A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Filters
Generating Personalized Recipes from Historical User Preferences
[article]
2019
arXiv
pre-print
Preserved Fulltext
Existing approaches to recipe generation are unable to create recipes for users with culinary preferences but incomplete knowledge of ingredients in specific dishes. We propose a new task of personalized recipe generation to help these users: expanding a name and incomplete ingredient details into complete natural-text instructions aligned with the user's historical preferences. We attend on technique- and recipe-level representations of a user's previously consumed recipes, fusing these
arXiv:1909.00105v1
fatcat:rtstm7t67vhhhgiwgdcm73nfci
more »
... ware' representations in an attention fusion layer to control recipe text generation. Experiments on a new dataset of 180K recipes and 700K interactions show our model's ability to generate plausible and personalized recipes compared to non-personalized baselines.
REDCLAN - RELATIVE DENSITY BASED CLUSTERING AND ANOMALY DETECTION
2018
Figshare
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Cluster analysis and Anomaly Detection are the primary methods for database mining. However, most of the data in today's world, generated from multifarious sources, don't adhere to the assumption of single or even known distribution - hence the problem of finding clusters in the data becomes arduous as clusters are of widely differing sizes, densities and shapes, along with the presence of noise and outliers. Thus, we propose a relative-KNN-kernel density-based clustering algorithm. The
doi:10.6084/m9.figshare.7206668.v1
fatcat:yzh4vqsodngtbbe23kqonkyrqy
more »
... ered (noise) points are further classified as anomaly or nonanomaly using a weighted rank-based anomaly detection method. This method works particularly well when the clusters are of varying variability and shape, in these cases our algorithm not only finds the "dense" clusters that other clustering algorithms find, it also finds low-density clusters that these approaches fail to identify. This more accurate clustering in turn helps reduce the noise points and makes the anomaly detection more accurate.
Self-Supervised Bot Play for Conversational Recommendation with Justifications
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Conversational recommender systems offer the promise of interactive, engaging ways for users to find items they enjoy. We seek to improve conversational recommendation via three dimensions: 1) We aim to mimic a common mode of human interaction for recommendation: experts justify their suggestions, a seeker explains why they don't like the item, and both parties iterate through the dialog to find a suitable item. 2) We leverage ideas from conversational critiquing to allow users to flexibly
arXiv:2112.05197v1
fatcat:nfjupandfbbuvlzm4kn44ltgf4
more »
... act with natural language justifications by critiquing subjective aspects. 3) We adapt conversational recommendation to a wider range of domains where crowd-sourced ground truth dialogs are not available. We develop a new two-part framework for training conversational recommender systems. First, we train a recommender system to jointly suggest items and justify its reasoning with subjective aspects. We then fine-tune this model to incorporate iterative user feedback via self-supervised bot-play. Experiments on three real-world datasets demonstrate that our system can be applied to different recommendation models across diverse domains to achieve superior performance in conversational recommendation compared to state-of-the-art methods. We also evaluate our model on human users, showing that systems trained under our framework provide more useful, helpful, and knowledgeable recommendations in warm- and cold-start settings.
Unsupervised Enrichment of Persona-grounded Dialog with Background Stories
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
., 2018; Majumder et al., 2020) . ...
Our underlying model is based on the discrete persona attribute choice model from Majumder et al. (2020) . ...
arXiv:2106.08364v1
fatcat:nis6cwddfneivn7n3ndmyffjlm
Fault Detection Engine in Intelligent Predictive Analytics Platform for DCIM
[article]
2016
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
With the advancement of huge data generation and data handling capability, Machine Learning and Probabilistic modelling enables an immense opportunity to employ predictive analytics platform in high security critical industries namely data centers, electricity grids, utilities, airport etc. where downtime minimization is one of the primary objectives. This paper proposes a novel, complete architecture of an intelligent predictive analytics platform, Fault Engine, for huge device network
arXiv:1610.04872v1
fatcat:m2w2tywukzbedfrttiiks4vl2m
more »
... d with electrical/information flow. Three unique modules, here proposed, seamlessly integrate with available technology stack of data handling and connect with middleware to produce online intelligent prediction in critical failure scenarios. The Markov Failure module predicts the severity of a failure along with survival probability of a device at any given instances. The Root Cause Analysis model indicates probable devices as potential root cause employing Bayesian probability assignment and topological sort. Finally, a community detection algorithm produces correlated clusters of device in terms of failure probability which will further narrow down the search space of finding route cause. The whole Engine has been tested with different size of network with simulated failure environments and shows its potential to be scalable in real-time implementation.
Interview: A Large-Scale Open-Source Corpus of Media Dialog
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
As in Majumder et al. ...
arXiv:2004.03090v1
fatcat:3xpvcou6inhb3fiknjpkheocrq
Deep Recurrent Neural Networks for Product Attribute Extraction in eCommerce
[article]
2018
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Extracting accurate attribute qualities from product titles is a vital component in delivering eCommerce customers with a rewarding online shopping experience via an enriched faceted search. We demonstrate the potential of Deep Recurrent Networks in this domain, primarily models such as Bidirectional LSTMs and Bidirectional LSTM-CRF with or without an attention mechanism. These have improved overall F1 scores, as compared to the previous benchmarks (More et al.) by at least 0.0391, showcasing
arXiv:1803.11284v1
fatcat:sr7zmfvrzbconihu56fgbjlyzy
more »
... overall precision of 97.94%, recall of 94.12% and the F1 score of 0.9599. This has made us achieve a significant coverage of important facets or attributes of products which not only shows the efficacy of deep recurrent models over previous machine learning benchmarks but also greatly enhances the overall customer experience while shopping online.
Kernelized Weighted SUSAN based Fuzzy C-Means Clustering for Noisy Image Segmentation
[article]
2016
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
The paper proposes a novel Kernelized image segmentation scheme for noisy images that utilizes the concept of Smallest Univalue Segment Assimilating Nucleus (SUSAN) and incorporates spatial constraints by computing circular colour map induced weights. Fuzzy damping coefficients are obtained for each nucleus or center pixel on the basis of the corresponding weighted SUSAN area values, the weights being equal to the inverse of the number of horizontal and vertical moves required to reach a
arXiv:1603.08564v1
fatcat:cv7dbftpdfepzgt26yo7tvm2vi
more »
... rhood pixel from the center pixel. These weights are used to vary the contributions of the different nuclei in the Kernel based framework. The paper also presents an edge quality metric obtained by fuzzy decision based edge candidate selection and final computation of the blurriness of the edges after their selection. The inability of existing algorithms to preserve edge information and structural details in their segmented maps necessitates the computation of the edge quality factor (EQF) for all the competing algorithms. Qualitative and quantitative analysis have been rendered with respect to state-of-the-art algorithms and for images ridden with varying types of noises. Speckle noise ridden SAR images and Rician noise ridden Magnetic Resonance Images have also been considered for evaluating the effectiveness of the proposed algorithm in extracting important segmentation information.
Rationale-Inspired Natural Language Explanations with Commonsense
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Rationale-Inspired Natural Language Explanations with Commonsense
Bodhisattwa Prasad Majumder♣ ...
Learning from the best: Ra-
Bodhisattwa Prasad Majumder, Harsh Jhamtani,
tionalizing predictions by adversarial informa-
Taylor Berg-Kirkpatrick ...
arXiv:2106.13876v2
fatcat:dq5ibj3h6zakdfrg7eal3hfxme
Like hiking? You probably enjoy nature: Persona-grounded Dialog with Commonsense Expansions
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Existing persona-grounded dialog models often fail to capture simple implications of given persona descriptions, something which humans are able to do seamlessly. For example, state-of-the-art models cannot infer that interest in hiking might imply love for nature or longing for a break. In this paper, we propose to expand available persona sentences using existing commonsense knowledge bases and paraphrasing resources to imbue dialog models with access to an expanded and richer set of persona
arXiv:2010.03205v1
fatcat:nnoo3rzf25bx3i6fd5fcec2obm
more »
... escriptions. Additionally, we introduce fine-grained grounding on personas by encouraging the model to make a discrete choice among persona sentences while synthesizing a dialog response. Since such a choice is not observed in the data, we model it using a discrete latent random variable and use variational learning to sample from hundreds of persona expansions. Our model outperforms competitive baselines on the PersonaChat dataset in terms of dialog quality and diversity while achieving persona-consistent and controllable dialog generation.
Detect and Perturb: Neutral Rewriting of Biased and Sensitive Text via Gradient-based Decoding
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Similar inference-time perturbation approaches also have been proposed for applications such as clarification question generation (Majumder et al., 2021b) and dialog generation (Majumder et al., 2021a ...
Representative approaches use an encoder-decoder setup with a discriminator (e,g. style) (Romanov et al., 2018; Dai et al., 2019; John et al., 2019; Aho and Ullman, 1972; Majumder et al., 2021a ,b), backtranslation ...
arXiv:2109.11708v1
fatcat:vytlja3uundx7avleaiuxw33ly
Upcycle Your OCR: Reusing OCRs for Post-OCR Text Correction in Romanised Sanskrit
[article]
2018
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
We propose a post-OCR text correction approach for digitising texts in Romanised Sanskrit. Owing to the lack of resources our approach uses OCR models trained for other languages written in Roman. Currently, there exists no dataset available for Romanised Sanskrit OCR. So, we bootstrap a dataset of 430 images, scanned in two different settings and their corresponding ground truth. For training, we synthetically generate training images for both the settings. We find that the use of copying
arXiv:1809.02147v1
fatcat:qgxvtpbdxjdl5njbhqgx3wqmae
more »
... nism (Gu et al., 2016) yields a percentage increase of 7.69 in Character Recognition Rate (CRR) than the current state of the art model in solving monotone sequence-to-sequence tasks (Schnober et al., 2016). We find that our system is robust in combating OCR-prone errors, as it obtains a CRR of 87.01% from an OCR output with CRR of 35.76% for one of the dataset settings. A human judgment survey performed on the models shows that our proposed model results in predictions which are faster to comprehend and faster to improve for a human than the other systems.
Improving Neural Story Generation by Targeted Common Sense Grounding
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Stories generated with neural language models have shown promise in grammatical and stylistic consistency. However, the generated stories are still lacking in common sense reasoning, e.g., they often contain sentences deprived of world knowledge. We propose a simple multi-task learning scheme to achieve quantitatively better common sense reasoning in language models by leveraging auxiliary training signals from datasets designed to provide common sense grounding. When combined with our
arXiv:1908.09451v2
fatcat:vqiiy4fscfbvvao2oyeitmziby
more »
... fine-tuning pipeline, our method achieves improved common sense reasoning and state-of-the-art perplexity on the Writing Prompts (Fan et al., 2018) story generation dataset.
ReZero is All You Need: Fast Convergence at Large Depth
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Deep networks often suffer from vanishing or exploding gradients due to inefficient signal propagation, leading to long training times or convergence difficulties. Various architecture designs, sophisticated residual-style networks, and initialization schemes have been shown to improve deep signal propagation. Recently, Pennington et al. used free probability theory to show that dynamical isometry plays an integral role in efficient deep learning. We show that the simplest architecture change
arXiv:2003.04887v2
fatcat:gfiztb7fdvbmpgelw4362x2xie
more »
... gating each residual connection using a single zero-initialized parameter satisfies initial dynamical isometry and outperforms more complex approaches. Although much simpler than its predecessors, this gate enables training thousands of fully connected layers with fast convergence and better test performance for ResNets trained on CIFAR-10. We apply this technique to language modeling and find that we can easily train 120-layer Transformers. When applied to 12 layer Transformers, it converges 56% faster on enwiki8.
Generating Personalized Recipes from Historical User Preferences
2019
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
Existing approaches to recipe generation are unable to create recipes for users with culinary preferences but incomplete knowledge of ingredients in specific dishes. We propose a new task of personalized recipe generation to help these users: expanding a name and incomplete ingredient details into complete naturaltext instructions aligned with the user's historical preferences. We attend on technique-and recipe-level representations of a user's previously consumed recipes, fusing these
doi:10.18653/v1/d19-1613
dblp:conf/emnlp/MajumderLNM19
fatcat:pyb4qcndwfdubjjwqqhoivwciq
more »
... e' representations in an attention fusion layer to control recipe text generation. Experiments on a new dataset of 180K recipes and 700K interactions show our model's ability to generate plausible and personalized recipes compared to non-personalized baselines.
« Previous
Showing results 1 — 15 out of 48 results