paper-with-me

Papers

Metaphor Detection Using Contextual Word Embeddings From Transformers

2020-07-01 · WS 2020 7 · Jerry Liu, Nathan O{'}Hara, Alex Rubin, er, Rachel Draelos, Cynthia Rudin

The detection of metaphors can provide valuable information about a given text and is crucial to sentiment analysis and machine translation. In this paper, we outline the techniques for word-level metaphor detection used in our submission to the Second Shared Task on Metaphor Detection. We propose using both BERT and XLNet language models to create contextualized embeddings and a bi-directional LSTM to identify whether a given word is a metaphor. Our best model achieved F1-scores of 68.0{\%} on VUA AllPOS, 73.0{\%} on VUA Verbs, 66.9{\%} on TOEFL AllPOS, and 69.7{\%} on TOEFL Verbs, placing 7th, 6th, 5th, and 5th respectively. In addition, we outline another potential approach with a KNN-LSTM ensemble model that we did not have enough time to implement given the deadline for the competition. We show that a KNN classifier provides a similar F1-score on a validation set as the LSTM and yields different information on metaphors.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Machine TranslationSentiment AnalysisTranslationWord Embeddings

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
k-NN $k$-Nearest Neighbors is a clustering-based algorithm for classification and regression. It is a a type of instance-based learning as it does not attempt to construct a…
Weight Decay 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Attention 설명 없음

Similar Papers 제목 키워드 기반

ContrastWSD: Enhancing Metaphor Detection with Word Sense Disambiguation Following the Metaphor Identification Procedure

2023-09-06 · Mohamad Elzohbi, Richard Zhao

This paper presents ContrastWSD, a RoBERTa-based metaphor detection model that integrates the Metaphor Identification Procedure (MIP) and Word Sense Disambiguation (WSD) to extract and contrast the contextual meaning wit…

SentenceWord Sense Disambiguation

On the Impact of Temporal Representations on Metaphor Detection

2021-11-05 · LREC 2022 6 · Giorgio Ottolina, Matteo Palmonari, Mehwish Alam, Manuel Vimercati

State-of-the-art approaches for metaphor detection compare their literal - or core - meaning and their contextual meaning using metaphor classifiers based on neural networks. However, metaphorical expressions evolve over…

Word Embeddings

Metaphor Detection using Deep Contextualized Word Embeddings

2020-09-26 · Shashwat Aggarwal, Ramesh Singh

Metaphors are ubiquitous in natural language, and their detection plays an essential role in many natural language processing tasks, such as language understanding, sentiment analysis, etc. Most existing approaches for m…

Sentiment AnalysisWord Embeddings

MelBERT: Metaphor Detection via Contextualized Late Interaction using Metaphorical Identification Theories

2021-04-28 · NAACL 2021 4 · Minjin Choi, Sunkyung Lee, Eunseong Choi, Heesoo Park 외

Automated metaphor detection is a challenging task to identify metaphorical expressions of words in a sentence. To tackle this problem, we adopt pre-trained contextualized models, e.g., BERT and RoBERTa. To this end, we …

Sentence

Improving Neural Metaphor Detection with Visual Datasets

2020-05-01 · LREC 2020 5 · Gitit Kehat, James Pustejovsky

We present new results on Metaphor Detection by using text from visual datasets. Using a straightforward technique for sampling text from Vision-Language datasets, we create a data structure we term a visibility word emb…