Cascaded Grammatical Relation Assignment
Sabine Buchholz, Jorn Veenstra, Walter Daelemans

TL;DR
This paper presents a cascaded memory-based approach for grammatical relation assignment, where chunking and relation labeling are performed in stages, showing that additional levels improve overall performance.
Contribution
It introduces a multi-level cascaded classifier for grammatical relations, demonstrating that even less accurate chunkers can enhance relation assignment.
Findings
Adding multiple levels improves relation assignment accuracy
Chunking with adverbial function labeling enhances relation detection
Even less performing chunkers contribute positively to the cascade
Abstract
In this paper we discuss cascaded Memory-Based grammatical relations assignment. In the first stages of the cascade, we find chunks of several types (NP,VP,ADJP,ADVP,PP) and label them with their adverbial function (e.g. local, temporal). In the last stage, we assign grammatical relations to pairs of chunks. We studied the effect of adding several levels to this cascaded classifier and we found that even the less performing chunkers enhanced the performance of the relation finder.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsNatural Language Processing Techniques · Topic Modeling · Semantic Web and Ontologies
