The open-access dissemination of pretrained language models through online repositories has led to a democratization of state-of-the-art natural language processing (NLP) research.This also allows people outside of NLP to use such models and adapt them to specific use-cases.However, a certain amount of technical proficiency is still required which is an entry barrier for users who want to apply these models to a certain task but lack the necessary knowledge or resources.In this work, we aim to overcome this gap by providing a tool which allows researchers to leverage pretrained models without writing a single line of code.Built upon the parameter-efficient adapter modules for transfer learning, our AdapterHub Playground provides an intuitive interface, allowing the usage of adapters for prediction, training and analysis of textual data for a variety of NLP tasks.We present the tool’s architecture and demonstrate its advantages with prototypical use-cases, where we show that predictive performance can easily be increased in a few-shot learning scenario.Finally, we evaluate its usability in a user study.We provide the code and a live interface at https://adapter-hub.github.io/playground.

Identifying the relation between two sentences requires datasets with pairwise annotations. In many cases, these datasets contain instances that are annotated multiple times as part of different pairs. They constitute a structure that contains additional helpful information about the inter-relatedness of the text instances based on the annotations. This paper investigates how this kind of structural dataset information can be exploited during training.We propose three batch composition strategies to incorporate such information and measure their performance over 14 heterogeneous pairwise sentence classification tasks. Our results show statistically significant improvements (up to 3.9%) - independent of the pre-trained language model - for most tasks compared to baselines that follow a standard training procedure. Further, we see that even this baseline procedure can profit from having such structural information in a low-resource setting.

Language use changes over time, and this impacts the effectiveness of NLP systems. This phenomenon is even more prevalent in social media data during crisis events where meaning and frequency of word usage may change over the course of days. Contextual language models fail to adapt temporally, emphasizing the need for temporal adaptation in models which need to be deployed over an extended period of time. While existing approaches consider data spanning large periods of time (from years to decades), shorter time spans are critical for crisis data. We quantify temporal degradation for this scenario and propose methods to cope with performance loss by leveraging techniques from domain adaptation. To the best of our knowledge, this is the first effort to explore effects of rapid language change driven by adversarial adaptations, particularly during natural and human-induced disasters. Through extensive experimentation on diverse crisis datasets, we analyze under what conditions our approaches outperform strong baselines while highlighting the current limitations of temporal adaptation methods in scenarios where access to unlabeled data is scarce.

Transformer models are expensive to fine-tune, slow for inference, and have large storage requirements. Recent approaches tackle these shortcomings by training smaller models, dynamically reducing the model size, and by training light-weight adapters. In this paper, we propose AdapterDrop, removing adapters from lower transformer layers during training and inference, which incorporates concepts from all three directions. We show that AdapterDrop can dynamically reduce the computational overhead when performing inference over multiple tasks simultaneously, with minimal decrease in task performances. We further prune adapters from AdapterFusion, which improves the inference efficiency while maintaining the task performances entirely.

This work investigates the use of interactively updated label suggestions to improve upon the efficiency of gathering annotations on the task of opinion mining in German Covid-19 social media data. We develop guidelines to conduct a controlled annotation study with social science students and find that suggestions from a model trained on a small, expert-annotated dataset already lead to a substantial improvement – in terms of inter-annotator agreement (+.14 Fleiss’ κ) and annotation quality – compared to students that do not receive any label suggestions. We further find that label suggestions from interactively trained models do not lead to an improvement over suggestions from a static model. Nonetheless, our analysis of suggestion bias shows that annotators remain capable of reflecting upon the suggested label in general. Finally, we confirm the quality of the annotated data in transfer learning experiments between different annotator groups. To facilitate further research in opinion mining on social media data, we release our collected data consisting of 200 expert and 2,785 student annotations.

We experiment with two recent contextualized word embedding methods (ELMo and BERT) in the context of open-domain argument search. For the first time, we show how to leverage the power of contextualized word embeddings to classify and cluster topic-dependent arguments, achieving impressive results on both tasks and across multiple datasets. For argument classification, we improve the state-of-the-art for the UKP Sentential Argument Mining Corpus by 20.8 percentage points and for the IBM Debater - Evidence Sentences dataset by 7.4 percentage points. For the understudied task of argument clustering, we propose a pre-training step which improves by 7.8 percentage points over strong baselines on a novel dataset, and by 12.3 percentage points for the Argument Facet Similarity (AFS) Corpus.