Idiomatic Expression Identification using Semantic Compatibility

Idiomatic Expression Identification using Semantic Compatibility Ziheng Zeng and Suma Bhat Department of Electrical and Computer Engineering University of Illinois at Urbana-Champaign Champaign, IL USA {zzeng13, spbhat2}@illinois.edu Abstract Idiomatic expressions are an integral part of natural language and constantly being added to a language. Owing to their non-compositionality and their ability to take on a figurative or literal meaning depending on the sentential context, they have been a classical challenge for NLP systems. To address this challenge, we study the task of detecting whether a sentence has an idiomatic expression and localizing it when it occurs in a figurative sense. Prior research for this task has studied specific classes of idiomatic expressions offering limited views of their generalizability to new idioms. We propose a multi-stage neural architecture with attention flow as a solution. The network ef- fectively fuses contextual and lexical infor- mation at different levels using word and sub-word representations. Empirical evalua- tions on three of the largest benchmark datasets with idiomatic expressions of varied syntactic patterns and degrees of non-compositionality show that our proposed model achieves new state-of-the-art results. A salient feature of the model is its ability to identify idioms un- seen during training with gains from 1.4% to 30.8% over competitive baselines on the largest dataset. 1 Introduction Idiomatic expressions (IEs) are a special class of multi-word expressions (MWEs) that typically occur as collocations and exhibit semantic non- compositionality (a.k.a. semantic idiomaticity), where the meaning of the expression is not deriv- able from its parts (Baldwin and Kim, 2010). In terms of occurrence, IEs are individually rare, but collectively frequent in and constantly added to na- tural language across different genres (Moon et al., 1998). Additionally, they are known to enhance fluency and used to convey ideas succinctly when used in everyday language (Baldwin and Kim, 2010; Moon et al., 1998). Classically regarded as a ‘‘pain in the neck’’ to idiom-unaware NLP applications (Sag et al., 2002) these phrases are challenging for reasons including their non-compositionality (semantic idiomaticity), besides taking a figurative or literal meaning depending on the context (semantic am- biguity), as shown by the example in Table 1. Borrowing the terminology from Haagsma et al. (2020), we call these phrases potentially idiomatic expressions (PIEs) to account for the context- ual semantic ambiguity. Indeed, prior work has identified the challenges that PIEs pose to many NLP applications, such as machine translation (Fadaee et al., 2018; Salton et al., 2014), para- phrase generation (Ganitkevitch et al., 2013), and sentiment analysis (Liu et al., 2017; Biddle et al., 2020). Accordingly, making applications idiom- aware, either by identifying them before or dur- ing the task, has been found to be effective (Korkontzelos and Manandhar, 2010; Nivre and Nilsson, 2004; Nasr et al., 2015). This study proposes a novel architecture that detects the pres- ence of a PIE. When found, its span in a given sentence is localized and returning the phrase if it is used figuratively (i.e., used as an IE); other- wise an empty string is returned …

Content truncated to 500 words