← Research

ABL: Alignment-Based Learning

Menno van Zaanen

This paper introduces a new type of grammar learning algorithm, inspired by string edit distance (Wagner and Fischer, 1974). The algorithm takes a corpus of flat sentences as input and returns a corpus of labelled, bracketed sentences. The method works on pairs of unstructured sentences that have one or more words in common. When two sentences are divided into parts that are the same in both sentences and parts that are different, this information is used to find parts that are interchangeable. These parts are taken as possible constituents of the same type. After this alignment learning step, the selection learning step selects the most probable constituents from all possible constituents. This method was used to bootstrap structure on the ATIS corpus (Marcus et al., 1993) and on the OVIS (Openbaar Vervoer Informatie Systeem (OVIS) stands for Public Transport Information System.) corpus (Bonnema et al., 1997). While the results are encouraging (we obtained up to 89.25 % non-crossing brackets precision), this paper will point out some of the shortcomings of our approach and will suggest possible solutions.

PDF ↗

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace