Semantically Informed Slang Interpretation

Slang is a predominant form of informal language making flexible and extended use of words that is notoriously hard for natural language processing systems to interpret. Existing approaches to slang interpretation tend to rely on context but ignore semantic extensions common in slang word usage. We propose a semantically informed slang interpretation (SSI) framework that considers jointly the contextual and semantic appropriateness of a candidate interpretation for a query slang. We perform rigorous evaluation on two large-scale online slang dictionaries and show that our approach not only achieves state-of-the-art accuracy for slang interpretation in English, but also does so in zero-shot and few-shot scenarios where training data is sparse. Furthermore, we show how the same framework can be applied to enhancing machine translation of slang from English to other languages. Our work creates opportunities for the automated interpretation and translation of informal language.

[1]  Richard Zemel,et al.  A Computational Framework for Slang Generation , 2021, Transactions of the Association for Computational Linguistics.

[2]  Jörg Tiedemann,et al.  OPUS-MT – Building open translation services for the World , 2020, EAMT.

[3]  Alon Lavie,et al.  COMET: A Neural Framework for MT Evaluation , 2020, EMNLP.

[4]  Mark Chen,et al.  Language Models are Few-Shot Learners , 2020, NeurIPS.

[5]  Chris Donahue,et al.  Enabling Language Models to Fill in the Blanks , 2020, ACL.

[6]  Thibault Sellam,et al.  BLEURT: Learning Robust Metrics for Text Generation , 2020, ACL.

[7]  Yang Xu,et al.  Slang Detection and Identification , 2019, CoNLL.

[8]  Ilya Sutskever,et al.  Language Models are Unsupervised Multitask Learners , 2019 .

[9]  Yang Xu,et al.  Slang Generation as Categorization , 2019, CogSci.

[10]  Devendra K. Tayal,et al.  SLANGZY: a fuzzy logic-based algorithm for English slang meaning selection , 2018, Progress in Artificial Intelligence.

[11]  Roland Vollgraf,et al.  Contextual String Embeddings for Sequence Labeling , 2018, COLING.

[12]  Huan Liu,et al.  SlangSD: building, expanding and using a sentiment dictionary of slang words for short-text sentiment classification , 2018, Lang. Resour. Evaluation.

[13]  William Yang Wang,et al.  Simple Models for Word Formation in Slang , 2018, NAACL.

[14]  William Yang Wang,et al.  Learning to Explain Non-Standard English Words and Phrases , 2017, IJCNLP.

[15]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[16]  Richard S. Zemel,et al.  Prototypical Networks for Few-shot Learning , 2017, NIPS.

[17]  Tomas Mikolov,et al.  Enriching Word Vectors with Subword Information , 2016, TACL.

[18]  Alok Ranjan Pal,et al.  Detection of Slang Words in e-Data using semi-Supervised Learning , 2017, ArXiv.

[19]  Jure Leskovec,et al.  Diachronic Word Embeddings Reveal Statistical Laws of Semantic Change , 2016, ACL.

[20]  Pushpak Bhattacharyya,et al.  SlangNet: A WordNet like resource for English Slang , 2016, LREC.

[21]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[22]  Yang Xu,et al.  A Computational Evaluation of Two Laws of Semantic Change , 2015, CogSci.

[23]  Quoc V. Le,et al.  Sequence to Sequence Learning with Neural Networks , 2014, NIPS.

[24]  Colin Cherry,et al.  A Systematic Comparison of Smoothing Techniques for Sentence-Level BLEU , 2014, WMT@ACL.

[25]  Alex Graves,et al.  Sequence Transduction with Recurrent Neural Networks , 2012, ArXiv.

[26]  Jörg Tiedemann,et al.  Parallel Data, Tools and Interfaces in OPUS , 2012, LREC.

[27]  Wiebke Wagner,et al.  Steven Bird, Ewan Klein and Edward Loper: Natural Language Processing with Python, Analyzing Text with the Natural Language Toolkit , 2010, Lang. Resour. Evaluation.

[28]  Jonathon Green.  Green's Dictionary of Slang , 2010 .

[29]  Elisa Mattiello,et al.  Difficulty of slang translation , 2009 .

[30]  Salim Roukos,et al.  Bleu: a Method for Automatic Evaluation of Machine Translation , 2002, ACL.

[31]  V. Braun,et al.  “Snatch,” “Hole,” or “Honey‐pot”? Semantic categories and the problem of nonspecificity in female genital slang , 2001 .

[32]  Yann LeCun,et al.  Signature Verification Using A "Siamese" Time Delay Neural Network , 1993, Int. J. Pattern Recognit. Artif. Intell..

[33]  Pierre Baldi,et al.  Neural Networks for Fingerprint Recognition , 1993, Neural Computation.

[34]  Beatrice Warren,et al.  Sense Developments: A Contrastive Study of the Development of Slang Senses and Novel Standard Senses in English , 1992 .

[35]  Douglas B. Terry,et al.  Using collaborative filtering to weave an information tapestry , 1992, CACM.

[36]  Adrienne Lehrer.  The influence of semantic fields on semantic change , 1985 .

[37]  E. Rosch.  Cognitive Representations of Semantic Categories. , 1975 .