Context Attentive Document Ranking and Query Suggestion

Ahmad, Wasi Uddin; Chang, Kai-Wei; Wang, Hongning

doi:10.1145/3331184.3331246

Cited by 83 publications

(64 citation statements)

References 49 publications

(85 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…A similar trend can be observed when comparing HREDCap with its multitask variants. For all the three metrics for query reformulations, the best performing model is a multitask model -this validates the observations from [1] in our context.…”

Section: 2supporting

confidence: 84%

“…This target reformulation q reform can either be (i) the subsequent query q i+1 in the same session S, or (ii) the caption C clicked i corresponding to the clicked image I clicked i . Note that obtaining contextual query suggestions via a translation model that has learnt a mapping between successive queries within a session (i.e., (i)) has been previously proposed in our reference baseline papers [1,26]. In the current paper, we utilize a linguistically richer supervision signal, in the form of captions of clicked images (i.e., (ii)), and analyze the behavior of the different models across three high level axes -relevance, descriptiveness and diversity of generated reformulations.…”

Section: Notationmentioning

confidence: 99%

“…During training, the ranker tries to learn model parameters based on one of the following two objectives: (i) Cross Entropy Loss: As described in [1], we utilize the 'clicked' versus 'not-clicked' boolean event to train a classifier, where the ranker scores the m retrieved results based on the probability of being clicked by the user. In the following equation, R i for query q i is an m-dimensional vector, where each value in the vector indicates whether the corresponding image was clicked or not.…”

Section: 2mentioning

confidence: 99%

See 2 more Smart Citations

Using Image Captions and Multitask Learning for Recommending Query Reformulations

Verma¹,

Vinay²,

Bansal

et al. 2020

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Interactive search sessions often contain multiple queries, where the user submits a reformulated version of the previous query in response to the original results. We aim to enhance the query recommendation experience for a commercial image search engine. Our proposed methodology incorporates current state-of-the-art practices from relevant literature -the use of generation-based sequence-to-sequence models that capture session context, and a multitask architecture that simultaneously optimizes the ranking of results. We extend this setup by driving the learning of such a model with captions of clicked images as the target, instead of using the subsequent query within the session. Since these captions tend to be linguistically richer, the reformulation mechanism can be seen as assistance to construct more descriptive queries. In addition, via the use of a pairwise loss for the secondary ranking task, we show that the generated reformulations are more diverse.

show abstract

Section: 2supporting

confidence: 84%

Section: Notationmentioning

confidence: 99%

Section: 2mentioning

confidence: 99%

See 1 more Smart Citation

Using Image Captions and Multitask Learning for Recommending Query Reformulations

Verma¹,

Vinay²,

Bansal

et al. 2020

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…Ahmad et al [149] incorporated short-term history information into a neural ranking model by multi-task training of document ranking and query suggestion. Short-and long-term history have been also used by Chen et al [150] for query suggestion.…”

Section: Learning With Contextmentioning

confidence: 99%

A Deep Look into neural ranking models for information retrieval

Guo

Fan

Pang

et al. 2020

Information Processing & Management

236

147

View full text Add to dashboard Cite

Ranking models lie at the heart of research on information retrieval (IR). During the past decades, different techniques have been proposed for constructing ranking models, from traditional heuristic methods, probabilistic methods, to modern machine learning methods. Recently, with the advance of deep learning technology, we have witnessed a growing body of work in applying shallow or deep neural networks to the ranking problem in IR, referred to as neural ranking models in this paper. The power of neural ranking models lies in the ability to learn from the raw text inputs for the ranking problem to avoid many limitations of hand-crafted features. Neural networks have sufficient capacity to model complicated tasks, which is needed to handle the complexity of relevance estimation in ranking. Since there have been a large variety of neural ranking models proposed, we believe it is the right time to summarize the current status, learn from existing methodologies, and gain some insights for future development. In contrast to existing reviews, in this survey, we will take a deep look into the neural ranking models from different dimensions to analyze their underlying assumptions, major design principles, and learning strategies. We compare these models through benchmark tasks to obtain a comprehensive empirical understanding of the existing techniques. We will also discuss what is missing in the current literature and what are the promising and desired future directions.

show abstract

“…Although we have seen significant progresses in multitask learning of unimodal tasks of vision [18,32] or language [26,1,35] so far, there has been only a lim-ited amount of progress in multi-task learning of visionlanguage tasks. This may be attributable to the diversity of these tasks.…”

Section: Introductionmentioning

confidence: 99%

Multi-Task Learning of Hierarchical Vision-Language Representation

Nguyen

Okatani

2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

It is still challenging to build an AI system that can perform tasks that involve vision and language at human level. So far, researchers have singled out individual tasks separately, for each of which they have designed networks and trained them on its dedicated datasets. Although this approach has seen a certain degree of success, it comes with difficulties of understanding relations among different tasks and transferring the knowledge learned for a task to others. We propose a multi-task learning approach that enables to learn vision-language representation that is shared by many tasks from their diverse datasets. The representation is hierarchical, and prediction for each task is computed from the representation at its corresponding level of the hierarchy. We show through experiments that our method consistently outperforms previous single-task-learning methods on image caption retrieval, visual question answering, and visual grounding. We also analyze the learned hierarchical representation by visualizing attention maps generated in our network.

show abstract

Context Attentive Document Ranking and Query Suggestion

Cited by 83 publications

References 49 publications

Using Image Captions and Multitask Learning for Recommending Query Reformulations

Using Image Captions and Multitask Learning for Recommending Query Reformulations

A Deep Look into neural ranking models for information retrieval

Multi-Task Learning of Hierarchical Vision-Language Representation

Contact Info

Product

Resources

About