This paper discusses how to automatically generate slide shows. The reported presentation system inputs documents annotated with the GDA tagset, an XML tagset which allows machines to automatically infer the semantic structure underlying the raw documents. The system picks up important topics in the input document on the basis of the semantic dependencies and coreferences identified from the ta...

We propose a thesaurus of predicates that can help to resolve pre-editing and/or post-editing problems in machine translation environments. It differs from earlier approaches such as conventional dictionaries in that we are aiming to link a wide range of near-synonyms and paraphrases. We are compiling such similar examples through both introspection and the use of translation data, giving us a ...

Question paraphrasing is critical in many Natural Language Processing (NLP) applications, especially for question reformulation in question answering (QA). However, choosing an appropriate data source and developing effective methods are challenging tasks. In this paper, we propose a method that exploits Encarta logs to automatically identify question paraphrases and extract templates. Question...

We developed a method for automatically distinguishing the machine-translatable and non-machine-translatable parts of a given sentence for a particular machine translation (MT) system. They can be distinguished by calculating the similarity between a source-language sentence and its back translation for each part of the sentence. The parts with low similarities are highly likely to be non-machi...

This paper describes a nealy unsupervised learning method for converting or paraphrasing Japanese noun phrases to verb phrases without changing their semantic contents. We focus on the paraphrasing of the noun phrases in the form of “A no B” where “A” and “B” are noun phrases and “no” is a postposition. Noun phrases in this form can express various relationships between “A” and “B.” In the past...

We present a method that paraphrases a given sentence by first generating candidate paraphrases and then ranking (or classifying) them. The candidates are generated by applying existing paraphrasing rules extracted from parallel corpora. The ranking component considers not only the overall quality of the rules that produced each candidate, but also the extent to which they preserve grammaticali...

Paraphrasing methods recognize, generate, or extract phrases, sentences, or longer natural language expressions that convey almost the same information. Textual entailment methods, on the other hand, recognize, generate, or extract pairs of natural language expressions, such that a human who reads (and trusts) the first element of a pair would most likely infer that the other element is also tr...

We discuss a previously proposed method for augmenting parallel corpora of limited size for the purposes of machine translation through monolingual paraphrasing of the source language. We develop a three-stage shallow paraphrasing procedure to be applied to the Swedish-Bulgarian language pair for which limited parallel resources exist. The source language exhibits specifics not typical of high-...

Existing paraphrase systems either create successive drafts from an underlying representation , or they aim to correct texts. A diierent kind of paraphrase, also reeecting a real-world task, involves imposing, on an original text, external constraints in terms of length, read-ability, etc. This sort of paraphrase requires a new framework which allows production of a new text satisfying the cons...