A Report on the 2020 VUA and TOEFL Metaphor Detection Shared Task

Leong, Chee Wee; Klebanov, Beata Beigman; Hamill, Chris; Stemle, Egon; Ubale, Rutuja; Chen, Xianyang

doi:10.18653/v1/2020.figlang-1.3

Cited by 34 publications

(27 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An effective approach to transfer learning used frequently in recent years is the pre-training of language models, such as BERT [4], on large amounts of unsupervised data. The knowledge from this pre-training phase is then transferred to the subsequent fine-tuning phase on task-and domain-specific data, which has shown significant improvements on several benchmark datasets, e.g., [12] and [1]. Subsequently, several languageand domain-specific adaptations of language models have been developed for non-English data or to further improve the performance of the original models on specific tasks.…”

Section: Related Researchmentioning

confidence: 99%

CoNTACT: A Dutch COVID-19 Adapted BERT for Vaccine Hesitancy and Argumentation Detection

Lemmens¹,

Nooten²,

Kreutz³

et al. 2022

Preprint

View full text Add to dashboard Cite

We present CoNTACT 1 : a Dutch language model adapted to the domain of COVID-19 tweets. The model was developed by continuing the pre-training phase of RobBERT [3] by using 2.8M Dutch COVID-19 related tweets posted in 2021. In order to test the performance of the model and compare it to RobBERT, the two models were tested on two tasks: (1) binary vaccine hesitancy detection and (2) detection of arguments for vaccine hesitancy. For both tasks, not only Twitter but also Facebook data was used to show cross-genre performance. In our experiments, CoNTACT showed statistically significant gains over RobBERT in all experiments for task 1. For task 2, we observed substantial improvements in virtually all classes in all experiments. An error analysis indicated that the domain adaptation yielded better representations of domain-specific terminology, causing CoNTACT to make more accurate classification decisions.

show abstract

Section: Related Researchmentioning

confidence: 99%

CoNTACT: A Dutch COVID-19 Adapted BERT for Vaccine Hesitancy and Argumentation Detection

Lemmens¹,

Nooten²,

Kreutz³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…First, it relies heavily on a number of models (metaphor classification, FrameNet frame tagging, and COMET symbol extraction), each of which introduces error. Specifically, metaphor detection remains a difficult task (with state-of-the-art results < .77 F1 (Leong et al, 2020)), making the identification of initial metaphors difficult. FrameNet tagging is also error prone, with the micro-F1 score for frame tagging being 70.9.…”

Section: Source/target Pairs From Framenet Taggingmentioning

confidence: 99%

Exploring Metaphoric Paraphrase Generation

Stowe¹,

Beck²,

Gurevych³

2021

Proceedings of the 25th Conference on Computational Natural Language Learning

View full text Add to dashboard Cite

Metaphor generation is a difficult task, and has seen tremendous improvement with the advent of deep pretrained models. We focus here on the specific task of metaphoric paraphrase generation, in which we provide a literal sentence and generate a metaphoric sentence which paraphrases that input. We compare naive, "free" generation models with those that exploit forms of control over the generation process, adding additional information based on conceptual metaphor theory. We evaluate two methods for generating paired training data, which is then used to train T5 models for free and controlled generation. We use crowdsourcing to evaluate the results, showing that free models tend to generate more fluent paraphrases, while controlled models are better at generating novel metaphors. We then analyze evaluation metrics, showing that different metrics are necessary to capture different aspects of metaphoric paraphrasing. We release our data and models, as well as our annotated results in order to facilitate development of better evaluation metrics. 1

show abstract

“…Such pervasiveness of metaphor in language and thought -as well as the ambiguity it creates -make metaphor a challenge to various NLP applications, such as machine translation, information retrieval and extraction, question answering, opinion mining, etc. The interest of the NLP community to computational metaphor research expressed itself in the series of dedicated workshops in 2013-2016 [10][11][12][13] and the two metaphor detection shared tasks in 2018 and 2020 [14,15].…”

Section: The Task Of Computational Metaphor Identificationmentioning

confidence: 99%

“…Besides, topic models, along with the other types of features, were suggested for use to the participants of the First and the Second shared tasks on metaphor detection [14,15].…”

Section: Topic Modelling In Metaphor Identification: Previous Workmentioning

confidence: 99%

Do Topics Make a Metaphor? Topic Modeling for Metaphor Identification and Analysis in Russian

Badryzlova

Nikiforova

Lyashevskaya

2021

Lecture Notes in Computer Science

View full text Add to dashboard Cite

The paper examines the efficiency of topic models as features for computational identification and conceptual analysis of linguistic metaphor on Russian data. We train topic models using three algorithms (LDA and ARTM -sparse and dense) and evaluate their quality. We compute topic vectors for sentences of a metaphor-annotated Russian corpus and train several classifiers to identify metaphor with these vectors. We compare the performance of the topic modeling classifiers with other state-of-the-art features (lexical, morphosyntactic, semantic coherence, and concreteness-abstractness) and their different combinations to see how topics contribute to metaphor identification. We show that some of the topics are more frequent in metaphoric contexts while others are more characteristic of non-metaphoric sentences, thus constituting topic predictors of metaphoricity, and discuss whether these predictors align with the conceptual mappings attested in literature. We also compare the topical heterogeneity of metaphoric and non-metaphoric contexts in order to test the hypothesis that metaphoric discourse should display greater topical variability due to the presence of Source and Target domains.

show abstract

A Report on the 2020 VUA and TOEFL Metaphor Detection Shared Task

Abstract: In this paper, we report on the shared task on metaphor identification on VU Amsterdam Metaphor Corpus and on a subset of the TOEFL Native Language Identification Corpus. The shared task was conducted as apart of the ACL 2020 Workshop on Processing Figurative Language.

Cited by 34 publications

References 50 publications

CoNTACT: A Dutch COVID-19 Adapted BERT for Vaccine Hesitancy and Argumentation Detection

CoNTACT: A Dutch COVID-19 Adapted BERT for Vaccine Hesitancy and Argumentation Detection

Exploring Metaphoric Paraphrase Generation

Do Topics Make a Metaphor? Topic Modeling for Metaphor Identification and Analysis in Russian

Contact Info

Product

Resources

About