Fine-tuning vs From Scratch: Do Vision & Language Models Have Similar Capabilities on Out-of-Distribution Visual Question Answering?

no code implementations • LREC 2022 • Kristian Nørgaard Jensen, Barbara Plank

Fine-tuning general-purpose pre-trained models has become a de-facto standard, also for Vision and Language tasks such as Visual Question Answering (VQA).

Question Answering Visual Question Answering

Skill Extraction from Job Postings using Weak Supervision

1 code implementation • 16 Sep 2022 • Mike Zhang, Kristian Nørgaard Jensen, Rob van der Goot, Barbara Plank

Aggregated data obtained from job postings provide powerful insights into labor market demands, and emerging skills, and aid job matching.

Kompetencer: Fine-grained Skill Classification in Danish Job Postings via Distant Supervision and Transfer Learning

2 code implementations • LREC 2022 • Mike Zhang, Kristian Nørgaard Jensen, Barbara Plank

Skill Classification (SC) is the task of classifying job competences from job postings.

Transfer Learning

SkillSpan: Hard and Soft Skill Extraction from English Job Postings

2 code implementations • NAACL 2022 • Mike Zhang, Kristian Nørgaard Jensen, Sif Dam Sonniks, Barbara Plank

We introduce a BERT baseline (Devlin et al., 2019).

Multi-Task Learning

DaN+: Danish Nested Named Entities and Lexical Normalization

1 code implementation • COLING 2020 • Barbara Plank, Kristian Nørgaard Jensen, Rob van der Goot

We examine language-specific versus multilingual BERT, and study the effect of lexical normalization on NER.

Cross-Lingual Transfer Lexical Normalization +4

De-identification of Privacy-related Entities in Job Postings

1 code implementation • NoDaLiDa 2021 • Kristian Nørgaard Jensen, Mike Zhang, Barbara Plank

We present JobStack, a new corpus for de-identification of personal data in job vacancies on Stackoverflow.

De-identification Multi-Task Learning +1