Year: 2010
Type: conference-paper
Abstract: Unsupervised sense induction methods offer a solution to the\nproblem of scarcity of semantic resources. These methods\nautomatically extract semantic information from textual data\nand create resources adapted to specific applications and domains of interest. In this paper, we present a clustering algorithm for cross-lingual sense induction which generates\nbilingual semantic inventories from parallel corpora. We describe the clustering procedure and the obtained resources. We then proceed to a large-scale evaluation by integrating the resources into a Machine Translation (MT) metric (METEOR). We show that the use of the data-driven sense-cluster inventories leads to better correlation with human judgments of translation quality, compared to precision-based metrics, and to improvements similar to those obtained when a handcrafted semantic resource is used.
Authors: Apidianaki, Marianna, He, Yifan
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W935015117