Extracting structural paraphrases from aligned monolingual corpora

Abstract

We present an approach for automatically learning paraphrases from aligned monolingual corpora. Our algorithm works by generalizing the syntactic paths between corresponding anchors in aligned sentence pairs. Compared to previous work, structural paraphrases generated by our algorithm tend to be much longer on average, and are capable of capturing long-distance dependencies. In addition to a standalone evaluation of our paraphrases, we also describe a question answering application currently under development that could immensely benefit from automatically-learned structural paraphrases.

Sentence-Alignment and Application of Russian-German Multi-Target Parallel Corpora for Linguistic Analysis and Literary Studies

“…Other works (Barzilay and Lee, 2003;Barzilay and McKeown, 2001;Pang et al, 2003;Ibrahim et al, 2003) have examined the use of monolingual parallel corpora for paraphrase extraction based on statistical methods. For this purpose, parallel corpora already exist, e.g.…”

Paraphrastic Reformulations in Spoken Corpora

“…Exploitation of such corpora becomes possible thanks to the methods for word alignment. Various approached are proposed for processing this kind of corpora [25][26][27]; 3. Monolingual comparable corpora.…”

Turkish synonym identification from multiple resources: monolingual corpus, mono/bilingual online dictionaries, and WordNet

“…There have been many studies [5,10,11] that used distributional similarity in the automatic extraction of semantically related words from large corpora. Distributional approaches are applied to monolingual corpora [5,12], monolingual parallel corpora [13,14], bilingual corpora [13,15], multilingual parallel corpora [16], monolingual dictionaries [17,18], and bilingual dictionaries [19]. Some of the studies [20][21][22][23][24] relied on multiple-choice synonym questions such as those of the Scholastic Aptitude Test (SAT) or the Test of English as a Foreign Language (TOEFL).…”