Joint Learning of a Dual SMT System for Paraphrase Generation
نویسندگان
چکیده
SMT has been used in paraphrase generation by translating a source sentence into another (pivot) language and then back into the source. The resulting sentences can be used as candidate paraphrases of the source sentence. Existing work that uses two independently trained SMT systems cannot directly optimize the paraphrase results. Paraphrase criteria especially the paraphrase rate is not able to be ensured in that way. In this paper, we propose a joint learning method of two SMT systems to optimize the process of paraphrase generation. In addition, a revised BLEU score (called iBLEU ) which measures the adequacy and diversity of the generated paraphrase sentence is proposed for tuning parameters in SMT systems. Our experiments on NIST 2008 testing data with automatic evaluation as well as human judgments suggest that the proposed method is able to enhance the paraphrase quality by adjusting between semantic equivalency and surface dissimilarity.
منابع مشابه
The Circle of Meaning: from Translation to Paraphrasing and Back
Title of dissertation: THE CIRCLE OF MEANING: FROM TRANSLATION TO PARAPHRASING AND BACK Nitin Madnani, Doctor of Philosophy, 2010 Dissertation directed by: Professor Bonnie Dorr Department of Computer Science The preservation of meaning between inputs and outputs is perhaps the most ambitious and, often, the most elusive goal of systems that attempt to process natural language. Nowhere is this ...
متن کاملEnriching SMT Training Data via Paraphrasing
This paper proposes a novel method to resolve the coverage problem of SMT system. The method generates paraphrases for source-side sentences of the bilingual parallel data, which are then paired with the target-side sentences to generate new parallel data. Within a statistical paraphrase generation framework, we employ an object function, named Sentence Novelty, to select paraphrases which havi...
متن کاملCombining Multiple Resources to Improve SMT-based Paraphrasing Model
This paper proposes a novel method that exploits multiple resources to improve statistical machine translation (SMT) based paraphrasing. In detail, a phrasal paraphrase table and a feature function are derived from each resource, which are then combined in a log-linear SMTmodel for sentence-level paraphrase generation. Experimental results show that the SMT-based paraphrasing model can be enhan...
متن کاملMonolingual Machine Translation for Paraphrase Generation
We apply statistical machine translation (SMT) tools to generate novel paraphrases of input sentences in the same language. The system is trained on large volumes of sentence pairs automatically extracted from clustered news articles available on the World Wide Web. Alignment Error Rate (AER) is measured to gauge the quality of the resulting corpus. A monotone phrasal decoder generates contextu...
متن کاملFine-Grained Linguistic Soft Constraints on Statistical Natural Language Processing Models
Title of dissertation: Fine-Grained Linguistic Soft Constraints on Statistical Natural Language Processing Models Yuval Marton, Doctor of Philosophy, 2009 Dissertation directed by: Professor Philip Resnik, Department of Linguistics and Institute for Advanced Computer Studies This dissertation focuses on effective combination of data-driven natural language processing (NLP) approaches with lingu...
متن کامل