[PDF] Phrasal Substitution of Idiomatic Expressions - Association for PDF N16-1040.pdf

17 jui 2016 · An idiom is a combination of words that has a fig- urative meaning which differs from its literal mean- ing Idioms pose a great challenge to many

An idiom is a phrase where the words together have a meaning that is different from the dictionary definitions of the individual words A A Bird In The Hand Is

[PDF] 100 Must Know Idioms - Oliveboard

Such phrases are called IDIOMS While their literal meanings may seem absurd, they have a metaphorical meaning and may even be written in an unusual

[PDF] 377 common IDIOMS and their meanings - PORTALLAS

IDIOM MEANING Acid test Proves the effectiveness of something Actions speak louder than words People's intentions can be judged better by what they do

[PDF] Idioms And Phrases With Meanings And Examples - Ruforum

15 jan 2021 · meanings of idioms and common sayings such as nest egg or new york minute and much more, 100 idioms amp phrases with meaning and example list of 100

English Idioms with Examples - Bloomsbury International

An idiom is a phrase that has a meaning which is different from the meanings of each individual Idioms are words or phrases whose meaning can't be worked

[PDF] AMERICAN SLANG WORDS AND PHRASES

Phrase often used rhetorically to express frustration or excitement You're telling me Phrase meaning "I know exactly what you mean"; Similar to "Don't I know it"

[PDF] 500+ Real English Phrases - Espresso English

The goal of this book is to teach you English phrases (not just individual English (this is a sarcastic phrase meaning that something UNLUCKY happened) 4

[PDF] A New Approach for Idiom Identification Using Meanings and the Web

nique, which model whether phrase meanings are constructed compositionally The dataset consists of phrases, definitions, and example sentences from the

[PDF] Phrasal Substitution of Idiomatic Expressions - Association for

17 jui 2016 · An idiom is a combination of words that has a fig- urative meaning which differs from its literal mean- ing Idioms pose a great challenge to many

[PDF] English for Writing Research Papers Useful Phrases - Springer

If you have checked that a word or phrase really has the same meaning, I suggest you choose the shortest option For example choose: Since x = y Although x =

Proceedings of NAACL-HLT 2016, pages 363-373,

San Diego, California, June 12-17, 2016.

2016 Association for Computational LinguisticsPhrasal Substitution of Idiomatic Expressions

Changsheng LiuandRebecca Hwa

Computer Science Department

University of Pittsburgh

Pittsburgh, PA 15260, USA

{changsheng,hwa}@cs.pitt.edu

Abstract

Idioms pose a great challenge to natural lan-

guage understanding. A system that can auto- matically paraphrase idioms in context has ap- plications in many NLP tasks. This paper pro- poses a phrasal substitution method to replace idioms with their figurative meanings in literal

English. Our approach identifies relevant re-

placement phrases from an idiom"s dictionary definition and performs appropriate grammat- ical and referential transformations to ensure that the idiom substitution fits seamlessly into the original context. The proposed method has been evaluated both by automatic metrics and human judgments. Results suggest that high quality paraphrases of idiomatic expressions can be achieved.

1 Introduction

An idiom is a combination of words that has a fig- urative meaning which differs from its literal mean- ing. Idioms pose a great challenge to many NLP tasks, such as machine translation, word sense dis- ambiguation, and sentiment analysis (Volk, 1998;

Korkontzelos et al., 2013; Zanzotto et al., 2010;

Williams et al., 2015). Previous work (Salton et

al., 2014) has shown that a typical statistical ma- chine translation system might achieve only half of the BLEU score (Papineni et al., 2002) on sentences that contain idiomatic expressions than on those that do not. Idioms are also problematic for second lan- guage learners. In a pilot study we have surveyed seven non-native speakers on 100 Tweets containing

idioms; we have found that, on average, the partici-pants had trouble understanding 70% of them due to

the inclusion of idioms.

This work explores the possibility of automati-

cally replacing idiomatic expressions in sentences. The full pipeline of a successful system has to solve many problems. First, it has to determine that an expression is, in fact, being used as an idiom in a sentence (Fazly et al., 2009; Korkontzelos et al.,

2013; Sporleder and Li, 2009). Moreover, the sys-

tem has tosense disambiguatethe idiom - it has to pick the correct interpretation when more than one is possible. Second, it has to generate an appropriate phrasal replacement for the idiom using literal En- glish. Third, it has to ensure that the replacement phrase will fit seamlessly back into the original sen- tence. This paper focuses on the second and third problem, which have not been studied as extensively in previous works.

We propose to extract the phrasal replacement for

an idiom from its definition, assuming the existence of an up-to-date dictionary of broad coverage and high quality.

1Because a typical definition is quite

long, it cannot directly serve as a replacement for the idiom. A major challenge of our work is in identi- fying the right nugget to extract from the definition.

Another major challenge is the smooth integration

of the substitution phrase into the sentence. We con- sider both grammatical fluency as well as references resolution in our automatic Post-Editing technique.

These phrasal challenges set our goals apart from

related work on lexical simplification and substitu- tion (Specia et al., 2012; Jauhar and Specia, 2012;

McCarthy, 2002; McCarthy and Navigli, 2007) and1

This work uses TheFreeDictionary.com.363

from general sentence simplification (Wubben et al.,

2012; Siddharthan, 2014; Zhu et al., 2010; Coster

and Kauchak, 2011) methods. We validate the plausibility of the proposed meth- ods with empirical experiments on a manually an- notated corpus.

2Results from both automatic eval-

uations and user studies show that the proposed ap- tences containing idiomatic expressions. A success- ful idiom paraphrase generator may not only bene- fit non-native speakers, but may also facilitate other

NLP applications.

2 Background

The main idea of this work is to produce a fluent

and meaningful paraphrase of the original sentence similar to how a human non-native reader might ap- proach the problem. Suppose the reader encounters the following sentence:

Sentence:This kind of language really

barfs me out andgets my blood up.3

If they do not understand the expressiongets my

blood up, they may look it up in a dictionary:

Definition:Fig. togetsomeoneoroneself

angry. (Fixed order.) 4 Then they might try to reconcile the definition with the context of the sentence and arrive at:

Paraphrased :This kind of language re-

ally barfs me out andgets me angry.

In the example above, only a portion of the full

definition is needed. One possible way to iden- tify this relevant nugget is to apply sentence com- pression techniques (McDonald, 2006; Siddharthan, 2011;

Stajner et al., 2013; Filippova et al., 2015;

Filippova and Strube, 2008; Narayan and Gardent,

2014; Cohn and Lapata, 2009). However, all these

complete sentences, and it is not clear whether they are suited to dictionary definitions. Consider Ta- ble 1, in which a corpus of 1000 randomly selected2 https://github.com/liucs1986/idiom_ corpus

3https://twitter.com/ezzwanaezwnd/

status/231992426548559872

4http://idioms.thefreedictionary.com/

get+blood+upCorpus Average length Punctuation density

CLspoken 17 2.16

CLwritten 18 2.07

Definition 12 2.86Table 1:Some statistics over normal text corpora and an idiom definition corpus. idiom definitions is compared with samples from two normal text corpora (CLwritten and CLspoken) used by Clarke and Lapata (2008). The CLwritten corpus comes from written sources in the British

National Corpus and the American News Text cor-

pus; the CLspoken corpus comes from transcribed broadcast news stories. We see that on average, definitions are shorter than complete sentences; ar- guably, each word in a definition carries more in- formation. The density of punctuation per sentence shows that definitions are more fragmented. These factors are problematic for sentence compression techniques that rely heavily on the syntactic parse trees of complete, well-formed sentences (Cohn andquotesdbs_dbs3.pdfusesText_6

[PDF] [PDF] Phrasal Substitution of Idiomatic Expressions - Association for