Skip to Main content Skip to Navigation
Conference papers

An algorithm for cross-lingual sense-clustering tested in a MT evaluation setting

Abstract : Unsupervised sense induction methods offer a solution to the problem of scarcity of semantic resources. These methods automatically extract semantic information from textual data and 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 bilingual 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 hand-crafted semantic resource is used.
Complete list of metadatas

Cited literature [28 references]  Display  Hide  Download
Contributor : Marianna Apidianaki <>
Submitted on : Wednesday, December 8, 2010 - 7:17:38 PM
Last modification on : Saturday, March 28, 2020 - 2:08:02 AM
Document(s) archivé(s) le : Thursday, March 10, 2011 - 12:56:41 PM


Files produced by the author(s)


  • HAL Id : hal-00544745, version 1



Marianna Apidianaki, Yifan He. An algorithm for cross-lingual sense-clustering tested in a MT evaluation setting. International Workshop on Spoken Language Translation (IWSLT-2010), Dec 2010, Paris, France. pp.219--226. ⟨hal-00544745⟩



Record views


Files downloads