In this paper we investigate the automatic collection, generation and evaluation of sentential paraphrases. Valuable sources of paraphrases are news article headlines; they tend to describe the same event in various different ways, and can easily be obtained from the web. We describe a method for generating paraphrases by using a large aligned monolingual corpus of news headlines acquired autom...

We present the 1.0 release of our paraphrase database, PPDB. Its English portion, PPDB:Eng, contains over 220 million paraphrase pairs, consisting of 73 million phrasal and 8 million lexical paraphrases, as well as 140 million paraphrase patterns, which capture many meaning-preserving syntactic transformations. The paraphrases are extracted from bilingual parallel corpora totaling over 100 mill...

In this paper, we present a novel way of tackling the monolingual alignment problem on pairs of sentential paraphrases by means of edit rate computation. In order to inform the edit rate, information in the form of subsentential paraphrases is provided by a range of techniques built for different purposes. We show that the tunable TER-PLUS metric from Machine Translation evaluation can achieve ...

Conversational services are emerging as a new paradigm for accessing information by simply uttering questions in natural language, posing whole set of challenges to the design and engineering systems. Training conversational deal with nuances language often requires collecting high-quality diverse training samples (i.e., paraphrases). Traditional approaches such hiring an expert or crowdsourcin...

1 Two sentences are paraphrases if their meanings are equivalent but their words and syntax are different. Paraphrasing can be used to aid comprehension, stimulate prior knowledge, and assist in writing skills development. While automated paraphrase assessment is both common-place and useful, research has centered solely on artificial, edited paraphrases and has used only binary dimensions (i.e...

Two kinds of paraphrases extracted from a bilingual parallel corpus were analyzed. One is from an adjectival predicate sentence to a non-adjectival one. The other is from a passive form to a non-passive form. The ability to extract paraphrases is strongly desired for paraphrasing studies. Although extracting paraphrases from multi-lingual parallel corpora is possible, the type of paraphrases ex...

This paper presents a paraphrase acquisition method that uncovers and exploits generalities underlying paraphrases: paraphrase patterns are first induced and then used to collect novel instances. Unlike existing methods, ours uses both bilingual parallel and monolingual corpora. While the former are regarded as a source of high-quality seed paraphrases, the latter are searched for paraphrases t...

We present the first fully unsupervised approach to metaphor interpretation, and a system that produces literal paraphrases for metaphorical expressions. Such a form of interpretation is directly transferable to other NLP applications that can benefit from a metaphor processing component. Our method is different from previous work in that it does not rely on any manually annotated data or lexic...

The paper addressed the question how the paraphrasing of synonyms can be linked with a fine-gained ontology based data representation. Our challenge is to identify for a set of synonyms (including terms and multiword expressions) the best lexical paraphrases suitable for given contexts. Our hypothesis is that: i. the minimal context in which the paraphrasing can be validated is different for di...