Search Results for author:
Found 14 papers, 12 papers with code
BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models
To address this, and to facilitate researchers to broadly evaluate the effectiveness of their models, we introduce Benchmarking-IR (BEIR), a robust and heterogeneous evaluation benchmark for information retrieval.
Ranked #1 on
Argument Retrieval
on ArguAna (BEIR)
Learning to Reason for Text Generation from Scientific Tables
In this paper, we introduce SciGen, a new challenge dataset for the task of reasoning-aware data-to-text generation consisting of tables from scientific articles and their corresponding descriptions.
What to Pre-Train on? Efficient Intermediate Task Selection
Our best methods achieve an average Regret@3 of less than 1% across all target tasks, demonstrating that we are able to efficiently identify the best datasets for intermediate training.
TWEAC: Transformer with Extendable QA Agent Classifiers
We argue that there exist a wide range of specialized QA agents in literature.
AdapterDrop: On the Efficiency of Adapters in Transformers
Massively pre-trained transformer models are computationally expensive to fine-tune, slow for inference, and have large storage requirements.
Improving QA Generalization by Concurrent Modeling of Multiple Biases
Our framework weights each example based on the biases it contains and the strength of those biases in the training data.
MultiCQA: Zero-Shot Transfer of Self-Supervised Text Matching Models on a Massive Scale
We investigate the model performances on nine benchmarks of answer selection and question similarity tasks, and show that all 140 models transfer surprisingly well, where the large majority of models substantially outperforms common IR baselines.
AdapterHub: A Framework for Adapting Transformers
We propose AdapterHub, a framework that allows dynamic "stitching-in" of pre-trained adapters for different tasks and languages.
AdapterFusion: Non-Destructive Task Composition for Transfer Learning
We show that by separating the two stages, i. e., knowledge extraction and knowledge composition, the classifier can effectively exploit the representations learned from multiple tasks in a non-destructive manner.
Neural Duplicate Question Detection without Labeled Training Data
We show that our proposed approaches are more effective in many cases because they can utilize larger amounts of unlabeled data from cQA forums.
Improving Generalization by Incorporating Coverage in Natural Language Inference
Finally, we show that using the coverage information is not only beneficial for improving the performance across different datasets of the same task.
Pitfalls in the Evaluation of Sentence Embeddings
Our motivation is to challenge the current evaluation of sentence embeddings and to provide an easy-to-access reference for future research.
Text Processing Like Humans Do: Visually Attacking and Shielding NLP Systems
Visual modifications to text are often used to obfuscate offensive comments in social media (e. g., "! d10t") or as a writing style ("1337" in "leet speak"), among other scenarios.
Concatenated Power Mean Word Embeddings as Universal Cross-Lingual Sentence Representations
Here, we generalize the concept of average word embeddings to power mean word embeddings.
