Search Results for author:
Found 6 papers, 3 papers with code
RoToR: Towards More Reliable Responses for Order-Invariant Inputs
Mitigating positional bias of language models (LMs) for listwise inputs is a well-known and important problem (e. g., lost-in-the-middle).
Analyzing the Effectiveness of Listwise Reranking with Positional Invariance on Temporal Generalizability
This working note outlines our participation in the retrieval task at CLEF 2024.
ListT5: Listwise Reranking with Fusion-in-Decoder Improves Zero-shot Retrieval
We propose ListT5, a novel reranking approach based on Fusion-in-Decoder (FiD) that handles multiple candidate passages at both train and inference time.
Exploring the Practicality of Generative Retrieval on Dynamic Corpora
Benchmarking the performance of information retrieval (IR) is mostly conducted with a fixed set of documents (static corpora).
Towards standardizing Korean Grammatical Error Correction: Datasets and Annotation
We show that the model trained with our datasets significantly outperforms the currently used statistical Korean GEC system (Hanspell) on a wider range of error types, demonstrating the diversity and usefulness of the datasets.
SSMix: Saliency-Based Span Mixup for Text Classification
Data augmentation with mixup has shown to be effective on various computer vision tasks.
