Filters








68,008 Hits in 2.9 sec

Enhancing Information Retrieval with Adapted Word Embedding

Navid Rekabsaz
2016 Proceedings of the 39th International ACM SIGIR conference on Research and Development in Information Retrieval - SIGIR '16  
In this paper, we propose addressing the question of combining the term-to-term similarity of word embedding with IR models. The retrieval models in the  ...  Recent developments on word embedding provide a novel source of information for term-to-term similarity.  ...  Considering the mentioned research questions, the main goal of this Ph.D. is providing stable, reliable, and reusable information retrieval models, enhanced with adapted word embedding methods.  ... 
doi:10.1145/2911451.2911475 dblp:conf/sigir/Rekabsaz16 fatcat:hvsac5ib7zgdxbasxqjfqxg46y

HunYuan_tvr for Text-Video Retrieval [article]

Shaobo Min, Weijie Kong, Rong-Cheng Tu, Dihong Gong, Chengfei Cai, Wenzhe Zhao, Chenyang Liu, Sixiao Zheng, Hongfa Wang, Zhifeng Li, Wei Liu
2022 arXiv   pre-print
In this way, we can construct hierarchical video representations for frame-clip-video granularities, and also explore word-wise correlations to form word-phrase-sentence embeddings for the text modality  ...  Further boosted by adaptive label denoising and marginal sample enhancement, HunYuan_tvr obtains new state-of-the-art results on various benchmarks, e.g., Rank@1 of 55.0 DiDemo, and ActivityNet respectively  ...  Then, with hierarchical frame-clip-video representations and word-phrase-sentence embeddings, cross-modal contrastive learning is designed to learn inter-modal knowledge at different granularities.  ... 
arXiv:2204.03382v5 fatcat:uds4wvgtbbbbxi7hrwe5ioyq7u

Improving Language Estimation with the Paragraph Vector Model for Ad-hoc Retrieval

Qingyao Ai, Liu Yang, Jiafeng Guo, W. Bruce Croft
2016 Proceedings of the 39th International ACM SIGIR conference on Research and Development in Information Retrieval - SIGIR '16  
However, their effectiveness in information retrieval is mostly unknown. In this paper, we study how to effectively use the PV model to improve ad-hoc retrieval.  ...  Incorporating topic level estimation into language models has been shown to be beneficial for information retrieval (IR) models such as cluster-based retrieval and LDA-based document representation.  ...  The experimental results demonstrate the effectiveness of our enhanced PV based retrieval model compared with the state-of-the-art topic enhanced language models.  ... 
doi:10.1145/2911451.2914688 dblp:conf/sigir/AiYGC16 fatcat:lrptx22whfcydmg66ksgsfki74

Microblog Retrieval Based on Concept-Enhanced Pre-Training Model

Yashen Wang, Zhaoyu Wang, Huanhuan Zhang, Zhirun Liu
2022 ACM Transactions on Knowledge Discovery from Data  
Despite substantial interest in applications of neural networks to information retrieval, neural ranking models have mostly been applied to conventional ad hoc retrieval tasks over web pages and newswire  ...  This paper proposes a concept-enhanced pre-training model for microblog retrieval task, leveraging Semantic Matching Model (SMM) objective and Concept Correlation Model (CCM) objective.  ...  DRMM represents words with pre-trained word embeddings.  ... 
doi:10.1145/3552311 fatcat:nvqy6v232fdwvjojxut7d34vs4

Enhancing Cross-modal Retrieval Based on Modality-specific and Embedding Spaces

Rintaro Yanagi, Ren Togo, Takahiro Ogawa, Miki Haseyama
2020 IEEE Access  
However, we argue that the forced embedding optimization results in loss of key information for sentences and images.  ...  Most of the existing methods learn optimal embeddings of visual and lingual information to a single common representation space.  ...  In a future work, we will attempt to consider adaptive fusion of similarities. Professor with the Faculty of Information Science and Technology, Hokkaido University.  ... 
doi:10.1109/access.2020.2995815 fatcat:ar7zdjypivfdrmakffvilmhdfy

SF-CNN: Deep Text Classification and Retrieval for Text Documents

R. Sarasu, K. K. Thyagharajan, N. R. Shanker
2023 Intelligent Automation and Soft Computing  
An efficient classification algorithm for retrieving documents based on keyword words is required.  ...  The proposed SF-CNN is based on deep semantic-based bag-of-word representation for document retrieval.  ...  Vectors fed into the embedded layer; vectors converted by the tool should be semantically enhanced. In SF-CNN, semantic enhancement is performed through text corpus word embedding.  ... 
doi:10.32604/iasc.2023.027429 fatcat:r2czwj5p6jdntkr3lgkp23erma

Two-stage Visual Cues Enhancement Network for Referring Image Segmentation [article]

Yang Jiao, Zequn Jie, Weixin Luo, Jingjing Chen, Yu-Gang Jiang, Xiaolin Wei, Lin Ma
2021 arXiv   pre-print
In this paper, we tackle this problem from a novel perspective of enhancing the visual information for the referents by devising a Two-stage Visual cues enhancement Network (TV-Net), where a novel Retrieval  ...  The diverse and flexible expressions as well as complex visual contents in the images raise the RIS model with higher demands for investigating fine-grained matching behaviors between words in expressions  ...  [37] concatenate every word with multi-level visual features and devise self-attention mechanism to adaptively focus on informative words in the referring expression and important local patches in the  ... 
arXiv:2110.04435v1 fatcat:zt23iztwbjbdhlxaxsnvfmuyei

Learning to Attend On Essential Terms: An Enhanced Retriever-Reader Model for Open-domain Question Answering [article]

Jianmo Ni, Chenguang Zhu, Weizhu Chen, Julian McAuley
2019 arXiv   pre-print
We build (1) an essential term selector which first identifies the most important words in a question, then reformulates the query and searches for related evidence; and (2) an enhanced reader that distinguishes  ...  between essential terms and distracting words to predict the answer.  ...  queries when retrieving related evidence; (2) we developed an attentionenhanced reader with attention and fusion among passages, questions, and candidate answers.  ... 
arXiv:1808.09492v5 fatcat:xhsippw2rfbchoo6a2by4uppdq

Learning Term Discrimination

Jibril Frej, Philippe Mulhem, Didier Schwab, Jean-Pierre Chevallet
2020 Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval  
Document indexing is a key component for efficient information retrieval (IR). After preprocessing steps such as stemming and stopword removal, document indexes usually store term-frequencies (tf).  ...  during retrieval.  ...  INTRODUCTION Document indexing for information retrieval (IR) usually consists in associating each document of a collection with a set of weighted terms reflecting its information content.  ... 
doi:10.1145/3397271.3401211 dblp:conf/sigir/FrejMSC20 fatcat:7dqdoez63rb3xcewhcpouz7lwq

Language Features Matter: Effective Language Representations for Vision-Language Tasks [article]

Andrea Burns, Reuben Tan, Kate Saenko, Stan Sclaroff, Bryan A. Plummer
2019 arXiv   pre-print
We believe that language features deserve more attention, and conduct experiments which compare different word embeddings, language models, and embedding augmentation steps on five common VL tasks: image-sentence  ...  This multi-task training is applied to a new Graph Oriented Vision-Language Embedding (GrOVLE), which we adapt from Word2Vec using WordNet and an original visual-language graph built from Visual Genome  ...  Adapted Word Embeddings Since the introduction of Word2Vec, several enhancement techniques have been proposed.  ... 
arXiv:1908.06327v1 fatcat:z7o4dq62aneprlxqmopuw3ymni

Deep Visual-Semantic Quantization for Efficient Image Retrieval

Yue Cao, Mingsheng Long, Jianmin Wang, Shichen Liu
2017 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
DVSQ enables efficient and effective image retrieval by supporting maximum inner-product search, which is computed based on learned codebooks with fast distance table lookup.  ...  This paper presents a compact coding solution with a focus on the deep learning to quantization approach, which improves retrieval quality by end-to-end representation learning and compact encoding and  ...  Foundation of China (61502265, 61325008), National Key R&D Program of China (2016YFB1000701, 2015BAF32B01), National Engineering Lab for Big Data System Software (NEL-BDSS), and Tsinghua National Lab for Information  ... 
doi:10.1109/cvpr.2017.104 dblp:conf/cvpr/CaoL0L17 fatcat:jgzhlmcoeraqblejcdeoeovh6i

Beyond the Deep Metric Learning: Enhance the Cross-Modal Matching with Adversarial Discriminative Domain Regularization [article]

Li Ren, Kai Li, LiQiang Wang, Kien Hua
2020 arXiv   pre-print
Existing approaches mainly match the local visual objects and the sentence words in a shared space with attention mechanisms.  ...  In this paper, we address this limitation with an efficient learning objective that considers the discriminative feature distributions between the visual objects and sentence words.  ...  To address these limitations, we propose to compare the local visual objects and textual words by generating discriminate representations with domain adaptation techniques to enhance the deep metric learning  ... 
arXiv:2010.12126v2 fatcat:we74xd3jdzdzlev2fewj7spf7m

A Survey of Knowledge Enhanced Pre-trained Models [article]

Jian Yang, Gang Xiao, Yulong Shen, Wei Jiang, Xinyu Hu, Ying Zhang, Jinghui Peng
2022 arXiv   pre-print
Pre-trained models with knowledge injection, which we call knowledge enhanced pre-trained models (KEPTMs), possess deep understanding and logical reasoning and introduce interpretability.  ...  Pre-trained models learn informative representations on large-scale training data through a self-supervised or supervised learning method, which has achieved promising performance in natural language processing  ...  [93] propose a multi-source word aligned attention (MWA) to integrate explicit word information with pretrained character embeddings.  ... 
arXiv:2110.00269v3 fatcat:b2g3ezuplvftfp7zlehvogd44m

Cross-Modal Retrieval between Event-Dense Text and Image

Zhongwei Xie, Lin Li, Luo Zhong, Jianquan Liu, Ling Liu
2022 Proceedings of the 2022 International Conference on Multimedia Retrieval  
Finally, we integrate text embedding and image embedding with the loss optimization empowered with the event tag by iteratively regulating the joint embedding learning for cross-modal retrieval.  ...  CCS CONCEPTS • Information systems → Multimedia and multimodal retrieval.  ...  For the recipe title, we first encode each word in the title through a word embedding layer and then input the word embedding sequence into a 2-layer Transformer network with 4 attention heads, using a  ... 
doi:10.1145/3512527.3531374 fatcat:5gvfwcywwregvlgzeoia6omaka

Dialogue Session Segmentation by Embedding-Enhanced TextTiling [article]

Yiping Song, Lili Mou, Rui Yan, Li Yi, Zinan Zhu, Xiaohua Hu, Ming Zhang
2016 arXiv   pre-print
We propose an embedding-enhanced TextTiling approach, inspired by the observation that conversation utterances are highly noisy, and that word embeddings provide a robust way of capturing semantics.  ...  In human-computer conversation systems, the context of a user-issued utterance is particularly important because it provides useful background information of the conversation.  ...  Therefore, we enhance TextTiling with modern word embedding techniques, as will be discussed in the next part.  ... 
arXiv:1610.03955v1 fatcat:khvjezh2fzezlmhhlzbeecs3wa
« Previous Showing results 1 — 15 out of 68,008 results