Английский язык: Аннотирование и реферирование текста

270 Google/Research: "Doctor said Akihito is scheduled to rest for about a month." Can a machine translator provide more than "gisting", a rough idea of the contents of a foreign-language text? Can a machine translator provide more than "gisting," a rough idea of the contents of a foreign-language text? The buzz about statistical machine translation has put Systran on the defensive. "You need rules when learning a foreign language," Sa- batakakis comments. "You don't learn a language with statistical meth- ods." Systran uses statistical techniques when creating systems in very narrow domains, such as translating patent documents. But the current embrace of statistical methods is somewhat of a marketing technique, he says. The company still employs 50 people in research and devel- opment, among them linguists. "The major difference between Systran and Google is that Google claims that it doesn't need native Chinese people to develop Chinese [applications] because of the magic and beauty of this stuff," Sabatakakis says, adding, "If we don't have some Chinese guys, our system may contain enormous mistakes." The distinction between the two camps has begun to blur a little as statistical MT researchers have started to incorporate techniques that account for the syntactical structure of a sentence. These methods forgo the intervention of a human linguist: a syntactic model might estimate the chance that an English adjective-noun phrase gets reordered after translation into French. Knight of Language Weaver says that relying on phrases instead of single words allows the statistics to deal with se- mantics as well, avoiding, for instance, having his surname translated as "Caballero." Microsoft Research has a substantial natural-language group, which for the past six years has also worked on MT. The group first focused on rule-based systems. But it is increasingly incorporating sta- tistical techniques. Recently Microsoft used primarily statistical ap- proaches when translating its online customer-support Web sites into