Skill Extraction (SE) is an important and widely-studied task useful to gain insights into labor market dynamics. However, there is a lacuna of datasets and annotation guidelines; available datasets are few and contain crowd-sourced labels on the span-level or labels from a predefined skill inventory. To address this gap, we introduce SKILLSPAN, a novel SE dataset consisting of 14.5K sentences and over 12.5K annotated spans. We release its respective guidelines created over three different sources annotated for hard and soft skills by domain experts. We introduce a BERT baseline (Devlin et al., 2019). To improve upon this baseline, we experiment with language models that are optimized for long spans (Joshi et al., 2020; Beltagy et al., 2020), continuous pre-training on the job posting domain (Han and Eisenstein, 2019; Gururangan et al., 2020), and multi-task learning (Caruana, 1997). Our results show that the domain-adapted models significantly outperform their non-adapted counterparts, and single-task outperforms multi-task learning.

Skill Classification (SC) is the task of classifying job competences from job postings. This work is the first in SC applied to Danish job vacancy data. We release the first Danish job posting dataset: *Kompetencer* (_en_: competences), annotated for nested spans of competences. To improve upon coarse-grained annotations, we make use of The European Skills, Competences, Qualifications and Occupations (ESCO; le Vrang et al., (2014)) taxonomy API to obtain fine-grained labels via distant supervision. We study two setups: The zero-shot and few-shot classification setting. We fine-tune English-based models and RemBERT (Chung et al., 2020) and compare them to in-language Danish models. Our results show RemBERT significantly outperforms all other models in both the zero-shot and the few-shot setting.

The field of Deep Learning (DL) has undergone explosive growth during the last decade, with a substantial impact on Natural Language Processing (NLP) as well. Yet, compared to more established disciplines, a lack of common experimental standards remains an open challenge to the field at large. Starting from fundamental scientific principles, we distill ongoing discussions on experimental standards in NLP into a single, widely-applicable methodology. Following these best practices is crucial to strengthen experimental evidence, improve reproducibility and enable scientific progress. These standards are further collected in a public repository to help them transparently adapt to future needs.

With the increase in availability of large pre-trained language models (LMs) in Natural Language Processing (NLP), it becomes critical to assess their fit for a specific target task a priori—as fine-tuning the entire space of available LMs is computationally prohibitive and unsustainable. However, encoder transferability estimation has received little to no attention in NLP. In this paper, we propose to generate quantitative evidence to predict which LM, out of a pool of models, will perform best on a target task without having to fine-tune all candidates. We provide a comprehensive study on LM ranking for 10 NLP tasks spanning the two fundamental problem types of classification and structured prediction. We adopt the state-of-the-art Logarithm of Maximum Evidence (LogME) measure from Computer Vision (CV) and find that it positively correlates with final LM performance in 94% of the setups.In the first study of its kind, we further compare transferability measures with the de facto standard of human practitioner ranking, finding that evidence from quantitative metrics is more robust than pure intuition and can help identify unexpected LM candidates.

We propose Cartography Active Learning (CAL), a novel Active Learning (AL) algorithm that exploits the behavior of the model on individual instances during training as a proxy to find the most informative instances for labeling. CAL is inspired by data maps, which were recently proposed to derive insights into dataset quality (Swayamdipta et al., 2020). We compare our method on popular text classification tasks to commonly used AL strategies, which instead rely on post-training behavior. We demonstrate that CAL is competitive to other common AL methods, showing that training dynamics derived from small seed data can be successfully used for AL. We provide insights into our new AL method by analyzing batch-level statistics utilizing the data maps. Our results further show that CAL results in a more data-efficient learning strategy, achieving comparable or better results with considerably less training data.

De-identification is the task of detecting privacy-related entities in text, such as person names, emails and contact data. It has been well-studied within the medical domain. The need for de-identification technology is increasing, as privacy-preserving data handling is in high demand in many domains. In this paper, we focus on job postings. We present JobStack, a new corpus for de-identification of personal data in job vacancies on Stackoverflow. We introduce baselines, comparing Long-Short Term Memory (LSTM) and Transformer models. To improve these baselines, we experiment with BERT representations, and distantly related auxiliary data via multi-task learning. Our results show that auxiliary data helps to improve de-identification performance. While BERT representations improve performance, surprisingly “vanilla” BERT turned out to be more effective than BERT trained on Stackoverflow-related data.

The effect of translationese has been studied in the field of machine translation (MT), mostly with respect to training data. We study in depth the effect of translationese on test data, using the test sets from the last three editions of WMT’s news shared task, containing 17 translation directions. We show evidence that (i) the use of translationese in test sets results in inflated human evaluation scores for MT systems; (ii) in some cases system rankings do change and (iii) the impact translationese has on a translation direction is inversely correlated to the translation quality attainable by state-of-the-art MT systems for that direction.

Hate speech occurs more often than ever and polarizes society. To help counter this polarization, SemEval 2019 organizes a shared task called the Multilingual Detection of Hate. The first task (A) is to decide whether a given tweet contains hate against immigrants or women, in a multilingual perspective, for English and Spanish. In the second task (B), the system is also asked to classify the following sub-tasks: hateful tweets as aggressive or not aggressive, and to identify the target harassed as individual or generic. We evaluate multiple models, and finally combine them in an ensemble setting. This ensemble setting is built of five and three submodels for the English and Spanish task respectively. In the current setup it shows that using a bigger ensemble for English tweets performs mediocre, while a slightly smaller ensemble does work well for detecting hate speech in Spanish tweets. Our results on the test set for English show 0.378 macro F1 on task A and 0.553 macro F1 on task B. For Spanish the results are significantly higher, 0.701 macro F1 on task A and 0.734 macro F1 for task B.