Analyzing Gender Bias within Narrative Tropes

Gala, Dhruvil; Khursheed, Mohammad Omar; Lerner, Hannah; O’Connor, Brendan; Iyyer, Mohit

doi:10.18653/v1/2020.nlpcss-1.23

Cited by 12 publications

(13 citation statements)

References 13 publications

(13 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Prompts with the same content can still lead to different narratives that are tied to character gender, suggesting that GPT-3 has internally linked stereotypical contexts to gender. In previous work, GPT-3's predecessor GPT-2 also places women in caregiving roles (Kirk et al, 2021), and character tropes for women emphasize maternalism and appearance (Gala et al, 2020).…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Proceedings of the Third Workshop on Narrative Understanding

2021

View full text Add to dashboard Cite

While natural language understanding of longform documents remains an open challenge, such documents often contain structural information that can inform the design of models encoding them. Movie scripts are an example of such richly structured text -scripts are segmented into scenes, which decompose into dialogue and descriptive components. In this work, we propose a neural architecture to encode this structure, which performs robustly on two multi-label tag classification tasks without using handcrafted features. We add a layer of insight by augmenting the encoder with an unsupervised 'interpretability' module, which can be used to extract and visualize narrative trajectories. Though this work specifically tackles screenplays, we discuss how the underlying approach can be generalized to a range of structured documents.

show abstract

Section: Resultsmentioning

confidence: 99%

“…Now, we measure how much descriptions of characters correspond to a few established gender stereotypes. Men are often portrayed as strong, intelli-gent, and natural leaders (Smith et al, 2012;Fast et al, 2016b;Gala et al, 2020).…”

Section: Lexicon-based Stereotypesmentioning

confidence: 99%

Proceedings of the Third Workshop on Narrative Understanding

2021

View full text Add to dashboard Cite

show abstract

“…We modify BERT embeddings in this project. Pretrained language models such as BERT are known to produce embeddings that raise ethical concerns such as gender (Gala et al, 2020) and racial biases (Merullo et al, 2019;Bommasani et al, 2020), and can also output other offensive text content. Practitioners may consider employing a post-processing step to filter out potentially offensive content before releasing the final output.…”

Section: Ethical Considerationsmentioning

confidence: 99%

Phrase-BERT: Improved Phrase Embeddings from BERT with an Application to Corpus Exploration

Wang¹,

Thompson²,

Iyyer³

2021

Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Self Cite

View full text Add to dashboard Cite

Phrase representations derived from BERT often do not exhibit complex phrasal compositionality, as the model relies instead on lexical similarity to determine semantic relatedness. In this paper, we propose a contrastive fine-tuning objective that enables BERT to produce more powerful phrase embeddings. Our approach (Phrase-BERT) relies on a dataset of diverse phrasal paraphrases, which is automatically generated using a paraphrase generation model, as well as a large-scale dataset of phrases in context mined from the Books3 corpus. Phrase-BERT outperforms baselines across a variety of phrase-level similarity tasks, while also demonstrating increased lexical diversity between nearest neighbors in the vector space. Finally, as a case study, we show that Phrase-BERT embeddings can be easily integrated with a simple autoencoder to build a phrase-based neural topic model that interprets topics as mixtures of words and phrases by performing a nearest neighbor search in the embedding space. Crowdsourced evaluations demonstrate that this phrase-based topic model produces more coherent and meaningful topics than baseline word and phrase-level topic models, further validating the utility of Phrase-BERT.

show abstract

“…Recently, Chiril et al (2020) developed a dataset for sexism detection in French tweets. While the study of sexism in TV shows has received little attention in natural language processing Lee et al (2019b), Gala et al (2020), Xu et al (2019), it has received significant attention in the field of gender studies (Sink and Mastro, 2017;Glascock, 2003). In gender studies, Sink and Mastro (2017) conducted a quantitative analysis to document portrayals of women and men on prime-time television and Glascock (2003) examines the perception of gender roles on network prime-time television programming.…”

Section: Related Workmentioning

confidence: 99%

“Hold on honey, men at work”: A semi-supervised approach to detecting sexism in sitcoms

Singh¹,

Anand²,

Chowdhury³

et al. 2021

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Confer

View full text Add to dashboard Cite

Television shows play an important role in propagating societal norms. Owing to the popularity of the situational comedy (sitcom) genre, it contributes significantly to the overall development of society. In an effort to analyze the content of television shows belonging to this genre, we present a dataset of dialogue turns from popular sitcoms annotated for the presence of sexist remarks. We train a text classification model to detect sexism using domain adaptive learning. We apply the model to our dataset to analyze the evolution of sexist content over the years. We propose a domain-specific semi-supervised architecture for the aforementioned detection of sexism. Through extensive experiments, we show that our model often yields better classification performance over generic deep learning based sentence classification that does not employ domain-specific training. We find that while sexism decreases over time on average, the proportion of sexist dialogue for the most sexist sitcom actually increases. . A quantitative analysis along with a detailed error analysis presents the case for our proposed methodology.

show abstract

Analyzing Gender Bias within Narrative Tropes

Cited by 12 publications

References 13 publications

Proceedings of the Third Workshop on Narrative Understanding

Proceedings of the Third Workshop on Narrative Understanding

Phrase-BERT: Improved Phrase Embeddings from BERT with an Application to Corpus Exploration

“Hold on honey, men at work”: A semi-supervised approach to detecting sexism in sitcoms

Contact Info

Product

Resources

About