Can a Frozen Pretrained Language Model be used for Zero-shot Neural Retrieval on Entity-centric Questions?

2023-03-09 · Yasuto Hoshi, Daisuke Miyashita, Yasuhiro Morioka, Youyang Ng, Osamu Torii, Jun Deguchi

Neural document retrievers, including dense passage retrieval (DPR), have outperformed classical lexical-matching retrievers, such as BM25, when fine-tuned and tested on specific question-answering datasets. However, it has been shown that the existing dense retrievers do not generalize well not only out of domain but even in domain such as Wikipedia, especially when a named entity in a question is a dominant clue for retrieval. In this paper, we propose an approach toward in-domain generalization using the embeddings generated by the frozen language model trained with the entities in the domain. By not fine-tuning, we explore the possibility that the rich knowledge contained in a pretrained language model can be used for retrieval tasks. The proposed method outperforms conventional DPRs on entity-centric questions in Wikipedia domain and achieves almost comparable performance to BM25 and state-of-the-art SPAR model. We also show that the contextualized keys lead to strong improvements compared to BM25 when the entity names consist of common words. Our results demonstrate the feasibility of the zero-shot retrieval method for entity-centric questions of Wikipedia domain, where DPR has struggled to perform.

📄 PDF Abstract BibTeX arXiv:2303.05153

Code (0)

등록된 구현이 없습니다.

Tasks

Domain GeneralizationLanguage ModelingLanguage Modelling Passage Retrieval Question Answering Retrieval

Zero-Shot Video Question Answering via Frozen Bidirectional Language Models

2022-06-16 · Antoine Yang, Antoine Miech, Josef Sivic, Ivan Laptev 외

Video question answering (VideoQA) is a complex task that requires diverse multi-modal data for training. Manual annotation of question and answers for videos, however, is tedious and prohibits scalability. To tackle thi…

Fill Mask Language Modeling Language Modelling Masked Language Modeling+8

Zero-Shot and Few-Shot Video Question Answering with Multi-Modal Prompts

2023-09-27 · Deniz Engin, Yannis Avrithis

Recent vision-language models are driven by large-scale pretrained models. However, adapting pretrained models on limited data presents challenges such as overfitting, catastrophic forgetting, and the cross-modal gap bet…

Few-shot Video Question Answering Prompt Learning Question Answering Video Question Answering+1

Frozen Pretrained Transformers for Neural Sign Language Translation

2021-08-20 · International Workshop on Automatic Translation for Signed and Spoken Languages (AT4SSL) 2021 8 · Mathieu De Coster, Karel D'Oosterlinck, Marija Pizurica, Paloma Rabaey 외

One of the major challenges in sign language translation from a sign language to a spoken language is the lack of parallel corpora. Recent works have achieved promising results on the RWTH-PHOENIX-Weather 2014T dataset,…

Decoder Machine Translation Sign Language Translation Transfer Learning+1

ZEETAD: Adapting Pretrained Vision-Language Model for Zero-Shot End-to-End Temporal Action Detection

2023-11-01 · Thinh Phan, Khoa Vo, Duy Le, Gianfranco Doretto 외

Temporal action detection (TAD) involves the localization and classification of action instances within untrimmed videos. While standard TAD follows fully supervised learning with closed-set setting on large training dat…

Action Detection Classification Language Modeling Language Modelling+2

Novel Semantic Prompting for Zero-Shot Action Recognition

2026-03-09 · Salman Iqbal, Waheed Rehman arxiv

Zero-shot action recognition relies on transferring knowledge from vision-language models to unseen actions using semantic descriptions. While recent methods focus on temporal modeling or architectural adaptations to han…

Zero-Shot Action Recognition Action Understanding