Researcher: An Experimental Intelligent Information System

The development of very powerful intelligent information systems requires the use of many techniques best derived by studying human understanding methods. RESEARCHER is a system that reads, remembers, generalizes from, and answers questions about complex technical texts, patent abstracts in particular. In this paper we discuss three current areas of research involving RESEARCHER the generalization of hierarchically structured representations; the use of long-term memory in text processing, specifically in resolving ambiguity; and the tailoring of answers to questions to the level of expertise of different users. 1 I n t r o d u c t i o n In [Lebowitz 83a] we described the first stages of development of RESEARCHER, a prototype intelligent information system. RESEARCHER is intended to accept natural language input, patent abstracts in particular, and 1) understand the text, 2) add the acquired information to a long term memory, generalizing as it docs so, and 3) answer questions from its memory. In this paper, we will present an overview of the new areas that we are using RESEARCHER to study. In each of these areas we apply techniques derived from cognitive modelling approaches to language and learning. We are using people as our model to help us achieve better performance on very hard tasks (which, in return, gives us insight into the human processing methods). 2 G e n e r a l i z i n g h i e r a r c h i e s The patent abstracts that we have been looking at describe the physical structure of complex objects. Since such objects are most naturally represented as hierarchies of parts, our learning research has addressed the generalization of hierarchically structured descriptions. EXl is part of a typical patent abstract. EX l P81; U. S. Patent #4306258; Higashiyama Nobor et al. A magnetic head supporting mechanism equipped with a magnetic head positioning carriage of a interchangeable double side type flexible disc drive apparatus comprising a carriage having a pair of arms which is rotated in detachable to a double side type flexible disc and arms ... *This research was supported in part by the Defense Advanced Research Projects Agency under contract N00039-84-C-0165 Many people have contributed to RESEARCHER. In particular, the work on generalizing hierarchies has largely been conducted by Kenneth Wasserman and the work on question answering by Cecile Paris, co-ad vised by Professor Kathleen McKeown. Our representation of patent abstracts such as this one includes three classes of information: 1) a parts hierarchy, that illustrates the components of each part; 2) intcrpart relations, physical and functional relations between various components; and 3) properties of the objects. We have concentrated on the parts hierarchy and physical relations [Wasserman and Lebowitz 83]. We are currently working on classification schemes for functional relations and object properties (such as size and composition). Full understanding requires that we integrate new representations with existing knowledge in memory. RESEARCHER has as one of its goals the incremental generalization of hierarchical descriptions of objects such as EXl by finding similar examples in memory, comparing them with the new example, and abstracting out the similarities. Generalizing hierarchical representations presents a number of difficult problems. Typical problems are: deciding how the components in the objects being compared correspond; dealing with differing levels of description of objects; and structuring memory so that maximally efficient inheritance of the sort used in semantic networks and frame systems (see [Barr et al. 82]) can be achieved automatically. In this paper, we will only give examples of how the generalization process works, and refer the reader to [Wasserman 85] for more details. We can break generalization into two phases — 1) when a new example is presented, deciding what other objects to compare it to (since RESEARCHER is not given examples designed to teach a specific concept), and 2) the comparison process itself, which abstracts out similarities. We will look at the comparison process first, as it is involved in the search process. EX2 and EX3 are two simplified disc drive patents. EX2 A disc drive comprising an enclosure surrounding the disc drive, said disc drive including a spinning assembly, a disc and a readwrite head, said spinning assembly including a spindle connected to a motor, said enclosure comprising a cover on top of a support member. EX3 A disc drive comprising an enclosure surrounding the disc drive, said disc drive including a spinning assembly, a magnetic assembly and a readwrite head, said spinning assembly including a spindle connected to a motor, said magnetic assembly comprising a disc, said enclosure comprising a cover on top of a support member. As human understanders, we can easily see that patents EX2 and EX3 describe similar objects. However, to begin