| 1 |
MIss RoBERTa WiLDe: Metaphor Identification Using Masked Language Model with Wiktionary Lexical Definitions
|
|
|
|
In: Applied Sciences; Volume 12; Issue 4; Pages: 2081 (2022)
|
|
Abstract:
Recent years have brought an unprecedented and rapid development in the field of Natural Language Processing. To a large degree this is due to the emergence of modern language models like GPT-3 (Generative Pre-trained Transformer 3), XLNet, and BERT (Bidirectional Encoder Representations from Transformers), which are pre-trained on a large amount of unlabeled data. These powerful models can be further used in the tasks that have traditionally been suffering from a lack of material that could be used for training. Metaphor identification task, which is aimed at automatic recognition of figurative language, is one of such tasks. The metaphorical use of words can be detected by comparing their contextual and basic meanings. In this work, we deliver the evidence that fully automatically collected dictionary definitions can be used as the optimal medium for retrieving the non-figurative word senses, which consequently may help improve the performance of the algorithms used in metaphor detection task. As the source of the lexical information, we use the openly available Wiktionary. Our method can be applied without changes to any other dataset designed for token-level metaphor detection given it is binary labeled. In the set of experiments, our proposed method (MIss RoBERTa WiLDe) outperforms or performs similarly well as the competing models on several datasets commonly chosen in the research on metaphor processing.
|
|
Keyword:
figurative language; language models; lexical definitions; metaphor detection; RoBERTa; Sentence-BERT; Wiktionary
|
|
URL: https://doi.org/10.3390/app12042081
|
|
BASE
|
|
Hide details
|
|
|
| 2 |
HokuMed in NTCIR-11 MedNLP2:Automatic extraction of medical complaints from Japanese health records using machine learning and rule-based methods.
|
|
|
|
In: http://arakilab.media.eng.hokudai.ac.jp/%7Earaki/2014/2014-A-6.pdf (2014)
|
|
BASE
|
|
Show details
|
|
|
| 3 |
A Casual Conversation System Using Modality and Word Associations Retrieved from the Web
|
|
|
|
In: http://www.aclweb.org/anthology/D08-1040/ (2008)
|
|
BASE
|
|
Show details
|
|
|
| 4 |
A dynamic memory management system based on forgetting and recalling
|
|
|
|
In: http://sig.media.eng.hokudai.ac.jp/~ptaszynski/data/2007_11_SHIBU_Forget_recall.pdf (2007)
|
|
BASE
|
|
Show details
|
|
|
| 5 |
Automatic First Utterance Creation Based on the Strongest Association Retrieved from WWW
|
|
|
|
In: http://www-kasm.nii.ac.jp/jsai2005/schedule/pdf/000245.pdf (2005)
|
|
BASE
|
|
Show details
|
|
|
| 6 |
cs.kitami-it.ac.jp
|
|
|
|
In: http://www.aclweb.org/anthology/W/W14/W14-2610.pdf
|
|
BASE
|
|
Show details
|
|
|
| 7 |
Effective Analysis of Emotiveness in Utterances Based on Features of Lexical and Non-Lexical Layer of Speech.
|
|
|
|
In: http://sig.media.eng.hokudai.ac.jp/~ptaszynski/data/2008_03_NLP_Analysis_of_Emotiveness.pdf
|
|
BASE
|
|
Show details
|
|
|
| 8 |
Toward Automatic Support For Japanese Lay Judge System – – Processing Precedent Factors For Sentencing Trends Discovery
|
|
|
|
In: http://research.nii.ac.jp/ntcir/workshop/OnlineProceedings7/pdf/NTCIR7/C4/MuST-F/08-NTCIR7-MuST-F-RzepkaR.pdf
|
|
BASE
|
|
Show details
|
|
|
| 9 |
Automatically Annotating A Five-Billion-Word Corpus of Japanese Blogs for Affect and Sentiment Analysis
|
|
|
|
In: http://www.aclweb.org/anthology-new/W/W12/W12-3714.pdf
|
|
BASE
|
|
Show details
|
|
|
| 10 |
4 Connectives Acquisition in a Humanoid Robot Based on an Inductive Learning Language Acquisition Model
|
|
|
|
In: http://cdn.intechweb.org/pdfs/6235.pdf
|
|
BASE
|
|
Show details
|
|
|
| 11 |
15+ MILLION TOP 1% MOST CITED SCIENTIST 12.2% AUTHORS AND EDITORS FROM TOP 500 UNIVERSITIES 4 Connectives Acquisition in a Humanoid Robot Based on an Inductive Learning Language Acquisition Model
|
|
|
|
In: http://cdn.intechopen.com/pdfs-wm/6235.pdf
|
|
BASE
|
|
Show details
|
|
|
| 12 |
Commonsense Retrieval as an Aid for Easier Conversation-based Language Acquisition
|
|
|
|
In: http://arakilab.media.eng.hokudai.ac.jp/~araki/2005(e)/2005-A-5.pdf
|
|
BASE
|
|
Show details
|
|
|
| 13 |
Engagement
|
|
|
|
In: http://arakilab.media.eng.hokudai.ac.jp/~araki/2011/2011-A-7.pdf
|
|
BASE
|
|
Show details
|
|
|
| 14 |
Blog Snippets Based Drug Effects Extraction System Using Lexical and Grammatical Restrictions
|
|
|
|
BASE
|
|
Show details
|
|
|
|
|
