DeepTileBars: Visualizing Term Distribution for Neural Information Retrieval

@inproceedings{Tang2019DeepTileBarsVT,
  title={DeepTileBars: Visualizing Term Distribution for Neural Information Retrieval},
  author={Zhiwen Tang and G. Yang},
  booktitle={AAAI},
  year={2019}
}
Most neural Information Retrieval (Neu-IR) models derive query-to-document ranking scores based on term-level matching. [...] Key Method Our system first splits the documents into topical segments, "visualizes" the matchings between the query and the segments, and then feeds an interaction matrix into a Neu-IR model, DeepTileBars, to obtain the final ranking scores. DeepTileBars models the relevance signals occurring at different granularities in a document's topic hierarchy.Expand
Query Query Processing Indexing Neural Ranking Model Relevant docs Neural ranking component User Return Relevant docs Unsupervised ranking
Ranking models are the main components of information retrieval systems. Several approaches to ranking are based on traditional machine learning algorithms using a set of hand-crafted features.Expand
A Deep Look into Neural Ranking Models for Information Retrieval
TLDR
A deep look into the neural ranking models from different dimensions is taken to analyze their underlying assumptions, major design principles, and learning strategies to obtain a comprehensive empirical understanding of the existing techniques. Expand
Word Embedding Models for Query Expansion in Answer Passage Retrieval
TLDR
Two word embedding models are compared—CBOW and IWE—in this thesis and it is found out that IWE word embeddings capture more semantic information than CBOW wordembeddings when trained on local data with a limited vocabulary. Expand
An In-depth Analysis of Passage-Level Label Transfer for Contextual Document Ranking
TLDR
It is found that direct transfer of relevance labels from documents to passages introduces label noise that strongly affects retrieval effectiveness for large training datasets and query processing times are adversely affected by fine-grained splitting schemes. Expand
Capreolus: A Toolkit for End-to-End Neural Ad Hoc Retrieval
TLDR
Using Capreolus, a toolkit designed to facilitate end-to-end it ad hoc retrieval experiments with neural networks by providing implementations of prominent neural ranking models within a common framework, it is found that Yang et al.'s recent SIGIR 2019 finding that many neural retrieval models do not significantly outperform a strong query expansion baseline holds true. Expand
Investigating Retrieval Method Selection with Axiomatic Features
TLDR
A meta-learner is proposed that predicts how to combine the methods' relevance scores into an overall relevance score based on features that quantify axiom-related properties of the query and its top ranked documents. Expand
Corpus Compression for Deep Reinforcement Learning in Natural Language Environments
Deep reinforcement learning (DRL) offers natural solutions to interactive artificial intelligence (AI) agents, for DRL’s ability of adaptation and exploration. Many existing methods use a searchExpand
Axiomatic Thinking in Neural IR: An axiomatic approach to diagnosing deep IR models
TLDR
The axiomatic approach to diagnosing neural IR models presented in this work is a step forward to gaining valuable insights into the black boxes that deep models are generally considered to be and it is hoped this work may prove a fruitful resource for analysis in the field of neural IR on the road towards achieving superior performance. Expand
Weakly Supervised Attention Networks for Entity Recognition
TLDR
It is shown that the proposed weakly supervised model, trained solely on a multi-label classification task, performs reasonably well on the task of entity recognition, despite not having access to any token-level ground truth data. Expand
Guided exploration of user groups
TLDR
This paper formalizes and solves the problem of guided exploration of user groups whose purpose is to find target users by applying reinforcement learning to discover an efficient exploration strategy from a simulated agent experience, and proposes to use the learned strategy to recommend an exploration policy that can be applied to the same task for any dataset. Expand
...
1
2
...

References

SHOWING 1-10 OF 69 REFERENCES
DSRIM: A Deep Neural Information Retrieval Model Enhanced by a Knowledge Resource Driven Representation of Documents
TLDR
The experimental evaluation carried out on two TREC datasets from TREC Terabyte and TREC CDS tracks relying respectively on WordNet and MeSH resources, indicates that the DSRIM model outperforms state-of-the-art semantic and deep neural IR models. Expand
Learning deep structured semantic models for web search using clickthrough data
TLDR
A series of new latent semantic models with a deep structure that project queries and documents into a common low-dimensional space where the relevance of a document given a query is readily computed as the distance between them are developed. Expand
DeepRank: A New Deep Architecture for Relevance Ranking in Information Retrieval
TLDR
Experiments on both benchmark LETOR dataset and a large scale clickthrough data show that DeepRank can significantly outperform learning to ranking methods, and existing deep learning methods. Expand
Learning to Match using Local and Distributed Representations of Text for Web Search
TLDR
This work proposes a novel document ranking model composed of two separate deep neural networks, one that matches the query and the document using a local representation, and another that Matching with distributed representations complements matching with traditional local representations. Expand
End-to-End Neural Ad-hoc Ranking with Kernel Pooling
TLDR
K-NRM uses a translation matrix that models word-level similarities via word embeddings, a new kernel-pooling technique that uses kernels to extract multi-level soft match features, and a learning-to-rank layer that combines those features into the final ranking score. Expand
PACRR: A Position-Aware Neural IR Model for Relevance Matching
TLDR
This work proposes a novel neural IR model named PACRR aiming at better modeling position-dependent interactions between a query and a document and yields better results under multiple benchmarks. Expand
Learning semantic representations using convolutional neural networks for web search
TLDR
This paper presents a series of new latent semantic models based on a convolutional neural network to learn low-dimensional semantic vectors for search queries and Web documents that significantly outperforms other se-mantic models in retrieval performance. Expand
Modeling Diverse Relevance Patterns in Ad-hoc Retrieval
TLDR
This work proposes a data-driven method to allow relevance signals at different granularities to compete with each other for final relevance assessment and demonstrates that the HiNT model outperforms existing state-of-the-art retrieval models significantly on benchmark ad-hoc retrieval datasets. Expand
A Deep Relevance Matching Model for Ad-hoc Retrieval
TLDR
A novel deep relevance matching model (DRMM) for ad-hoc retrieval that employs a joint deep architecture at the query term level for relevance matching and can significantly outperform some well-known retrieval models as well as state-of-the-art deep matching models. Expand
A Study of MatchPyramid Models on Ad-hoc Retrieval
TLDR
The MatchPyramid models can significantly outperform several recently introduced deep matching models on the retrieval task, but still cannot compete with the traditional retrieval models, such as BM25 and language models. Expand
...
1
2
3
4
5
...