22.1.1 Ambiguity in Named Entity Recognition

Named entity recognition systems face two types of ambiguity. The first arises from the fact the same name can refer to different entities of the same type. For example, JFK can refer to the former president or his son. This is basically a reference resolution problem and approaches to resolving this kind of ambiguity are discussed in Ch. 21.

The second source of ambiguity arises from the fact that identical named entity mentions can refer to entities of completely different types. For example, in addition to people, JFK might refer to the airport in New York, or to any number of schools, bridges and streets around the United States. Some examples of this kind of cross-type confusion are given in Figures 22.3 and 22.4.

Notice that some of the ambiguities shown in Fig. 22.3 are completely coincidental. There is no relationship between the financial and organizational uses of the name IRA — they simply arose coincidentally as acronyms from different sources (Individual Retirement Account and International Reading Association). On the other hand, the organizational uses of Washington and Downing St. are examples of a LOCATION-FOR-ORGANIZATION metonymy, as discussed in Ch. 19.