Entity disambiguation using semantic networks by Jorge H. Román, Kevin J. Hulin, Linn M. Collins and James E. Powell. Journal of the American Society for Information Science and Technology, published 29 August 2012.
Abstract:
A major stumbling block preventing machines from understanding text is the problem of entity disambiguation. While humans find it easy to determine that a person named in one story is the same person referenced in a second story, machines rely heavily on crude heuristics such as string matching and stemming to make guesses as to whether nouns are coreferent. A key advantage that humans have over machines is the ability to mentally make connections between ideas and, based on these connections, reason how likely two entities are to be the same. Mirroring this natural thought process, we have created a prototype framework for disambiguating entities that is based on connectedness. In this article, we demonstrate it in the practical application of disambiguating authors across a large set of bibliographic records. By representing knowledge from the records as edges in a graph between a subject and an object, we believe that the problem of disambiguating entities reduces to the problem of discovering the most strongly connected nodes in a graph. The knowledge from the records comes in many different forms, such as names of people, date of publication, and themes extracted from the text of the abstract. These different types of knowledge are fused to create the graph required for disambiguation. Furthermore, the resulting graph and framework can be used for more complex operations.
To give you a sense of the author’s approach:
A semantic network is the underlying information representation chosen for the approach. The framework uses several algorithms to generate subgraphs in various dimensions. For example: a person’s name is mapped into a phonetic dimension, the abstract is mapped into a conceptual dimension, and the rest are mapped into other dimensions. To map a name into its phonetic representation, an algorithm translates the name of a person into a sequence of phonemes. Therefore, two names that are written differently but pronounced the same are considered to be the same in this dimension. The “same” qualification in one of these dimensions is then used to identify potential coreferent entities. Similarly, an algorithm for generating potential alternate spellings of a name has been used to find entities for comparison with similarly spelled names by computing word distance.
…
The hypothesis underlying our approach is that coreferent entities are strongly connected on a well-constructed graph.
Question: What if the nodes to which the coreferent entities are strongly connected are themselves ambiguous?