For developing a data-driven text rewriting algorithm for paraphrasing, it is essential to have a monolingual corpus of aligned paraphrased sentences. News ...

For developing a data-driven text rewriting algorithm for paraphrasing, it is essential to have a monolingual corpus of aligned paraphrased sentences. News ...

We compare two methods of aligning headlines to construct such an aligned corpus of paraphrases, one based on clustering, and the other on pair-wise similarity- ...

Clustering and matching headlines for automatic paraphrase acquisition ; English · The 12th European Workshop on Natural Language Generation · E. Krahmer, M.

We compare two methods of aligning headlines to construct such an aligned corpus of paraphrases, one based on clustering, and the other on pairwise similarity- ...

Clustering and Matching Headlines for Automatic Paraphrase Acquisition. Author. Wubben, Sander and Bosch, Antal and Krahmer, Emiel and Marsi, Erwin. Conference.

Sander Wubben, Antal van den Bosch, Emiel Krahmer, Erwin Marsi: Clustering and Matching Headlines for Automatic Paraphrase Acquisition. ENLG 2009: 122-125.

Clustering and Matching Headlines for Automatic Paraphrase Acquisition ... Generalizing Sub-sentential Paraphrase Acquisition across Original Signal Type ...

We use substring matching to compare two NEs. This is because several NEs ... connects two cluster (this means a wrong paraphrase) is not used. To ...

Clustering and matching headlines for automatic paraphrase acquisition. M. Bank et al. Fuzzification of agglomerative hierarchical crisp clustering algorithms.