SenseSpotting: Never let your parallel data tie you to an old domain

نویسندگان

  • Marine Carpuat
  • Hal Daumé
  • Katharine Henry
  • Ann Irvine
  • Jagadeesh Jagarlamudi
  • Rachel Rudinger
چکیده

Words often gain new senses in new domains. Being able to automatically identify, from a corpus of monolingual text, which word tokens are being used in a previously unseen sense has applications to machine translation and other tasks sensitive to lexical semantics. We define a task, SENSESPOTTING, in which we build systems to spot tokens that have new senses in new domain text. Instead of difficult and expensive annotation, we build a goldstandard by leveraging cheaply available parallel corpora, targeting our approach to the problem of domain adaptation for machine translation. Our system is able to achieve F-measures of as much as 80%, when applied to word types it has never seen before. Our approach is based on a large set of novel features that capture varied aspects of how words change when used in new domains.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

P14: How to Find a Talent?

Talents may be artistic or technical, mental or physical, personal or social. You can be a talented introvert or a talented extrovert. Learning to look for your talents in the right places and building those talents into skills and abilities might take some work, but going about it creatively will let you explore your natural abilities and find your innate talents. You’re not going to fin...

متن کامل

مدیر موفق کیست؟

Who is a really successful manager? A manager who spends less money, or the one who earns more? A manager who can survive for a longer period of time, or an administrator who expands his organization, and opens up new branches? Which one is the most successful? The article tries to answer these questions and provides, some simple guidlines for the managers in every domain of management who wan...

متن کامل

جستاری میان رشته ای در اصول طراحی اتاق خواب با استناد به آموزه های نَقلی مکتب اسلام

The Holy Quran and hadiths as the most important Islamic religious texts have significant capacities in various fields of human knowledge which have been often neglected. Among the issues raised in this religious texts are some of architectural problems. One of these problems is quality of bedroom design. In this article, this problem will be probed by citing verses and hadiths to deduct bedroo...

متن کامل

P35: How to Manage Anxiety

Anxiety is a mental state that is elicited in anticipation of threat or potential threat. Sensations of anxiety are a normal part of human experience, but excessive or inappropriate anxiety can become an illness. Anxiety is part of the normal human experience. We may speculate that it served human survival during evolution by enhancing preparedness and alertness. However, anxious manifestations...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2013