861 Hits in 6.1 sec

Efficient Passage Retrieval with Hashing for Open-domain Question Answering

Ikuya Yamada, Akari Asai, Hannaneh Hajishirzi
2021 Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)   unpublished
Most state-of-the-art open-domain question answering systems use a neural retrieval model to encode passages into continuous vectors and extract them from a knowledge source.  ...  Compared with DPR, BPR substantially reduces the memory cost from 65GB to 2GB without a loss of accuracy on two standard open-domain question answering benchmarks: Natural Questions and TriviaQA.  ...  Acknowledgement We are grateful for the feedback and suggestions from the anonymous reviewers and the members of the UW NLP group.  ... 
doi:10.18653/v1/2021.acl-short.123 fatcat:xjp75dipubgjndc3p4nksfgsii

Open Domain Question Answering over Tables via Dense Retrieval [article]

Jonathan Herzig, Thomas Müller, Syrine Krichene, Julian Martin Eisenschlos
2021 arXiv   pre-print
Recent advances in open-domain QA have led to strong models based on dense retrieval, but only focused on retrieving textual passages.  ...  In this work, we tackle open-domain QA over tables for the first time, and show that retrieval can be improved by a retriever designed to handle tabular context.  ...  This work was completed in partial fulfillment for the PhD degree of the first author, which was also supported by a Google PhD fellowship.  ... 
arXiv:2103.12011v2 fatcat:jwrtnmv4lbhflf425xqmddyjsi

ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction [article]

Keshav Santhanam, Omar Khattab, Jon Saad-Falcon, Christopher Potts, Matei Zaharia
2021 arXiv   pre-print
In this work, we introduce ColBERTv2, a retriever that couples an aggressive residual compression mechanism with a denoised supervision strategy to simultaneously improve the quality and space footprint  ...  Neural information retrieval (IR) has greatly advanced search and other knowledge-intensive language tasks.  ...  As a further test of outof-domain generalization, we evaluate the strongest three models-ColBERTv2, SPLADEv2, and vanilla ColBERT-on retrieval for open-domain question answering, similar to the out-of-domain  ... 
arXiv:2112.01488v2 fatcat:vaucpjvuejbidiibss5pxgu7y4

Generative Retrieval for Long Sequences [article]

Hyunji Lee, Sohee Yang, Hanseok Oh, Minjoon Seo
2022 arXiv   pre-print
Text retrieval is often formulated as mapping the query and the target items (e.g., passages) to the same vector space and finding the item whose embedding is closest to that of the query.  ...  We also conjecture that generative retrieval is complementary to traditional retrieval, as we find that an ensemble of both outperforms homogeneous ensembles.  ...  an open domain multi-hop question answering dataset, which requires aggregating multiple Wikipedia passages through logical reasoning or sequential processing.  ... 
arXiv:2204.13596v1 fatcat:i2uu5j4qbjhfpambxfdcun47k4

Cluster-Former: Clustering-based Sparse Transformer for Long-Range Dependency Encoding [article]

Shuohang Wang, Luowei Zhou, Zhe Gan, Yen-Chun Chen, Yuwei Fang, Siqi Sun, Yu Cheng, Jingjing Liu
2021 arXiv   pre-print
This new design allows information integration beyond local windows, which is especially beneficial for question answering (QA) tasks that rely on long-range dependencies.  ...  However, despite its effectiveness in modeling short sequences, self-attention suffers when handling inputs with extreme long-range dependencies, as its complexity grows quadratically with respect to the  ...  ., 2017) : The goal of this task is to answer open-domain questions from Trivia Challenge. All the passages harvested through information retrieval can be used to answer questions.  ... 
arXiv:2009.06097v2 fatcat:stsmr7vwone2jfm3fo7t2t2dku

MFAQ: a Multilingual FAQ Dataset [article]

Maxime De Bruyn, Ehsan Lotfi, Jeska Buhmann, Walter Daelemans
2021 arXiv   pre-print
We adopt a similar setup as Dense Passage Retrieval (DPR) and test various bi-encoders on this dataset.  ...  Although this is significantly larger than existing FAQ retrieval datasets, it comes with its own challenges: duplication of content and uneven distribution of topics.  ...  Dense passage retrieval for open-domain question answering. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 6769-6781, Online.  ... 
arXiv:2109.12870v2 fatcat:okrggnbm4zepvnrw3uqsd2oroi

Knowledge-Aided Open-Domain Question Answering [article]

Mantong Zhou, Zhouxing Shi, Minlie Huang, Xiaoyan Zhu
2020 arXiv   pre-print
, there is still much room for improving open-domain QA systems since document retrieval and answer reranking are still unsatisfactory.  ...  Open-domain question answering (QA) aims to find the answer to a question from a large collection of documents.Though many models for single-document machine comprehension have achieved strong performance  ...  We first fine-tune the reader (with only L 2 ) for 1 epoch, and then fine-tune the whole model (with L) for another 2 epoches.  ... 
arXiv:2006.05244v1 fatcat:jalykeljibcbdeatk2muvkghu4

XLMRQA: Open-Domain Question Answering on Vietnamese Wikipedia-based Textual Knowledge Source [article]

Kiet Van Nguyen and Phong Nguyen-Thuan Do and Nhat Duy Nguyen and Tin Van Huynh and Anh Gia-Tuan Nguyen and Ngan Luu-Thuy Nguyen
2022 arXiv   pre-print
A reader-based QA system is a high-level search engine that can find correct answers to queries or questions in open-domain or domain-specific texts using machine reading comprehension (MRC) techniques  ...  Question answering (QA) is a natural language understanding task within the fields of information retrieval and information extraction that has attracted much attention from the computational linguistics  ...  Conclusion and Future Work In this paper, we introduced XLMRQA, a QA system based on the retriever-readerselector mechanism for Vietnamese open-domain texts, which outperformed two state-of-the-art question  ... 
arXiv:2204.07002v1 fatcat:oqrwofffpbd2fi5apwrc65gsde

Retrieving and Reading: A Comprehensive Survey on Open-domain Question Answering [article]

Fengbin Zhu, Wenqiang Lei, Chao Wang, Jianming Zheng, Soujanya Poria, Tat-Seng Chua
2021 arXiv   pre-print
Open-domain Question Answering (OpenQA) is an important task in Natural Language Processing (NLP), which aims to answer a question in the form of natural language based on large-scale unstructured documents  ...  Specifically, we begin with revisiting the origin and development of OpenQA systems.  ...  In 2001, a QA system called MULDER [44] was designed to automatically answer open-domain factoid questions with a search engine (e.g.,  ... 
arXiv:2101.00774v3 fatcat:6evkg5cikjdp5fsi3ou3iqqkyq

Accelerating Real-Time Question Answering via Question Generation [article]

Yuwei Fang, Shuohang Wang, Zhe Gan, Siqi Sun, Jingjing Liu, Chenguang Zhu
2021 arXiv   pre-print
answer without question encoding.  ...  Although deep neural networks have achieved tremendous success for question answering (QA), they are still suffering from heavy computational and energy cost for real product deployment.  ...  Related Work Open-Domain Question Answering Opendomain QA aims to answer any given factoid question without knowing the target domain.  ... 
arXiv:2009.05167v2 fatcat:sqy6s5f2jvbyfpltataeayoozm

Recent Trends in Deep Learning Based Open-Domain Textual Question Answering Systems

Zhen Huang, Shiyi Xu, Minghao Hu, Xinyi Wang, Jinyan Qiu, Yongquan Fu, Yuncai Zhao, Yuxing Peng, Changjian Wang
2020 IEEE Access  
INDEX TERMS Open-domain textual question answering, deep learning, machine reading comprehension, information retrieval.  ...  Open-domain textual question answering (QA), which aims to answer questions from large data sources like Wikipedia or the web, has gained wide attention in recent years.  ...  However, it is not beneficial in both efficiency and scalability since each passage needs to be encoded along with individual questions.  ... 
doi:10.1109/access.2020.2988903 fatcat:po4euxfronf3pob52qc2wcgrre

Differentiable Reasoning over a Virtual Knowledge Base [article]

Bhuwan Dhingra, Manzil Zaheer, Vidhisha Balachandran, Graham Neubig, Ruslan Salakhutdinov, William W. Cohen
2020 arXiv   pre-print
On HotpotQA, DrKIT leads to a 10% improvement over a BERT-based re-ranking approach to retrieving the relevant passages required to answer a question.  ...  We consider the task of answering complex multi-hop questions using a corpus as a virtual knowledge base (KB).  ...  End-to-end open-domain question answering with bertserini. arXiv preprint arXiv:1902.01718, 2019. Zhilin Yang, Peng Qi, Saizheng Zhang, Yoshua Bengio, William W.  ... 
arXiv:2002.10640v1 fatcat:2fcnpovwjjfdvfl36nvhoj3u54

Semantic Models for the First-stage Retrieval: A Comprehensive Review [article]

Yinqiong Cai, Yixing Fan, Jiafeng Guo, Fei Sun, Ruqing Zhang, Xueqi Cheng
2021 arXiv   pre-print
Therefore, it has been a long-term desire to build semantic models for the first-stage retrieval that can achieve high recall efficiently.  ...  Moreover, we identify some open challenges and envision some future directions, with the hope of inspiring more researches on these important yet less investigated topics.  ...  approaches for open-domain question answering.  ... 
arXiv:2103.04831v3 fatcat:6qa7hvc3jve3pcmo2mo4qsiefq

BioinQA: metadata-based multi-document QA system for addressing the issues in biomedical domain

Sparsh Mittal, Saket Gupta, Ankush Mittal
2013 International Journal of Data Mining Modelling and Management  
While specialised information retrieval tools are not suitable for beginners, general purpose search engines are not intelligent enough to respond to domain specific questions.  ...  The system constructs answers from multiple documents for complex comparison seeking questions.  ...  They adapt an open domain QAS to answer genomic questions with emphasis on identifying term relations based on a linguistic-rich full-parser.  ... 
doi:10.1504/ijdmmm.2013.051921 fatcat:sm4dotonqrghrieptmzjo3ysme

Putting Question-Answering Systems into Practice

Bernhard Kratzwald, Stefan Feuerriegel
2019 ACM Transactions on Management Information Systems  
Conversely, question-answering systems change how humans interact with information systems: users can now ask specific questions and obtain a tailored answer - both conveniently in natural language.  ...  approach for transfer learning in order to improve the performance of answer extraction.  ...  More precisely, we draw upon a different dataset that Manuscript submitted to ACM contains general, open-domain question-answer pairs.  ... 
doi:10.1145/3309706 fatcat:blc5y2o36ze6zk3ezlt7o6ubaa
« Previous Showing results 1 — 15 out of 861 results