In recent years, there has been a resurgence in research on empirical methods in natural language processing. These methods employ learning techniques to automatically extract linguistic knowledge from natural language corpora rather than require the system developer to manually encode the requisite knowledge. The current special issue reviews recent research in empirical methods in speech recognition, syntactic parsing, semantic processing, information extraction, and machine translation. This article presents an introduction to the series of specialized articles on these topics and attempts to describe and explain the growing interest in using learning methods to aid the development of natural language processing systems.

Gary Kasparov in the final game of of Technology Computer Science Computer Chess, created in a tied, six-game match last May 11. Soon thereafter, the team moved to IBM, where they have been ever since, working under wraps on Deep Blue. The $100,000 third tier of the prize was awarded at AAAI-97 to this IBM team, who built the first computer chess machine that beat a world chess champion. The members of the Deep Blue team were also honored for their achievement with the Allen Newell Research Excellence Medal, sponsored by Carnegie Mellon University. Allen Newell Medals were presented to each of the major researchers in the field whose earlier contributions ultimately led to the success of Deep Blue.

One of the best things about conferences, as we all know, is the opportunity they afford to consolidate old friendships and make new contacts. Clusters of con-versation provide a more valuable way to spend ones time than attending sessions. At the last national meeting we escaped from the celebrations of the recent victory of Deep Blue over the dreaded Kasparov, to find just such a group, already engaged in an animated discussion ....

The assessment of bidirectional heuristic search has been incorrect since it was first published more than a quarter of a century ago. For quite a long time, this search strategy did not achieve the expected results, and there was a major misunderstanding about the reasons behind it. Although there is still wide-spread belief that bidirectional heuristic search is afflicted by the problem of search frontiers passing each other, we demonstrate that this conjecture is wrong. Based on this finding, we present both a new generic approach to bidirectional heuristic search and a new approach to dynamically improving heuristic values that is feasible in bidirectional search only. These approaches are put into perspective with both the traditional and more recently proposed approaches in order to facilitate a better overall understanding. Empirical results of experiments with our new approaches show that bidirectional heuristic search can be performed very efficiently and also with limited memory. These results suggest that bidirectional heuristic search appears to be better for solving certain difficult problems than corresponding unidirectional search. This provides some evidence for the usefulness of a search strategy that was long neglected. In summary, we show that bidirectional heuristic search is viable and consequently propose that it be reconsidered.

Local search algorithms for combinatorial search problems frequently encounter a sequence of states in which it is impossible to improve the value of the objective function; moves through these regions, called plateau moves, dominate the time spent in local search. We analyze and characterize plateaus for three different classes of randomly generated Boolean Satisfiability problems. We identify several interesting features of plateaus that impact the performance of local search algorithms. We show that local minima tend to be small but occasionally may be very large. We also show that local minima can be escaped without unsatisfying a large number of clauses, but that systematically searching for an escape route may be computationally expensive if the local minimum is large. We show that plateaus with exits, called benches, tend to be much larger than minima, and that some benches have very few exit states which local search can use to escape. We show that the solutions (i.e., global minima) of randomly generated problem instances form clusters, which behave similarly to local minima. We revisit several enhancements of local search algorithms and explain their performance in light of our results. Finally we discuss strategies for creating the next generation of local search algorithms.

Partially observable Markov decision processes (POMDPs) are a natural model for planning problems where effects of actions are nondeterministic and the state of the world is not completely observable. It is difficult to solve POMDPs exactly. This paper proposes a new approximation scheme. The basic idea is to transform a POMDP into another one where additional information is provided by an oracle. The oracle informs the planning agent that the current state of the world is in a certain region. The transformed POMDP is consequently said to be region observable. It is easier to solve than the original POMDP. We propose to solve the transformed POMDP and use its optimal policy to construct an approximate policy for the original POMDP. By controlling the amount of additional information that the oracle provides, it is possible to find a proper tradeoff between computational time and approximation quality. In terms of algorithmic contributions, we study in details how to exploit region observability in solving the transformed POMDP. To facilitate the study, we also propose a new exact algorithm for general POMDPs. The algorithm is conceptually simple and yet is significantly more efficient than all previous exact algorithms.

The model of a non-Bayesian agent who faces a repeated game with incomplete information against Nature is an appropriate tool for modeling general agent-environment interactions. In such a model the environment state (controlled by Nature) may change arbitrarily, and the feedback/reward function is initially unknown. The agent is not Bayesian, that is he does not form a prior probability neither on the state selection strategy of Nature, nor on his reward function. A policy for the agent is a function which assigns an action to every history of observations and actions. Two basic feedback structures are considered. In one of them -- the perfect monitoring case -- the agent is able to observe the previous environment state as part of his feedback, while in the other -- the imperfect monitoring case -- all that is available to the agent is the reward obtained. Both of these settings refer to partially observable processes, where the current environment state is unknown. Our main result refers to the competitive ratio criterion in the perfect monitoring case. We prove the existence of an efficient stochastic policy that ensures that the competitive ratio is obtained at almost all stages with an arbitrarily high probability, where efficiency is measured in terms of rate of convergence. It is further shown that such an optimal policy does not exist in the imperfect monitoring case. Moreover, it is proved that in the perfect monitoring case there does not exist a deterministic policy that satisfies our long run optimality criterion. In addition, we discuss the maxmin criterion and prove that a deterministic efficient optimal strategy does exist in the imperfect monitoring case under this criterion. Finally we show that our approach to long-run optimality can be viewed as qualitative, which distinguishes it from previous work in this area.

Case-Based Planning (CBP) provides a way of scaling up domain-independent planning to solve large problems in complex domains. It replaces the detailed and lengthy search for a solution with the retrieval and adaptation of previous planning experiences. In general, CBP has been demonstrated to improve performance over generative (from-scratch) planning. However, the performance improvements it provides are dependent on adequate judgements as to problem similarity. In particular, although CBP may substantially reduce planning effort overall, it is subject to a mis-retrieval problem. The success of CBP depends on these retrieval errors being relatively rare. This paper describes the design and implementation of a replay framework for the case-based planner DERSNLP+EBL. DERSNLP+EBL extends current CBP methodology by incorporating explanation-based learning techniques that allow it to explain and learn from the retrieval failures it encounters. These techniques are used to refine judgements about case similarity in response to feedback when a wrong decision has been made. The same failure analysis is used in building the case library, through the addition of repairing cases. Large problems are split and stored as single goal subproblems. Multi-goal problems are stored only when these smaller cases fail to be merged into a full solution. An empirical evaluation of this approach demonstrates the advantage of learning from experienced retrieval failure.

There is a great dispute among researchers about the roles, characteristics, and specifications of what are called agents, intelligent agents, and adaptive agents. Most research in the field focuses on methodologies for solving specific problems (for example, communications, cooperation, architectures), and little work has been accomplished to highlight and distinguish the field of intelligent agents. As a result, more and more research is cataloged as research on intelligent agents. The Workshop on Intelligent Adaptive Agents, presented as part of the Thirteenth National Conference on Artificial Intelligence, addressed these issues as well as many others that are presented in this article.

The Association for the Advancement of Artificial Intelligence (AAAI) held its 1997 Spring Symposium Series on 24 to 26 March at Stanford University in Stanford, California. This article contains summaries of the seven symposia that were conducted: (1) Artificial Intelligence in Knowledge Management; (2) Computational Models for Mixed-Initiative Interaction; (3) Cross-Language Text and Speech Retrieval; (4) Intelligent Integration and Use of Text, Image, Video, and Audio Corpora; (5) Natural Language Processing for the World Wide Web; (6) Ontological Engineering; and (7) Qualitative Preferences in Deliberation and Practical Reasoning.