We explored what kind of information is acquired when amnesic patients are able to exhibit significant retention on tests of cued recall and recognition memory. Amnesic patients and control subjects attempted to learn sets of sentences. Memory for the last word in each sentence was tested after 1 hr in the case of the amnesic patients, or after 1 to 2 weeks in the case of (delayed) control subj...

In this paper on-going work of creating an extensive multilingual parallel corpus of movie subtitles is presented. The corpus currently contains roughly 23,000 pairs of aligned subtitles covering about 2,700 movies in 29 languages. Subtitles mainly consist of transcribed speech, sometimes in a very condensed way. Insertions, deletions and paraphrases are very frequent which makes them a challen...

in this paper we present a new dimension to paraphrasing text in which characteristics of the original text motivate strategies for effective pacaphrasing. Our system combines two existing robust components: the IRIJS-.II natural language underst~mding system and the SPOKESMAN generation system. We describe the architectur(: of the system and enhancements made to these components to facilitate ...

Studies on paraphrasing are important with respect to various research topics such as sentence generation, summarization, and question-answering. We consider the automatic extraction of synonyms (which are a kind of paraphrase) through the matching of word definitions from two dictionaries, and describe a new method for extracting paraphrases. Higher precision was obtained than with a conventio...

Parallel corpora are made by human beings. However, as an MT system is an aggregation of state-of-the-art NLP technologies without any intervention of human beings, it is unavoidable that quite a few sentence pairs are beyond its analysis and that will therefore not contribute to the system. Furthermore, they in turn may act against our objectives to make the overall performance worse. Possible...

In this paper, we present a nearly unsupervised learning methodology for automatically extracting paraphrases from the Web. Starting with one single linguistic expression of a semantic relationship, our learning algorithm repeatedly samples the Web, in order to build a corpus of potential new examples of the same relationship. Sampling steps alternate with validation steps, during which implaus...

PLANDoc, a system under joint development by Columbia and Bellcore, documents the activity of planning engineers as they study telephone routes. It takes as input a trace of the engineer’s interaction with a network planning tool and produces 1-2 page summary. In this paper, we describe the user needs analysis we performed and how it influenced the development of PLANDoc. In particular, we show...

This paper proposes an empirical approach to the development of a computational model for assessing texts according to cohesiveness. We argue that the NLG technologies for the generation of structural paraphrases can be used to efficiently create what we call a cohesion-variant parallel corpus, which would serve as a good resource for empirical acquisition of cohesiveness criteria. We also pres...

Parallel corpora are crucial for training SMT systems. However, for many language pairs they are available only in very limited quantities. For these language pairs a huge portion of phrases encountered at run-time will be unknown. We show how techniques from paraphrasing can be used to deal with these otherwise unknown source language phrases. Our results show that augmenting a stateof-the-art...

We propose a minimally supervised method for multilingual paraphrase extraction from definition sentences on the Web. Hashimoto et al. (2011) extracted paraphrases from Japanese definition sentences on the Web, assuming that definition sentences defining the same concept tend to contain paraphrases. However, their method requires manually annotated data and is language dependent. We extend thei...