “to bring back” or “to bring up.” In rhetoric, anaphora is the repetition of keywords at the beginning of sentences, sentences or paragraphs.
Within the discipline of linguistics, anaphora refers more precisely to a third person pronoun referring to a noun that has already been mentioned within a text. When discussing anaphora resolution, it can have a more general meaning than any pronoun, whether its referent occurs before or after it in the text, or outside the text. For an example of the latter, a person might point to a painting and say, “I like it.” In the context of the real world, “that” would mean “the painting I’m pointing to.”
When only the linguistic content is available for analysis, sometimes there is only one noun in the sentence which corresponds to the anaphora in grammatical person, number and gender. In this case the resolution of the anaphora is clear, as in: “Laura is stronger than she seems”, with the referent of “her” being “Laura”. If there is more than one noun in the sentence, however, the reader relies on common sense to determine the referent, as in: “Some girls wear pink bows in their hair because they like them.” In this sentence, “they” clearly refers to girls, while “they” clearly refers to bows, because bows are not able to like girls, but girls are able to like bows.
If instead the sentence were placed in a different context, the reference might not be so clear: “Girls do many things to get boys’ attention. Some girls wear bows in their hair because they like them.” In this case, the “they” can refer to “girls” or it can refer to “boys.” An argument could be made for both antecedents.
Linguists have devised statistical algorithms to predict the resolution of anaphora using factors such as distance from the pronoun to the referent, the grammatical agreement of the noun with the pronoun, and the animacity of the noun. Some of these algorithms can lead to the correct resolution of the anaphora in the vast majority of cases, but no existing algorithm has the same level of common sense as an intelligent human reader. The following sentence demonstrates this fact: “The seal propelled the ball with a flipper, then balanced the ball on its nose.” Grammatically speaking, “his” could refer to the seal, fin, or ball, but only one of those options actually has a nose. Developing code that eliminates all illogical possibilities, such as a ball with a nose, would seem virtually impossible.
[ad_2]