6,692 Hits in 5.8 sec

Neural word and entity embeddings for ad hoc retrieval

Ebrahim Bagheri, Faezeh Ensan, Feras Al-Obeidat
2018 Information Processing & Management  
In this paper, we perform a methodical study on how neural embeddings in uence the ad hoc document retrieval task.  ...  While there have been several successful attempts at integrating embeddings within the ad hoc document retrieval task, yet, no systematic study has been reported that explores the various aspects of neural  ...  Several recent work have reported the impact of considering entities in ad hoc document retrieval.  ... 
doi:10.1016/j.ipm.2018.04.007 fatcat:ctlnqrysnfgytfdkpux5avqg6y

A Study of MatchPyramid Models on Ad-hoc Retrieval [article]

Liang Pang, Yanyan Lan, Jiafeng Guo, Jun Xu, Xueqi Cheng
2016 arXiv   pre-print
In this paper, we study a state-of-the-art deep matching model, namely MatchPyramid, on the ad-hoc retrieval task.  ...  Although ad-hoc retrieval can also be formalized as a text matching task, few deep models have been tested on it.  ...  Few deep model has been tested on the ad-hoc retrieval task.  ... 
arXiv:1606.04648v1 fatcat:d3vpcu4hozhndn5eo6h6oeufmm

A Deep Relevance Matching Model for Ad-hoc Retrieval

Jiafeng Guo, Yixing Fan, Qingyao Ai, W. Bruce Croft
2016 Proceedings of the 25th ACM International on Conference on Information and Knowledge Management - CIKM '16  
However, there have been few positive results of deep models on ad-hoc retrieval tasks.  ...  This is partially due to the fact that many important characteristics of the ad-hoc retrieval task have not been well addressed in deep models yet.  ...  ad-hoc retrieval setting • e.g., DSSM and C-DSSM, were only evaluated on the <query, doc title> pairs min Loss : feature representation of <q,d> … … T 1 T 2 Input Vector Deep Network Matching  ... 
doi:10.1145/2983323.2983769 dblp:conf/cikm/GuoFAC16 fatcat:m2zmgubzh5eztj6l6dxg4obhx4

PROP: Pre-training with Representative Words Prediction for Ad-hoc Retrieval [article]

Xinyu Ma, Jiafeng Guo, Ruqing Zhang, Yixing Fan, Xiang Ji, Xueqi Cheng
2020 arXiv   pre-print
By further fine-tuning on a variety of representative downstream ad-hoc retrieval tasks, PROP achieves significant improvements over baselines without pre-training or with other pre-training methods.  ...  However, pre-training objectives tailored for ad-hoc retrieval have not been well explored. In this paper, we propose Pre-training with Representative wOrds Prediction (PROP) for ad-hoc retrieval.  ...  PROP just needs to pre-train one model and then fine tune on a variety of downstream ad-hoc retrieval tasks.  ... 
arXiv:2010.10137v2 fatcat:jar2r7zcgbevnivhmvnwufpikq

Toward a Deep Neural Approach for Knowledge-Based IR [article]

Gia-Hung Nguyen, Lynda Tamine, Laure Soulier, Nathalie Bricon-Souf
2016 arXiv   pre-print
This paper tackles the problem of the semantic gap between a document and a query within an ad-hoc information retrieval task.  ...  In this paper, we review the main approaches of neural-based document ranking as well as those approaches for latent representation of entities and relations via KBs.  ...  TOWARD LEVERAGING KB FOR NEU-RAL AD-HOC IR The reported literature review clearly highlights the potential of neural networks in one hand and the benefit of KBs, in the other hand, for ad-hoc search tasks  ... 
arXiv:1606.07211v1 fatcat:jdypcyno3zcwphnoclk44dsfxi

MRNN: A Multi-Resolution Neural Network with Duplex Attention for Document Retrieval in the Context of Question Answering [article]

Tolgahan Cakaloglu, Xiaowei Xu
2019 arXiv   pre-print
The primary goal of ad-hoc retrieval (document retrieval in the context of question answering) is to find relevant documents satisfied the information need posted in a natural language query.  ...  In this paper, we devise a multi-resolution neural network(MRNN) to leverage the whole hierarchy of representations for document retrieval.  ...  for ad-hoc retrieval.  ... 
arXiv:1911.00964v1 fatcat:vxhhe4fbwrhcxbgdit36mwomqy

A Match-Transformer Framework for Modeling Diverse Relevance Patterns in Ad-hoc Retrieval

Yongyu Jiang, Peng Zhang, Hui Gao, Xindian Ma, Donghao Zhao, Zeting Hu, Junyan Wang, Meixian Song
2019 Australian Journal of Intelligent Information Processing Systems  
Experimental results on two benchmark collections demonstrate that our approach outperforms most wellknown Neural IR models in ad-hoc retrieval.  ...  In ad-hoc retrieval, judging relevance between a query and a document is still challenging due to its diverse patterns (e.g., a query is usually short and does not have enough contextual information which  ...  Specially, deep neural networks have led to exciting breakthroughs on ad-hoc retrieval tasks.  ... 
dblp:journals/ajiips/JiangZGMZHWS19 fatcat:7istzbqbizgshjvvnasjbnbgpi

A Graph-based Relevance Matching Model for Ad-hoc Retrieval [article]

Yufeng Zhang, Jinghao Zhang, Zeyu Cui, Shu Wu, Liang Wang
2021 arXiv   pre-print
In this work, we propose a novel relevance matching model based on graph neural networks to leverage the document-level word relationships for ad-hoc retrieval.  ...  Our approach significantly outperforms strong baselines on two ad-hoc benchmarks. We also experimentally compare our model with BERT and show our advantages on long documents.  ...  Acknowledgements This work is supported by National Key Research and Development Program (2018YFB1402605, 2018YFB1402600), National Natural Science Foundation of China (U19B2038, 61772528), and Beijing  ... 
arXiv:2101.11873v2 fatcat:wtorbqcwuvd47lw3m7sy2ownmu

Lecture Notes on Neural Information Retrieval [article]

Nicola Tonellotto
2022 arXiv   pre-print
These lecture notes focus on the recent advancements in neural information retrieval, with particular emphasis on the systems and models exploiting transformer networks.  ...  a basic understanding of the main information retrieval techniques and approaches based on deep learning.  ...  Neural Information Retrieval focuses on retrieving text documents able to fulfill the information needs of their users exploiting deep neural networks.  ... 
arXiv:2207.13443v2 fatcat:3bsuag2gn5andgi4dxjks7bzdq

Transfer Learning Approaches for Building Cross-Language Dense Retrieval Models [article]

Suraj Nair, Eugene Yang, Dawn Lawrie, Kevin Duh, Paul McNamee, Kenton Murray, James Mayfield, Douglas W. Oard
2022 arXiv   pre-print
Results on ad hoc document ranking tasks in several languages demonstrate substantial and statistically significant improvements of these trained dense retrieval models over traditional lexical CLIR baselines  ...  The advent of transformer-based models such as BERT has led to the rise of neural ranking models.  ...  Acknowledgments This research is based upon work supported in part by the Office of the Director of National Intelligence (ODNI), Intelligence Advanced Research Projects Activity (IARPA), via contract  ... 
arXiv:2201.08471v1 fatcat:qotjmi4dmner3cqxym6ad3ol3q

Neural information retrieval: at the end of the early years

Kezban Dilek Onal, Ye Zhang, Ismail Sengor Altingovde, Md Mustafizur Rahman, Pinar Karagoz, Alex Braylan, Brandon Dang, Heng-Lu Chang, Henna Kim, Quinten McNamara, Aaron Angert, Edward Banner (+7 others)
2017 Information retrieval (Boston)  
Recent years have witnessed an explosive growth of research into NN-based approaches to information retrieval (IR). A significant body of work has now been created.  ...  A recent "third wave" of neural network (NN) approaches now delivers state-ofthe-art performance in many machine learning tasks, spanning speech recognition, computer vision, and natural language processing  ...  The following additional students at the University of Texas at Austin contributed indirectly to the writing of this literature review: Manu Agarwal, Edward Babbe, Anuparna Banerjee, Jason Cai, Dillon  ... 
doi:10.1007/s10791-017-9321-y fatcat:plrhhwkppjgb7l5r5daiyryj4q

Modeling Diverse Relevance Patterns in Ad-hoc Retrieval

Yixing Fan, Jiafeng Guo, Yanyan Lan, Jun Xu, Chengxiang Zhai, Xueqi Cheng
2018 The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval - SIGIR '18  
Experimental results demonstrate that our HiNT model outperforms existing state-of-the-art retrieval models significantly on benchmark ad-hoc retrieval datasets.  ...  Assessing relevance between a query and a document is challenging in ad-hoc retrieval due to its diverse patterns, i.e., a document could be relevant to a query as a whole or partially as long as it provides  ...  Recently, deep neural models have been applied to ad-hoc retrieval.  ... 
doi:10.1145/3209978.3209980 dblp:conf/sigir/FanGLXZC18 fatcat:mp6e7qe5ivh5pjmijwctporhfa

Complementing Lexical Retrieval with Semantic Residual Embedding [article]

Luyu Gao, Zhuyun Dai, Tongfei Chen, Zhen Fan, Benjamin Van Durme, Jamie Callan
2021 arXiv   pre-print
Empirical evaluations demonstrate the advantages of CLEAR over state-of-the-art retrieval models, and that it can substantially improve the end-to-end accuracy and efficiency of reranking pipelines.  ...  This paper presents CLEAR, a retrieval model that seeks to complement classical lexical exact-match models such as BM25 with semantic matching signals from a neural embedding matching model.  ...  The effectiveness of representation-based neural retrieval models for standard ad-hoc search is mixed [11, 40] .  ... 
arXiv:2004.13969v3 fatcat:rdrcnpkepfbjngrjw2sigokjgu

Multi-Perspective Relevance Matching with Hierarchical ConvNets for Social Media Search [article]

Jinfeng Rao, Wei Yang, Yuhao Zhang, Ferhan Ture, Jimmy Lin
2019 arXiv   pre-print
Despite substantial interest in applications of neural networks to information retrieval, neural ranking models have only been applied to standard ad hoc retrieval tasks over web pages and newswire documents  ...  We identify document length, informal language, and heterogeneous relevance signals as features that distinguish documents in our domain, and present a model specifically designed with these characteristics  ...  Baselines We compare our model to a number of non-neural baselines as well as recent neural ranking models designed for "standard" ad hoc retrieval tasks on web and newswire documents (we call these the  ... 
arXiv:1805.08159v2 fatcat:dtvkp7pvxvbxzgczjyqzz7wc4m

B-PROP: Bootstrapped Pre-training with Representative Words Prediction for Ad-hoc Retrieval [article]

Xinyu Ma, Jiafeng Guo, Ruqing Zhang, Yixing Fan, Yingyan Li, Xueqi Cheng
2022 arXiv   pre-print
the SOTA on a variety of ad-hoc retrieval tasks.  ...  Recently, pre-training methods tailored for information retrieval (IR) have also been explored, and the latest success is the PROP method which has reached new SOTA on a variety of ad-hoc retrieval benchmarks  ...  [22] proposed a novel pre-training objective tailored for ad-hoc retrieval, i.e., representation words prediction (ROP), and achieved new SOTA on a variety of ad-hoc retrieval tasks.  ... 
arXiv:2104.09791v4 fatcat:sjovklmqhfbfveeiu3vgtkhwym
« Previous Showing results 1 — 15 out of 6,692 results