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...

We present a substitution-only approach to sentence compression which “tightens” a sentence by reducing its character length. Replacing phrases with shorter paraphrases yields paraphrastic compressions as short as 60% of the original length. In support of this task, we introduce a novel technique for re-ranking paraphrases extracted from bilingual corpora. At high compression rates1 paraphrasti...

To what extent are the processing patterns for nouns and verbs universal across languages? Under conditions of semantic strain, English speakers tend to adapt the meaning of the verb to fit the noun in the sentence. We asked Japanese and English speakers to paraphrase simple sentences of the form “The noun verbed,” varying in semantic strain (e.g., “The blender talked”). We then assessed the de...

This study presents a method to automatically acquire paraphrases using bilingual corpora, which utilizes the bilingual dependency relations obtained by projecting a monolingual dependency parse onto the other language sentence based on statistical alignment techniques. Since the paraphrasing method is capable of clearly disambiguating the sense of an original phrase using the bilingual context...

We present a framework for the acquisition of sentential paraphrases based on crowdsourcing. The proposed method maximizes the lexical divergence between an original sentence s and its valid paraphrases by running a sequence of paraphrasing jobs carried out by a crowd of non-expert workers. Instead of collecting direct paraphrases of s, at each step of the sequence workers manipulate semantical...

We present a method of creating disjunctive logical forms (DLFs) from aligned sentences for grammar-based paraphrase generation using the OpenCCG broad coverage surface realizer. The method takes as input word-level alignments of two sentences that are paraphrases and projects these alignments onto the logical forms that result from automatically parsing these sentences. The projected alignment...

This paper presents a lightweight method for unsupervised extraction of paraphrases from arbitrary textual Web documents. The method differs from previous approaches to paraphrase acquisition in that 1) it removes the assumptions on the quality of the input data, by using inherently noisy, unreliable Web documents rather than clean, trustworthy, properly formatted documents; and 2) it does not ...

Paraphrases, which stem from the variety of lexical and grammatical means of expressing meaning available in a language, pose challenges for a sentence generation system. In this paper, we discuss the generation of paraphrases from predicate/argument structure using a simple, uniform generation methodology. Central to our approach are lexico-grammatical resources which pair elementary semantic ...

Automatic generation of paraphrases for a given sentence is an important yet challenging task in natural language processing (NLP), and plays a key role in a number of applications such as question answering, information retrieval and dialogue. In this paper we present a deep reinforcement learning approach to paraphrase generation. Specifically, we propose a new model for the task, which consi...