The source text provided to a machine translation system is typically only one of many ways the input sentence could have been expressed, and alternative forms of expression can often produce a better translation. We introduce here error driven paraphrasing of source sentences: instead of paraphrasing a source sentence exhaustively, we obtain paraphrases for only the parts that are predicted to...

This paper describes a method for checking the acceptability of paraphrases in context. We use the Google n-gram data and a CCG parser to certify the paraphrasing grammaticality and fluency. We collect a corpus of human judgements to evaluate our system. The ultimate goal of our work is to integrate text paraphrasing into a Linguistic Steganography system, by using paraphrases to hide informati...

This paper examines the effect of paraphrasing noun-noun compounds in statistical machine translation from Swedish to English. The paraphrases are meant to elicit the underlying relationship that holds between the compounding nouns, with the use of prepositional and verb phrases. Though some types of noun-noun compounds are too lexicalized, or have some other qualities that make them unsuitable...

Mismatch between queries and documents is a key issue for the web search task. In order to narrow down such mismatch, in this paper, we present an in-depth investigation on adapting a paraphrasing technique to web search from three aspects: a search-oriented paraphrasing model; an NDCG-based parameter optimization algorithm; an enhanced ranking model leveraging augmented features computed on pa...

This paper studies the impact of paraphrases on the accuracy of automatic evaluation. Given a reference sentence and a machine-generated sentence, we seek to find a paraphrase of the reference sentence that is closer in wording to the machine output than the original reference. We apply our paraphrasing method in the context of machine translation evaluation. Our experiments show that the use o...

Semantic distance measures aim to answer questions such as: How close in meaning are words A and B? Fore example: "couch" and "sofa"? (very); "wave" and "ripple"? (soso); "wave" and "bank"? (far). Distributional measures do that by modeling which words occur next to A and next to B in large corpora of text, and then comparing these models of A and B (based on the "Distributional Hypothesis"). P...

Lexical and syntactic mismatches between languages are the main challenge for every translation (especially formidable for Machine Translation; see Mel’čuk & Wanner 2001, 2006). An example of mismatches in English-to-Russian translation: a. The demonstrators were brutally beaten and tear-gassed by the police. b. Rus. Demonstranty podverglis ́ zverskomu izbieniju so storony policii; protiv nix by...

Abstract Automatic paraphrase generation is an essential task of natural language processing. However, due to the scarcity corpus in many languages, Chinese, for example, generating high-quality paraphrases these languages still challenging. Especially domain paraphrasing, it even more difficult obtain in-domain sentence pairs. In this paper, we propose a novel approach domain-specific zero-sho...