S-LDA: Documents Classification Enrichment for Information Retrieval

Drissi, Amani; Tissaoui, Anis; Sassi, Salma; Chbeir, Richard; Jemai, Abderrazak

doi:10.1007/978-3-031-16210-7_56

Cited by 2 publications

(1 citation statement)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Retrieval augmented methods have been widely used in many Natural Language Processing (NLP) tasks, such as question answering (Yang et al, 2021;Mao et al, 2021), semantic parsing (Pasupat et al, 2021;Dong et al, 2023), code generation (Lu et al, 2022), classification (Drissi et al, 2022;Gur et al, 2021), etc. Existing retrieval-augmented models attached several retrieved texts as knowledge to the original inputs to improve performance.…”

Section: Introductionmentioning

confidence: 99%

Retrieval-Augmented Classification with Decoupled Representation

Liang¹,

Wu²,

Huang³

et al. 2023

Preprint

View full text Add to dashboard Cite

Retrieval augmented methods have shown promising results in various classification tasks. However, existing methods focus on retrieving extra context to enrich the input, which is noise sensitive and non-expandable. In this paper, following this line, we propose a k-nearest-neighbor (KNN) -based method for retrieval augmented classifications, which interpolates the predicted label distribution with retrieved instances' label distributions. Different from the standard KNN process, we propose a decoupling mechanism as we find that shared representation for classification and retrieval hurts performance and leads to training instability. We evaluate our method on a wide range of classification datasets. Experimental results demonstrate the effectiveness and robustness of our proposed method. We also conduct extra experiments to analyze the contributions of different components in our model. 1

show abstract