The MERGER operates at the end of each sentence in two steps: first all the raw templates that are found in a single sentence are merged to the extent possible, and then the remaining templates are merged with any templates from previous sentences.
There are two types of merge operations: full merges on templates of like types, and default merges on templates of different types. Full merges are like unification operations. The merger merges each slot of the two templates recursively, each time determining the best alignment for elements of a slot when the slots can contain multiple fills.
Default merges involve templates of different types. If it is possible for the template of one type to fill a slot, or merge with the slot contents of one of the slots in the other template, and certain other conditions are satisfied, then the merger is accomplished by filling in the appropriate slot. Default merging allows the combination of information from disparate parts of the text into a single tie-up schema. Default merges are allowed as long as the parts occur reasonably near each other in the text. We have found the best results with allowing default merges over a distance of two sentences.
In the walkthrough example, as previously mentioned, the entity for Bridgestone was merged with the joint venture company because of the appositive, and because the company name was incorrectly recognized. Then, the pattern recognizer recognizes the sequences ``BRIDGESTONE ... CAPITALIZED AT 20 MILLION NEW TAIWAN DOLLARS'' leading to an instantiation of a tie-up relationship with the joint venture company BRIDGESTONE, and an OWNERSHIP object giving the capitalization, and ``PRODUCTION OF 2000 IRON AND ``METAL WOOD'' CLUBS'' as an activity and industry with appropriate industry-type and product/service slot fills. The tie-up relationship combines in a full merge with the tie up relationship from the previous sentence, and since nearness constraints are satisfied, the activity object is attached to the tie-up relationship at this time.
The next sentence partially matches the passive-ownership pattern, however full recognition of the pattern was blocked by the failure to correctly recognize the company name ``UNION PRECISION CASTING CO.'' and the erroneous attachment of ``AND THE REMAINDER'' to the previous noun group as a conjunction. The result was a tie up relationship with an ownership template attributing 75% ownership to Bridgestone, which merged in a full merge with the previously found tie-up relationship and ownership. This example illustrates the crucial importance of recognizing company names in this domain. If the company names had been correctly recognized here, the system's output would have been nearly perfect. As a direct result of name recognition failure, compounded errors led to a much less satisfactory result.
Finally, spurious activity and industry templates are produced from the next sentence, which recognizes ``PRODUCTION OF GOLF CLUB PARTS'' and attaches it to the tie-up relationship in a default merge, because nearness constraints are satisfied.