arXiv subjects

Menno van Zaanen

Publications and source records attributed to Menno van Zaanen.

3 recordsLinked to original sources

arXiv2001

Bootstrapping Structure using Similarity

In this paper a new similarity-based learning algorithm, inspired by string edit-distance (Wagner and Fischer, 1974), is applied to the problem of bootstrapping structure from scratch. The algorithm takes a corpus of unannotated sentences as input and returns a corpus of bracketed sentences. The method works on pairs of unstructured sentences or sentences partially bracketed by the algorithm that have one or more words in common. It finds parts of sentences that are interchangeable (i.e. the parts of the sentences that are different in both sentences). These parts are taken as possible constituents of the same type. While this corresponds to the basic bootstrapping step of the algorithm, further structure may be learned from comparison with other (similar) sentences. We used this method for bootstrapping structure from the flat sentences of the Penn Treebank ATIS corpus, and compared the resulting structured sentences to the structured sentences in the ATIS corpus. Similarly, the algorithm was tested on the OVIS corpus. We obtained 86.04 % non-crossing brackets precision on the ATIS corpus and 89.39 % non-crossing brackets precision on the OVIS corpus.

cs.LG↗

arXiv2001

ABL: Alignment-Based Learning

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.

cs.LG↗

arXiv2001

Bootstrapping Syntax and Recursion using Alignment-Based Learning

This paper introduces a new type of unsupervised learning algorithm, based on the alignment of sentences and Harris's (1951) notion of interchangeability. The algorithm is applied to an untagged, unstructured corpus of natural language sentences, resulting in a labelled, bracketed version of the corpus. Firstly, the algorithm aligns all sentences in the corpus in pairs, resulting in a partition of the sentences consisting of parts of the sentences that are similar in both sentences and parts that are dissimilar. This information is used to find (possibly overlapping) constituents. Next, the algorithm selects (non-overlapping) constituents. Several instances of the algorithm are applied to the ATIS corpus (Marcus et al., 1993) and the OVIS (Openbaar Vervoer Informatie Systeem (OVIS) stands for Public Transport Information System.) corpus (Bonnema et al., 1997). Apart from the promising numerical results, the most striking result is that even the simplest algorithm based on alignment learns recursion.

cs.LG↗