We present MULTIP (Multi-instance Learning Paraphrase Model), a new model suited to identify paraphrases within the short messages on Twitter. We jointly model paraphrase relations between word and sentence pairs and assume only sentence-level annotations during learning. Using this principled latent variable model alone, we achieve the performance competitive with a state-of-the-art method whi...

Treebanks are key resources for developing accurate statistical parsers. However, building treebanks is expensive and timeconsuming for humans. For domains requiring deep subject matter expertise such as law and medicine, treebanking is even more difficult. To reduce annotation costs for these domains, we develop methods to improve cross-domain parsing inference using paraphrases. Paraphrases a...

We explore the effect of using Arabic semantic equivalents in an example-based Arabic-English translation system. We describe two experiments using single-word equivalents in translation as test cases for broadening the level of similarity and using multi-word Arabic paraphrases in the future. In the first experiment, we use synonymous Arabic nouns, derived from a lexicon, to help locate potent...

Aiming to create verb paraphrases to lay the foundation of sentence paraphrases I automatically created Hungarian semantic verb classes with k-means algorithm. The vector representation of verbs was special: dimensions were cases and values were sets of lemmas that can fill the verb frame position defined by the case. I clustered 900 frequent verbs, from which 243 got into 71 smaller clusters, ...

Paraphrases and other semantically related sentences present a challenge to NLP and IR applications such as multi-document sum-marization and question answering systems. While it is generally agreed that paraphrases contain approximately equivalent ideas, they often diier from one another in subtle, yet non-trivial, ways. In this paper, we examine semantic diierences in cases of paraphrase and ...

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...