Author name cluster

David Pierce

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

4 papers

2 author rows

AAAI Conference 1999 Conference Paper

The Role of Lexicalization and Pruning for Base Noun Phrase Grammars

Claire Cardie
David Pierce
Cornell University

This paper explores the role of lexicalization and pruning of grammars for base noun phrase identification. We modify our original framework (Cardie & Pierce 1998) to extract lexicalized treebank grammars that assign a score to each potential noun phrase based upon both the part-of-speech tag sequence and the word sequence of the phrase. We evaluate the modified framework on the “simple” and “complex” base NP corpora of the original study. As expected, we find that lexicalization dramatically improves the performance of the unpruned treebank grammars; however, for the simple base noun phrase data set, the lexicalized grammar performs below the corresponding unlexicalized but pruned grammar, suggesting that lexicalization is not critical for recognizing very simple, relatively unambiguous constituents. Somewhat surprisingly, we also find that error-driven pruning improves the performance of the probabilistic, lexicalized base noun phrase grammars by up to 1. 0% recall and 0. 4% precision, and does so even using the original pruning strategy that fails to distinguish the effects of lexicalization. This result may have implications for many probabilistic grammar-based approaches to problems in natural language processing: error-driven pruning is a remarkably robust method for improving the performance of probabilistic and non-probabilistic grammars alike.

PDF Details

AIJ Journal 1997 Journal Article

Map learning with uninterpreted sensors and effectors

David Pierce
Benjamin J. Kuipers

This paper presents a set of methods by which a learning agent can learn a sequence of increasingly abstract and powerful interfaces to control a robot whose sensorimotor apparatus and environment are initially unknown. The result of the learning is a rich hierarchical model of the robot's world (its sensorimotor apparatus and environment). The learning methods rely on generic properties of the robot's world such as almost-everywhere smooth effects of motor control signals on sensory features. At the lowest level of the hierarchy, the learning agent analyzes the effects of its motor control signals in order to define a new set of control signals, one for each of the robot's degrees of freedom. It uses a generate-and-test approach to define sensory features that capture important aspects of the environment. It uses linear regression to learn models that characterize context-dependent effects of the control signals on the learned features. It uses these models to define high-level control laws for finding and following paths defined using constraints on the learned features. The agent abstracts these control laws, which interact with the continuous environment, to a finite set of actions that implement discrete state transitions. At this point, the agent has abstracted the robot's continuous world to a finite-state world and can use existing methods to learn its structure. The learning agent's methods are evaluated on several simulated robots with different sensorimotor systems and environments.

Details DOI

AAAI Conference 1994 Conference Paper

Learning to Explore and Build Maps

David Pierce

Using the methods demonstrated in this paper, a robot with an unknown sensorimotor system can learn sets of features and behaviors adequate to explore a continuous environment and abstract it to a finitestate automaton. The structure of this automaton can then be learned from experience, and constitutes a cognitive map of the environment. A generate-andtest method is used to define a hierarchy of features defined on the raw sense vector culminating in a set of continuously differentiable local state variu bles. Control laws based on these local state variables are defined for robustly following paths that implement repeatable state transitions. These state transitions are the basis for a finite-state automaton, a discrete abstraction of the robot’ s continuous world. A variety of existing methods can learn the structure of the automaton defined by the resulting states and transitions. A simple example of the performance of our implemented system is presented.

PDF Details

ICRA Conference 1991 Conference Paper

Learning turn and travel actions with an uninterpreted sensorimotor apparatus

David Pierce

A learning method by which a mobile robot may analyze an initially uninterpreted sensorimotor apparatus and produce a useful characterization of its set of actions is demonstrated. By initially uninterpreted it is meant that the robot is given no knowledge of the structure of its sensory system nor of the effects of its actions. It merely sees and produces vectors of real numbers. The method is applied to the case of a simulated robot with an array of 16 range finders, and a motor apparatus with which it can make combinations of turning and advancing actions. The robot learns a set of primitive actions allowing it to make pure turns (both clockwise and counterclockwise) and pure travels. It is believed that this approach is robust and will apply to sensory systems used for motion detection, such as arrays of photoreceptors or range finders. >

Details