Interactive learning of node selecting tree transducer

Abstract

We develop new algorithms for learning monadic node selection queries in unranked trees from annotated examples, and apply them to visually interactive Web information extraction.We propose to represent monadic queries by bottom-up deterministic Node Selecting Tree Transducers (NSTTs), a particular class of tree automata that we introduce. We prove that deterministic NSTTs capture the class of queries definable in monadic second order logic (MSO) in trees, which Gottlob and Koch (2002) argue to have the right expressiveness for Web information extraction, and prove that monadic queries defined by NSTTs can be answered efficiently. We present a new polynomial time algorithm in RPNI-style that learns monadic queries defined by deterministic NSTTs from completely annotated examples, where all selected nodes are distinguished.In practice, users prefer to provide partial annotations. We propose to account for partial annotations by intelligent tree pruning heuristics. We introduce pruning NSTTs -a formalism that shares many advantages of NSTTs. This leads us to an interactive learning algorithm for monadic queries defined by pruning NSTTs, which satisfies a new formal active learning model in the style of Angluin (1987).We have implemented our interactive learning algorithm integrated it into a visually interactive Web information extraction system-called SQUIRREL-by plugging it into the Mozilla Web browser. Experiments on realistic Web documents confirm excellent quality with very few user interactions during wrapper induction.

Schema-Guided Induction of Monadic Queries

“…The reason for ignoring schema information may be that it cannot be integrated into most approaches. Tree automata based techniques for the inference of regular tree languages are the exception [4,15], as we show in this article, but it requires considerable effort. Automata for local tree languages are not sufficient [19,13].…”

“…These range from classification [11,12,16], conditional random fields [14], inductive logic programming [7], to tree automata induction [19,13,4,15].…”

“…In this article, we introduce schema guidance into the learning algorithm for monadic queries represented by pruning node selecting tree transducers (pNSTTs) presented in [4]. These are tree automata that recognize monadic queries represented as tree languages.…”

“…An algorithm for testing functionality and an RPNI algorithm for learning NSTTs from completely annotated examples have been presented in [4].…”

Learning Rational Functions

“…For various classes of automata, this can be done in polynomial time in the size of the sample, while there exist characteristic samples of polynomial cardinality in the size of the target automaton. This approach has been established for finite deterministic automata (Dfas) [12,16], for deterministic tree automata [17], and for deterministic stepwise tree automata for unranked trees [3].…”