76 citations · 148 across the 26 of their papers we have counts for
5 papers · 1 filter
Exploring Anisotropy and Outliers in Multilingual Language Models for Cross-Lingual Semantic Sentence Similarity
Katharina Hämmerl, Alina Fastowski, Jindřich Libovický +1
Previous work has shown that the representations output by contextual language models are more anisotropic than static type embeddings, and typically display outlier dimensions. Th…
On the Copying Problem of Unsupervised NMT: A Training Schedule with a Language Discriminator Loss
Yihong Liu, Alexandra Chronopoulou, Hinrich Schütze +1
Although unsupervised neural machine translation (UNMT) has achieved success in many language pairs, the copying problem, i.e., directly copying some parts of the input sentence as…
How to Solve Few-Shot Abusive Content Detection Using the Data We Actually Have
Viktor Hangya, Alexander Fraser
Due to the broad range of social media platforms, the requirements of abusive language detection systems are varied and ever-changing. Already a large set of annotated corpora with…
Mitigating Data Imbalance and Representation Degeneration in Multilingual Machine Translation
Wen Lai, Alexandra Chronopoulou, Alexander Fraser
Despite advances in multilingual neural machine translation (MNMT), we argue that there are still two major challenges in this area: data imbalance and representation degeneration.…
AdapterSoup: Weight Averaging to Improve Generalization of Pretrained Language Models
Alexandra Chronopoulou, Matthew E. Peters, Alexander Fraser +1
Pretrained language models (PLMs) are trained on massive corpora, but often need to specialize to specific domains. A parameter-efficient adaptation method suggests training an ada…