An Approach to News Paraphrase Recognition Based on SRL Xiaofeng Wu, Chengqing Zong (National Lab of Pattern Recognition, Institute of Automation, CAS, Beijing 100190, China) Abstract: Paraphrase Recognition can be regarded as a sub-problem of Text Entailment Recognition. This problem is hard in that simply using term frequency or syntax information is prone to error judgment. For even the same...

We propose a method for acquiring plain lexical paraphrase using a Japanese dictionary in order to achieve lexical simplification for children. The proposed method extracts plain words that are the most similar to the headword from the dictionary definition. The definition statements describe the headword using plain words; therefore, paraphrasing by replacing the headword with the most similar...

ABSTARCT: Paraphrase is a process of computing the semantic similarity between sentences, which are not lexicographically similar. Though a number of metrics for English language have been proposed in literature, to quantify textual similarity; it addresses the problem for detection of monolingual text-text lexical similarity. Existing system for Indian Language paraphrase detection uses lexica...

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 ...

In this paper, we propose a novel neural approach for paraphrase generation. Conventional paraphrase generation methods either leverage hand-written rules and thesauri-based alignments, or use statistical machine learning principles. To the best of our knowledge, this work is the first to explore deep learning models for paraphrase generation. Our primary contribution is a stacked residual LSTM...

This paper describes the ParaPhrase project, a new 3-year targeted research project funded under EU Framework 7 Objective 3.4 (Computer Systems), starting in October 2011. ParaPhrase aims to follow a new approach to introducing parallelism using advanced refactoring techniques coupled with high-level parallel design patterns. The refactoring approach will use these design patterns to restructur...

Parameter set learned using all WMT12 data (Callison-Burch et al., 2012): • 100,000 binary rankings covering 8 language directions. •Restrict scoring for all languages to exact and paraphrase matching. Parameters encode human preferences that generalize across languages: •Prefer recall over precision. •Prefer word choice over word order. •Prefer correct translations of content words over functi...

In this paper, we study the problem of extracting technical paraphrases from a parallel software corpus, namely, a collection of duplicate bug reports. Paraphrase acquisition is a fundamental task in the emerging area of text mining for software engineering. Existing paraphrase extraction methods are not entirely suitable here due to the noisy nature of bug reports. We propose a number of techn...

ParaEval is an automated evaluation method for comparing reference and peer summaries. It facilitates a tieredcomparison strategy where recall-oriented global optimal and local greedy searches for paraphrase matching are enabled in the top tiers. We utilize a domainindependent paraphrase table extracted from a large bilingual parallel corpus using methods from Machine Translation (MT). We show ...