| 3 |
TSDAE: Using Transformer-based Sequential Denoising Auto-Encoder for Unsupervised Sentence Embedding Learning ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 4 |
The Curse of Dense Low-Dimensional Information Retrieval for Large Index Sizes ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 5 |
BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 6 |
GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrieval ...
|
|
|
|
Abstract:
Dense retrieval approaches can overcome the lexical gap and lead to significantly improved search results. However, they require large amounts of training data which is not available for most domains. As shown in previous work (Thakur et al., 2021b), the performance of dense retrievers severely degrades under a domain shift. This limits the usage of dense retrieval approaches to only a few domains with large training datasets. In this paper, we propose the novel unsupervised domain adaptation method Generative Pseudo Labeling (GPL), which combines a query generator with pseudo labeling from a cross-encoder. On six representative domain-specialized datasets, we find the proposed GPL can outperform an out-of-the-box state-of-the-art dense retrieval approach by up to 9.3 points nDCG@10. GPL requires less (unlabeled) data from the target domain and is more robust in its training than previous methods. We further investigate the role of six recent pre-training methods in the scenario of domain adaptation for ... : Accepted at NAACL 2022 ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences; Information Retrieval cs.IR
|
|
URL: https://arxiv.org/abs/2112.07577
https://dx.doi.org/10.48550/arxiv.2112.07577
|
|
BASE
|
|
Hide details
|
|
|
| 7 |
Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 8 |
Revisiting Joint Modeling of Cross-document Entity and Event Coreference Resolution ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 9 |
Optimal Hyperparameters for Deep LSTM-Networks for Sequence Labeling Tasks ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 11 |
GermEval-2014: Nested Named Entity Recognition with Neural Networks
|
|
|
|
BASE
|
|
Show details
|
|
|
|
|
