Verna Dankers


Paper Bullets: Modeling Propaganda with the Help of Metaphor
Daniel Baleato Rodríguez | Verna Dankers | Preslav Nakov | Ekaterina Shutova
Findings of the Association for Computational Linguistics: EACL 2023

Propaganda aims to persuade an audience by appealing to emotions and using faulty reasoning, with the purpose of promoting a particular point of view. Similarly, metaphor modifies the semantic frame, thus eliciting a response that can be used to tune up or down the emotional volume of the message. Given the close relationship between them, we hypothesize that, when modeling them computationally, it can be beneficial to do so jointly. In particular, we perform multi-task learning with propaganda identification as the main task and metaphor detection as an auxiliary task. To the best of our knowledge, this is the first work that models metaphor and propaganda together. We experiment with two datasets for identifying propaganda techniques in news articles and in memes shared on social media. We find that leveraging metaphor improves model performance, particularly for the two most common propaganda techniques: loaded language and name-calling.


Text Characterization Toolkit (TCT)
Daniel Simig | Tianlu Wang | Verna Dankers | Peter Henderson | Khuyagbaatar Batsuren | Dieuwke Hupkes | Mona Diab
Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing: System Demonstrations

We present a tool, Text Characterization Toolkit (TCT), that researchers can use to study characteristics of large datasets. Furthermore, such properties can lead to understanding the influence of such attributes on models’ behaviour. Traditionally, in most NLP research, models are usually evaluated by reporting single-number performance scores on a number of readily available benchmarks, without much deeper analysis. Here, we argue that – especially given the well-known fact that benchmarks often contain biases, artefacts, and spurious correlations – deeper results analysis should become the de-facto standard when presenting new models or benchmarks. TCT aims at filling this gap by facilitating such deeper analysis for datasets at scale, where datasets can be for training/development/evaluation. TCT includes both an easy-to-use tool, as well as off-the-shelf scripts that can be used for specific analyses. We also present use-cases from several different domains. TCT is used to predict difficult examples for given well-known trained models; TCT is also used to identify (potentially harmful) biases present in a dataset.

Can Transformer be Too Compositional? Analysing Idiom Processing in Neural Machine Translation
Verna Dankers | Christopher Lucas | Ivan Titov
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Unlike literal expressions, idioms’ meanings do not directly follow from their parts, posing a challenge for neural machine translation (NMT). NMT models are often unable to translate idioms accurately and over-generate compositional, literal translations. In this work, we investigate whether the non-compositionality of idioms is reflected in the mechanics of the dominant NMT model, Transformer, by analysing the hidden states and attention patterns for models with English as source language and one of seven European languages as target language.When Transformer emits a non-literal translation - i.e. identifies the expression as idiomatic - the encoder processes idioms more strongly as single lexical units compared to literal expressions. This manifests in idioms’ parts being grouped through attention and in reduced interaction between idioms and their context.In the decoder’s cross-attention, figurative inputs result in reduced attention on source-side tokens. These results suggest that Transformer’s tendency to process idioms as compositional expressions contributes to literal translations of idioms.

The Paradox of the Compositionality of Natural Language: A Neural Machine Translation Case Study
Verna Dankers | Elia Bruni | Dieuwke Hupkes
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Obtaining human-like performance in NLP is often argued to require compositional generalisation. Whether neural networks exhibit this ability is usually studied by training models on highly compositional synthetic data. However, compositionality in natural language is much more complex than the rigid, arithmetic-like version such data adheres to, and artificial compositionality tests thus do not allow us to determine how neural models deal with more realistic forms of compositionality. In this work, we re-instantiate three compositionality tests from the literature and reformulate them for neural machine translation (NMT).Our results highlight that: i) unfavourably, models trained on more data are more compositional; ii) models are sometimes less compositional than expected, but sometimes more, exemplifying that different levels of compositionality are required, and models are not always able to modulate between them correctly; iii) some of the non-compositional behaviours are mistakes, whereas others reflect the natural variation in data. Apart from an empirical study, our work is a call to action: we should rethink the evaluation of compositionality in neural networks and develop benchmarks using real data to evaluate compositionality on natural language, where composing meaning is not as straightforward as doing the math.

Meta-Learning for Fast Cross-Lingual Adaptation in Dependency Parsing
Anna Langedijk | Verna Dankers | Phillip Lippe | Sander Bos | Bryan Cardenas Guevara | Helen Yannakoudakis | Ekaterina Shutova
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Meta-learning, or learning to learn, is a technique that can help to overcome resource scarcity in cross-lingual NLP problems, by enabling fast adaptation to new tasks. We apply model-agnostic meta-learning (MAML) to the task of cross-lingual dependency parsing. We train our model on a diverse set of languages to learn a parameter initialization that can adapt quickly to new languages. We find that meta-learning with pre-training can significantly improve upon the performance of language transfer and standard supervised learning baselines for a variety of unseen, typologically diverse, and low-resource languages, in a few-shot learning setup.

Recursive Neural Networks with Bottlenecks Diagnose (Non-)Compositionality
Verna Dankers | Ivan Titov
Findings of the Association for Computational Linguistics: EMNLP 2022

A recent line of work in NLP focuses on the (dis)ability of models to generalise compositionally for artificial languages.However, when considering natural language tasks, the data involved is not strictly, or locally, compositional.Quantifying the compositionality of data is a challenging task, which has been investigated primarily for short utterances.We use recursive neural models (Tree-LSTMs) with bottlenecks that limit the transfer of information between nodes.We illustrate that comparing data’s representations in models with and without the bottleneck can be used to produce a compositionality metric.The procedure is applied to the evaluation of arithmetic expressions using synthetic data, and sentiment classification using natural language data.We demonstrate that compression through a bottleneck impacts non-compositional examples disproportionatelyand then use the bottleneck compositionality metric (BCM) to distinguish compositional from non-compositional samples, yielding a compositionality ranking over a dataset.


Generalising to German Plural Noun Classes, from the Perspective of a Recurrent Neural Network
Verna Dankers | Anna Langedijk | Kate McCurdy | Adina Williams | Dieuwke Hupkes
Proceedings of the 25th Conference on Computational Natural Language Learning

Inflectional morphology has since long been a useful testing ground for broader questions about generalisation in language and the viability of neural network models as cognitive models of language. Here, in line with that tradition, we explore how recurrent neural networks acquire the complex German plural system and reflect upon how their strategy compares to human generalisation and rule-based models of this system. We perform analyses including behavioural experiments, diagnostic classification, representation analysis and causal interventions, suggesting that the models rely on features that are also key predictors in rule-based models of German plurals. However, the models also display shortcut learning, which is crucial to overcome in search of more cognitively plausible generalisation behaviour.


Being neighbourly: Neural metaphor identification in discourse
Verna Dankers | Karan Malhotra | Gaurav Kudva | Volodymyr Medentsiy | Ekaterina Shutova
Proceedings of the Second Workshop on Figurative Language Processing

Existing approaches to metaphor processing typically rely on local features, such as immediate lexico-syntactic contexts or information within a given sentence. However, a large body of corpus-linguistic research suggests that situational information and broader discourse properties influence metaphor production and comprehension. In this paper, we present the first neural metaphor processing architecture that models a broader discourse through the use of attention mechanisms. Our models advance the state of the art on the all POS track of the 2018 VU Amsterdam metaphor identification task. The inclusion of discourse-level information yields further significant improvements.

The Pragmatics behind Politics: Modelling Metaphor, Framing and Emotion in Political Discourse
Pere-Lluís Huguet Cabot | Verna Dankers | David Abadi | Agneta Fischer | Ekaterina Shutova
Findings of the Association for Computational Linguistics: EMNLP 2020

There has been an increased interest in modelling political discourse within the natural language processing (NLP) community, in tasks such as political bias and misinformation detection, among others. Metaphor-rich and emotion-eliciting communication strategies are ubiquitous in political rhetoric, according to social science research. Yet, none of the existing computational models of political discourse has incorporated these phenomena. In this paper, we present the first joint models of metaphor, emotion and political rhetoric, and demonstrate that they advance performance in three tasks: predicting political perspective of news articles, party affiliation of politicians and framing of policy issues.


Modelling the interplay of metaphor and emotion through multitask learning
Verna Dankers | Marek Rei | Martha Lewis | Ekaterina Shutova
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)

Metaphors allow us to convey emotion by connecting physical experiences and abstract concepts. The results of previous research in linguistics and psychology suggest that metaphorical phrases tend to be more emotionally evocative than their literal counterparts. In this paper, we investigate the relationship between metaphor and emotion within a computational framework, by proposing the first joint model of these phenomena. We experiment with several multitask learning architectures for this purpose, involving both hard and soft parameter sharing. Our results demonstrate that metaphor identification and emotion prediction mutually benefit from joint learning and our models advance the state of the art in both of these tasks.

pdf bib
Transcoding Compositionally: Using Attention to Find More Generalizable Solutions
Kris Korrel | Dieuwke Hupkes | Verna Dankers | Elia Bruni
Proceedings of the 2019 ACL Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP

While sequence-to-sequence models have shown remarkable generalization power across several natural language tasks, their construct of solutions are argued to be less compositional than human-like generalization. In this paper, we present seq2attn, a new architecture that is specifically designed to exploit attention to find compositional patterns in the input. In seq2attn, the two standard components of an encoder-decoder model are connected via a transcoder, that modulates the information flow between them. We show that seq2attn can successfully generalize, without requiring any additional supervision, on two tasks which are specifically constructed to challenge the compositional skills of neural networks. The solutions found by the model are highly interpretable, allowing easy analysis of both the types of solutions that are found and potential causes for mistakes. We exploit this opportunity to introduce a new paradigm to test compositionality that studies the extent to which a model overgeneralizes when confronted with exceptions. We show that seq2attn exhibits such overgeneralization to a larger degree than a standard sequence-to-sequence model.