Data is a critical resource for Machine Learning (ML), yet working with data remains a key friction point. This paper introduces Croissant, a metadata format for datasets that simplifies how data is used by ML tools and frameworks. Croissant makes datasets more discoverable, portable and interoperable, thereby addressing significant challenges in ML data management and responsible AI. Croissant is already supported by several popular dataset repositories, spanning hundreds of thousands of datasets, ready to be loaded into the most popular ML frameworks.

Data is critical to advancing AI technologies, yet its quality and documentation remain significant challenges, leading to adverse downstream effects (e.g., potential biases) in AI applications. This paper addresses these issues by introducing Croissant-RAI, a machine-readable metadata format designed to enhance the discoverability, interoperability, and trustworthiness of AI datasets. Croissant-RAI extends the Croissant metadata format and builds upon existing responsible AI (RAI) documentation frameworks, offering a standardized set of attributes and practices to facilitate community-wide adoption. Leveraging established web-publishing practices, such as Schema.org, Croissant-RAI enables dataset users to easily find and utilize RAI metadata regardless of the platform on which the datasets are published. Furthermore, it is seamlessly integrated into major data search engines, repositories, and machine learning frameworks, streamlining the reading and writing of responsible AI metadata within practitioners' existing workflows. Croissant-RAI was developed through a community-led effort. It has been designed to be adaptable to evolving documentation requirements and is supported by a Python library and a visual editor.

This research explores automated text classification using data from Low- and Middle-Income Countries (LMICs). In particular, we explore enhancing text representations with demographic information of speakers in a privacy-preserving manner. We introduce the Demographic-Rich Qualitative UPV-Interviews Dataset (DR-QI), a rich dataset of qualitative interviews from rural communities in India and Uganda. The interviews were conducted following the latest standards for respectful interactions with illiterate speakers (Hirmer et al., 2021a). The interviews were later sentence-annotated for Automated User-Perceived Value (UPV) Classification (Conforti et al., 2020), a schema that classifies values expressed by speakers, resulting in a dataset of 5,333 sentences. We perform the UPV classification task, which consists of predicting which values are expressed in a given sentence, on the new DR-QI dataset. We implement a classification model using DistilBERT (Sanh et al., 2019), which we extend with demographic information. In order to preserve the privacy of speakers, we investigate encoding demographic information using autoencoders. We find that adding demographic information improves performance, even if such information is encoded. In addition, we find that the performance per UPV is linked to the number of occurrences of that value in our data.

Understanding consumer needs and values is crucial to the sustainable delivery and uptake of energy access projects in Low-and Middle-Income Countries (LMICs). Nevertheless, many energy projects aim to empower women without first assessing gendered roles, needs, values, and relations for both men and women in project communities. Neglecting these can be detrimental to the end-users of energy projects, exacerbating conflict within households rather than empowering vulnerable groups. We propose a value-based approach to elicit the varying priorities and values of men and women and assess how these may shape energy access project design and communication in LMICs. Data from 84 qualitative individual interviews, equally split between men and women, and 28 gender-disaggregated focus-group discussions in seven rural Ugandan communities were used. We find that men and women in rural Uganda held largely the same high-priority underlying values focused on basic human needs such as income, healthcare, information services, food security, and water security. However, the language used to communicate these values differed in small but significant ways. Based on this, we offer two potential solutions for a more balanced gender-inclusive approach to energy service project design and communication: (1) Design projects and messaging based on underlying values of both genders while avoiding inadvertently reproducing patriarchal norms; and (2) use gender-specific messaging and vocabulary1 linking energy projects to underlying values to increase buy-in. This work constitutes a first step in better understanding the importance of gender-disaggregated data in decision-making for energy access initiatives in LMICs.

Research in stance detection has so far focused on models which leverage purely textual input. In this paper, we investigate the integration of textual and financial signals for stance detection in the financial domain. Specifically, we propose a robust multi-task neural architecture that combines textual input with high-frequency intra-day time series from stock market prices. Moreover, we extend wt–wt, an existing stance detection dataset which collects tweets discussing Mergers and Acquisitions operations, with the relevant financial signal. Importantly, the obtained dataset aligns with Stander, an existing news stance detection dataset, thus resulting in a unique multimodal, multi-genre stance detection resource. We show experimentally and through detailed result analysis that our stance detection system benefits from financial information, and achieves state-of-the-art results on the wt–wt dataset: this demonstrates that the combination of multiple input signals is effective for cross-target stance detection, and opens interesting research directions for future work.

Cross-target generalization constitutes an important issue for news Stance Detection (SD). In this short paper, we investigate adversarial cross-genre SD, where knowledge from annotated user-generated data is leveraged to improve news SD on targets unseen during training. We implement a BERT-based adversarial network and show experimental performance improvements over a set of strong baselines. Given the abundance of user-generated data, which are considerably less expensive to retrieve and annotate than news articles, this constitutes a promising research direction.

We introduce 9 guiding principles to integrate Participatory Design (PD) methods in the development of Natural Language Processing (NLP) systems. The adoption of PD methods by NLP will help to alleviate issues concerning the development of more democratic, fairer, less-biased technologies to process natural language data. This short paper is the outcome of an ongoing dialogue between designers and NLP experts and adopts a non-standard format following previous work by Traum (2000); Bender (2013); Abzianidze and Bos (2019). Every section is a guiding principle. While principles 1–3 illustrate assumptions and methods that inform community-based PD practices, we used two fictional design scenarios (Encinas and Blythe, 2018), which build on top of situations familiar to the authors, to elicit the identification of the other 6. Principles 4–6 describes the impact of PD methods on the design of NLP systems, targeting two critical aspects: data collection & annotation, and the deployment & evaluation. Finally, principles 7–9 guide a new reflexivity of the NLP research with respect to its context, actors and participants, and aims. We hope this guide will offer inspiration and a road-map to develop a new generation of PD-inspired NLP.

This article describes a dataset of perceived values and socioeconomic indicators collected in rural Ugandan communities. The data were collected in interviews which employed: (1) the User-Perceived Value game, which solicits verbal data using graphical prompts and ‘why’-probing; and (2) socio-economic surveys, which collected demographic data. The dataset constitutes 119 interviews conducted between 2014 and 2015 in seven rural Ugandan villages. Interviews were conducted in various settings (e.g. individual/group, women/men/mixed) and in seven different local languages (which were subsequently translated into English). These interviews were part of a research project aiming to better understand what is important to rural communities in Uganda, and to investigate decision-making as a function of different demographics. This dataset can be used by researchers and practitioners in various fields such as sustainable development (e.g. to analyze how development initiatives may be designed to match community values) and natural language processing (e.g. to automatically perform perceived value classification from the expert-annotated interviews).

Cross-target generalization is a known problem in stance detection (SD), where systems tend to perform poorly when exposed to targets unseen during training. Given that data annotation is expensive and time-consuming, finding ways to leverage abundant unlabeled in-domain data can offer great benefits. In this paper, we apply a weakly supervised framework to enhance cross-target generalization through synthetically annotated data. We focus on Twitter SD and show experimentally that integrating synthetic data is helpful for cross-target generalization, leading to significant improvements in performance, with gains in F1 scores ranging from +3.4 to +5.1.

Stance detection (SD) entails classifying the sentiment of a text towards a given target, and is a relevant sub-task for opinion mining and social media analysis. Recent works have explored knowledge infusion supplementing the linguistic competence and latent knowledge of large pre-trained language models with structured knowledge graphs (KGs), yet few works have applied such methods to the SD task. In this work, we first perform stance-relevant knowledge probing on Transformers-based pre-trained models in a zero-shot setting, showing these models' latent real-world knowledge about SD targets and their sensitivity to context. We then train and evaluate new knowledge-enriched stance detection models on two Twitter stance datasets, achieving state-of-the-art performance on both.

Dataset (JSON and CSV files) of 119 interviews conducted between 2014 and 2015 in seven rural Ugandan villages from surveys and face-to-face interviews.

Most well-established data collection methods currently adopted in NLP depend on the as- sumption of speaker literacy. Consequently, the collected corpora largely fail to represent swathes of the global population, which tend to be some of the most vulnerable and marginalised people in society, and often live in rural developing areas. Such underrepresented groups are thus not only ignored when making modeling and system design decisions, but also prevented from benefiting from development outcomes achieved through data-driven NLP. This paper aims to address the under-representation of illiterate communities in NLP corpora: we identify potential biases and ethical issues that might arise when collecting data from rural communities with high illiteracy rates in Low-Income Countries, and propose a set of practical mitigation strategies to help future work.

In recent years, there has been an increasing interest in the application of Artificial Intelligence - and especially Machine Learning - to the field of Sustainable Development (SD). However, until now, NLP has not been applied in this context. In this research paper, we show the high potential of NLP applications to enhance the sustainability of projects. In particular, we focus on the case of community profiling in developing countries, where, in contrast to the developed world, a notable data gap exists. In this context, NLP could help to address the cost and time barrier of structuring qualitative data that prohibits its widespread use and associated benefits. We propose the new task of Automatic UPV classification, which is an extreme multi-class multi-label classification problem. We release Stories2Insights, an expert-annotated dataset, provide a detailed corpus analysis, and implement a number of strong neural baselines to address the task. Experimental results show that the problem is challenging, and leave plenty of room for future research at the intersection of NLP and SD.

We present a new challenging news dataset that targets both stance detection (SD) and fine-grained evidence retrieval (ER). With its 3,291 expert-annotated articles, the dataset constitutes a high-quality benchmark for future research in SD and multi-task learning. We provide a detailed description of the corpus collection methodology and carry out an extensive analysis on the sources of disagreement between annotators, observing a correlation between their disagreement and the diffusion of uncertainty around a target in the real world. Our experiments show that the dataset poses a strong challenge to recent state-of-the-art models. Notably, our dataset aligns with an existing Twitter SD dataset: their union thus addresses a key shortcoming of previous works, by providing the first dedicated resource to study multi-genre SD as well as the interplay of signals from social media and news sources in rumour verification.

We present a new challenging stance detection dataset, called Will-They-Won't-They (WT-WT), which contains 51,284 tweets in English, making it by far the largest available dataset of the type. All the annotations are carried out by experts; therefore, the dataset constitutes a high-quality and reliable benchmark for future research in stance detection. Our experiments with a wide range of recent state-of-the-art stance detection systems show that the dataset poses a strong challenge to existing models in this domain.

AbstractIn this work, we focus on the task of open-type relation argument extraction (ORAE): given a corpus, a query entity Q, and a knowledge base relation (e.g., “Q authored notable work with title X”), the model has to extract an argument of non-standard entity type (entities that cannot be extracted by a standard named entity tagger, for example, X: the title of a book or a work of art) from the corpus. We develop and compare a wide range of neural models for this task yielding large improvements over a strong baseline obtained with a neural question answering system. The impact of different sentence encoding architectures and answer extraction methods is systematically compared. An encoder based on gated recurrent units combined with a conditional random fields tagger yields the best results. We release a data set to train and evaluate ORAE, based on Wikidata and obtained by distant supervision.

In this paper, we propose to adapt the four-staged pipeline proposed by Zubiaga et al. (2018) for the Rumor Verification task to the problem of Fake News Detection. We show that the recently released FNC-1 corpus covers two of its steps, namely the Tracking and the Stance Detection task. We identify asymmetry in length in the input to be a key characteristic of the latter step, when adapted to the framework of Fake News Detection, and propose to handle it as a specific type of Cross-Level Stance Detection. Inspired by theories from the field of Journalism Studies, we implement and test two architectures to successfully model the internal structure of an article and its interactions with a claim.

Translation to morphologically rich languages is a difficult task because of sparsity caused by morphological richness. In this work we perform a pilot study on predicting the morphologically rich POS tags of sequences of lemmas. Similar studies have been conducted in the context of phrase-based statistical machine translation. We implement a state-of-the-art tagger taking lemmas as input and show that we can successfully predict the morphologically rich POS tags, with accuracies of up to 91%.