Leveraging Multiple MT Engines for Paraphrase Generation
نویسندگان
چکیده
This paper proposes a method that leverages multiple machine translation (MT) engines for paraphrase generation (PG). The method includes two stages. Firstly, we use a multi-pivot approach to acquire a set of candidate paraphrases for a source sentence S. Then, we employ two kinds of techniques, namely the selection-based technique and the decoding-based technique, to produce a best paraphrase T for S using the candidates acquired in the first stage. Experimental results show that: (1) The multi-pivot approach is effective for obtaining plenty of valuable candidate paraphrases. (2) Both the selectionbased and decoding-based techniques can make good use of the candidates and produce high-quality paraphrases. Moreover, these two techniques are complementary. (3) The proposed method outperforms a state-of-the-art paraphrase generation approach.
منابع مشابه
Re-examining Machine Translation Metrics for Paraphrase Identification
We propose to re-examine the hypothesis that automated metrics developed for MT evaluation can prove useful for paraphrase identification in light of the significant work on the development of new MT metrics over the last 4 years. We show that a meta-classifier trained using nothing but recent MT metrics outperforms all previous paraphrase identification approaches on the Microsoft Research Par...
متن کاملLeveraging Crowdsourcing for Paraphrase Recognition
Crowdsourcing, while ideally reducing both costs and the need for domain experts, is no all-purpose tool. We review how paraphrase recognition has benefited from crowdsourcing in the past and identify two problems in paraphrase acquisition and semantic similarity evaluation that can be solved by employing a smart crowdsourcing strategy. First, we employ the CrowdFlower platform to conduct an ex...
متن کاملUsing Multiple Metrics in Automatically Building Turkish Paraphrase Corpus
Paraphrasing is expressing similar meanings with different words in different order. In this sense it is viewed as translation in the same language. It is an important issue in natural language processing for automatic machine translation, question answering, text summarization and language generation. Studies in paraphrasing can be classified as paraphrase extraction, paraphrase generation, pa...
متن کاملAutomatic generation of paraphrases to be used as translation references in objective evaluation measures of machine translation
We propose a method that automatically generates paraphrase sets from seed sentences to be used as reference sets in objective machine translation evaluation measures like BLEU and NIST. We measured the quality of the paraphrases produced in an experiment, i.e., (i) their grammaticality: at least 99% correct sentences; (ii) their equivalence in meaning: at least 96% correct paraphrases either b...
متن کاملAssessing Divergence Measures for Automated Document Routing in an Adaptive MT System
Custom machine translation (MT) engines systematically outperform general-domain MT engines when translating within the relevant custom domain. This paper investigates the use of the Jensen-Shannon divergence measure for automatically routing new documents within a translation system with multiple MT engines to the appropriate custom MT engine in order to obtain the best translation. Three dist...
متن کامل