Spain

Is it possible to draw a line between workforce statistics and gender bias in contextualized word embeddings? Focusing on BERT (Devlin et al., 2018), we measure gender bias by studying associations between gender-denoting target words and names of professions (Kurita et al., 2019), offering two further perspectives: a comparison with U.S. labor statistics as well as a cross-lingual approach. We mitigate bias by fine-tuning BERT on the GAP corpus (Webster et al., 2018), after applying Counterfactual Data Substitution (CDS; Maudslay et al., 2019). While our method of measuring bias is appropriate for languages such as English, it is not suitable for languages with gender-marking, such as German. Our results highlight the importance of investigating bias and mitigation techniques cross-linguistically and connect large-scale language models to real-world data.

COLING 2020

Unmasking Contextual Stereotypes: Measuring and Mitigating BERT&#39;S Gender Bias

### Welcome!
The 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024) will take place in Bangkok, Thailand from August 11th to 16th, 2024. Our Virtual Poster Sessions will take place online Thursday, August 22, 2024.

You are required to register for this event. **Please register [here](https://2024.aclweb.org/registration). **

If you have already registered, please check your inbox for an email from Underline granting you access to ACL 2024 content.

Please register!

ACL 2024

The 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024) will take place in Bangkok, Thailand from August 11th to 16th, 2024. More information will be announced soon.

Unmasking Contextual Stereotypes: Measuring and Mitigating BERT'S Gender Bias

technical paper

stages 

COLING, the International Conference on Computational Linguistics, is one of the premier conferences for natural language processing and computational linguistics. Often grouped within the field of artificial intelligence, but actually pre-dating the development of artificial intelligence, advances in computational linguistics and natural language processing are now some of the major drivers behind the use of artificial intelligence for commercial and social applications – for example, on-line search, machine translation and with voice-assisted conversational devices.

First established in 1965, the biennial COLING conference is held in diverse parts of the globe and attracts participants from both top-ranked research centers and emerging countries. Today, the most important developments in our field are taking place not only in universities and academic research institutes, but also in industrial research departments and in technological startups. COLING conferences provide opportunities for all these communities to showcase their exciting developments.

COLING, the International Conference on Computational Linguistics, is one of the premier conferences for natural language processing and computational linguistics. Often grouped within the field of artificial intelligence, but actually pre-dating the development of artificial intelligence, advances in computational linguistics and natural language processing are now some of the major drivers behind the use of artificial intelligence for commercial and social applications – for example, on-line search, machine translation and with voice-assisted conversational devices.

Recent years have seen a surge in research on the biases in word embeddings with respect to gender and, to a lesser extent, race. Few of these studies, however, have given attention to the critical intersection of race and gender. In this case study, we analyze the dimensions of gender and race in contextualized word embeddings of given names, taken from BERT, and investigate the nature and nuance of their interaction. We find that these demographic axes, though typically treated as physically and conceptually separate, are in fact interdependent and thus inadvisable to consider in isolation. Further, we show that demographic dimensions predicated on default settings in language, such as in pronouns, may risk rendering groups with multiple marginalized identities invisible. We conclude by discussing the importance and implications of intersectionality for future studies on bias and debiasing in NLP.

Interdependencies of Gender and Race in Contextualized Word Embeddings

Recent research in Natural Language Processing has revealed that word embeddings can encode social biases present in the training data which can affect minorities in real world applications. This paper explores the gender bias implicit in Dutch embeddings while investigating whether English language based approaches can also be used in Dutch. We implement the Word Embeddings Association Test (WEAT), Clustering and Sentence Embeddings Association Test (SEAT) methods to quantify the gender bias in Dutch word embeddings, then we proceed to reduce the bias with Hard-Debias and Sent-Debias mitigation methods and finally we evaluate the performance of the debiased embeddings in downstream tasks. The results suggest that, among others, gender bias is present in traditional and contextualized Dutch word embeddings. We highlight how techniques used to measure and reduce bias created for English can be used in Dutch embeddings by adequately translating the data and taking into account the unique characteristics of the language. Furthermore, we analyze the effect of the debiasing techniques on downstream tasks which show a negligible impact on traditional embeddings and a 2% decrease in performance in contextualized embeddings.

Evaluating Bias In Dutch Word Embeddings

Gender bias in models and datasets is widely studied in NLP. The focus has usually been on analysing how females and males express themselves, or how females and males are described. However, a less studied aspect is the combination of these two perspectives, how female and male describe the same or opposite gender. In this paper, we present a new gender annotated sentiment dataset of critics reviewing the works of female and male authors. We investigate if this newly annotated dataset contains differences in how the works of male and female authors are critiqued, in particular in terms of positive and negative sentiment. We also explore the differences in how this is done by male and female critics. We show that there are differences in how critics assess the works of authors of the same or opposite gender. For example, male critics rate crime novels written by females, and romantic and sentimental works written by males, more negatively.

Gender and sentiment, critics and authors: a dataset of Norwegian book reviews

Product descriptions in e-commerce platforms contain detailed and valuable information about the retailers’ assortment. In particular, coding promotions within digital leaflets are of great interest in e-commerce as they capture the attention of consumers by showing regular promotions for different products. However, this information is embedded into images, making it difficult to extract and process for downstream tasks. In this paper, we present an end-to-end approach that classifies promotions within digital leaflets into their corresponding product categories using both visual and textual information. Our approach can be divided into three key components: 1) region detection, 2) text recognition and 3) text classification. In many cases, a single promotion refers to multiple product categories, so we introduce a multi-label objective in the classification head. We demonstrate the effectiveness of our approach for two separated tasks: 1) image-based detection of the descriptions for each individual promotion and 2) multi-label classification of the product categories using the text from the product descriptions. We train and evaluate our models using a private dataset composed of images from digital leaflets. Results show that we consistently outperform the proposed baseline by a large margin in all the experiments.

Multi-label classification of promotions in digital leaflets using textual and visual information

We show how alternative data sources can be used for detailed, neartime inflation monitoring. We make use of web-scraped product data for online supermarkets and classify them in to the inflation basket. Furthermore we show how to transfer knowledge from German to French using multilingual embeddings and how to efficently labeld a new data set using active learning.

Bilingual Transfer Learning for Online Product Classification

We propose a novel way of conversational recommendation, where instead of asking questions to the user to acquire their preferences; the recommender tracks their conversation with other people, including customer support agents (CSA), and joins the conversation only when it is time to introduce a recommendation. Building a recommender that joins a human conversation (RJC), we propose information extraction, discourse and argumentation analyses, as well as dialogue management techniques to compute a recommendation for a product and service that is needed by the customer, as inferred from the conversation. A special case of such conversations is considered where the customer raises his problem with CSA in an attempt to resolve it, along with receiving a recommendation for a product with features addressing this problem. We evaluate performance of RJC is in a number of human-human and human-chat bot dialogues, and demonstrate that RJC is an efficient and less intrusive way to provide high relevance and persuasive recommendations.

Interrupt me Politely: Recommending Products and Services by 
Joining Human Conversation

Online customer reviews are of growing importance for many businesses in the hospitality industry, particularly restaurants and hotels. Managerial responses to such reviews provide businesses with the opportunity to influence the public discourse and to attain improved ratings over time. However, responding to each and every review is a time-consuming endeavour. Therefore, we investigate automatic generation of review responses in the hospitality domain for two languages, English and German. 

We apply an existing system, originally proposed for review response generation for smartphone apps. This approach employs an extended neural network sequence-to-sequence architecture and performs well in the original domain. However, as shown through our experiments, when applied to a new domain, such as hospitality, performance drops considerably. Therefore, we analyse potential causes for the differences in performance and provide evidence to suggest that review response generation in the hospitality domain is a more challenging task and thus requires further study and additional domain adaptation techniques.

Benchmarking Automated Review Response Generation for the Hospitality Domain

We tackle tag-based query refinement as a mobile-friendly alternative to standard facet search. We approach the inference challenge with reinforcement learning, and propose a deep contextual bandit that can be efficiently scaled in a multi-tenant SaaS scenario.

Blending Search and Discovery: Tag-Based Query Refinement with Contextual Reinforcement Learning

Information retrieval chatbots are widely used as assistants, to help users formulate their requirements about the products they want to purchase and navigate to the set of items that satisfies their requirements in the best way. The work of the modern chatbots is based mostly on the deep learning theory behind the knowledge model that can improve the performance of the system. In our work, we are developing a concept-based knowledge model that encapsulates objects and their common descriptions. The leveraging of the concept-based knowledge model allows the system to refine the initial users’ requests and lead them to the set of objects with the maximal variability of parameters that matters less to them. Introducing the additional textual characteristics allows users to formulate their initial query as a phrase in natural language, rather than as some standard request in the form of, “Attribute - value”.

On a Chatbot Navigating a User through a Concept-Based Knowledge Model

Product matching, i.e., being able to infer the product being sold for a merchant-created offer, is crucial for any e-commerce marketplace, enabling product-based navigation, price comparisons, product reviews, etc. This problem proves a challenging task, mostly due to the extent of product catalog, data heterogeneity, missing product representants, and varying levels of data quality. Moreover, new products are being introduced every day, making it difficult to cast the problem as a classification task. 
In this work, we apply BERT-based models in a similarity learning setup to solve the product matching problem. We provide a thorough ablation study, showing the impact of architecture and training objective choices. Application of transformer-based architectures and proper sampling techniques significantly boosts performance for a range of e-commerce domains, allowing for production deployment.

Downloads

Next from COLING 2020

Interdependencies of Gender and Race in Contextualized Word Embeddings

Similar lecture

Towards Fairer NLP Models: Handling Gender Bias In Classification Tasks

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from COLING 2020

Interdependencies of Gender and Race in Contextualized Word Embeddings

Similar lecture

Towards Fairer NLP Models: Handling Gender Bias In Classification Tasks

Downloads