Experiments in Idiom Recognition

نویسندگان

  • Jing Peng
  • Anna Feldman
چکیده

Some expressions can be ambiguous between idiomatic and literal interpretations depending on the context they occur in, e.g., sales hit the roof vs. hit the roof of the car. We present a novel method of classifying whether a given instance is literal or idiomatic, focusing on verb-noun constructions. We report state-of-the-art results on this task using an approach based on the hypothesis that the distributions of the contexts of the idiomatic phrases will be different from the contexts of the literal usages. We measure contexts by using projections of the words into vector space. For comparison, we implement Fazly et al. (2009)’s, Sporleder and Li (2009)’s, and Li and Sporleder (2010b)’s methods and apply them to our data. We provide experimental results validating the proposed techniques.

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

Japanese Idiom Recognition: Drawing a Line between Literal and Idiomatic Meanings

Recognizing idioms in a sentence is important to sentence understanding. This paper discusses the lexical knowledge of idioms for idiom recognition. The challenges are that idioms can be ambiguous between literal and idiomatic meanings, and that they can be “transformed” when expressed in a sentence. However, there has been little research on Japanese idiom recognition with its ambiguity and tr...

متن کامل

On the Effects of Linguistic, Verbal, and Visual Mnemonics on Idioms Learning

Finding more effective ways of teaching second language idioms has been a long standing concern of many teaching practitioners and researchers. This study was an endeavorto explore the effects of three linguistic mnemonic devices (etymological elaboration, keyword method, and translation) on EFL learners’ recognition and recall of English idioms. To achieve the purpose of the study, ninety male...

متن کامل

The Automatic Translation of Idioms. Machine Translation vs. Translation Memory Systems

Translating idioms is one of the most difficult tasks for human translators and translation machines alike. The main problems consist in recognizing an idiom and in distinguishing idiomatic from non-idiomatic usage. Recognition is difficult since many idioms can be modified and others can be discontinuously spread over a clause. But with the help of systematic idiom collections and special rule...

متن کامل

The Automatic Translation of Idioms

Translating idioms is one of the most diicult tasks for human translators and translation machines alike. The main problems consist in recognizing an idiom and in distinguishing idiomatic from non-idiomatic usage. Recognition is diicult since many idioms can be modiied and others can be discontinuously spread over a clause. But with the help of systematic idiom collections and special rules the...

متن کامل

The Comparative Effect of Using Idioms in Conversation and Paragraph Writing on EFL Learners’ Idiom Learning

This study investigated the comparative effect of teaching idiomatic expressions through practicing them in conversation and paragraph writing on intermediate EFL learners’ idiom learning. The participants were sorted out of a population of 134 intermediate students in Zabansara Language School in Khorramabad based on their scores on a Preliminary English Test (PET) and an idiom test piloted in...

متن کامل

A New Idiom Recognition Framework for Exploiting Accelerators

Modern processors support hardware-assist instructions (such as TRT and TROT instructions on IBM zSeries) to accelerate certain functions such as delimiter search and character conversion. Such special instructions have often been used in high performance libraries, but they have not been exploited well in optimizing compilers except for some limited cases. We propose a new idiom recognition te...

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 2016