Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

"Topic": models, code, and papers

Sparse Group Lasso: Optimal Sample Complexity, Convergence Rate, and Statistical Inference

Sep 21, 2019
T. Tony Cai, Anru Zhang, Yuchen Zhou

In this paper, we study sparse group Lasso for high-dimensional double sparse linear regression, where the parameter of interest is simultaneously element-wise and group-wise sparse. This problem is an important instance of the simultaneously structured model -- an actively studied topic in statistics and machine learning. In the noiseless case, we provide matching upper and lower bounds on sample complexity for the exact recovery of sparse vectors and for stable estimation of approximately sparse vectors, respectively. In the noisy case, we develop upper and matching minimax lower bounds for estimation error. We also consider the debiased sparse group Lasso and investigate its asymptotic property for the purpose of statistical inference. Finally, numerical studies are provided to support the theoretical results.


  Access Paper or Ask Questions

Careful Selection of Knowledge to solve Open Book Question Answering

Jul 24, 2019
Pratyay Banerjee, Kuntal Kumar Pal, Arindam Mitra, Chitta Baral

Open book question answering is a type of natural language based QA (NLQA) where questions are expected to be answered with respect to a given set of open book facts, and common knowledge about a topic. Recently a challenge involving such QA, OpenBookQA, has been proposed. Unlike most other NLQA tasks that focus on linguistic understanding, OpenBookQA requires deeper reasoning involving linguistic understanding as well as reasoning with common knowledge. In this paper we address QA with respect to the OpenBookQA dataset and combine state of the art language models with abductive information retrieval (IR), information gain based re-ranking, passage selection and weighted scoring to achieve 72.0% accuracy, an 11.6% improvement over the current state of the art.

* Accepted to ACL 2019 

  Access Paper or Ask Questions

A Tweet Dataset Annotated for Named Entity Recognition and Stance Detection

Jan 16, 2019
Dilek Küçük, Fazli Can

Annotated datasets in different domains are critical for many supervised learning-based solutions to related problems and for the evaluation of the proposed solutions. Topics in natural language processing (NLP) similarly require annotated datasets to be used for such purposes. In this paper, we target at two NLP problems, named entity recognition and stance detection, and present the details of a tweet dataset in Turkish annotated for named entity and stance information. Within the course of the current study, both the named entity and stance annotations of the included tweets are made publicly available, although previously the dataset has been publicly shared with stance annotations only. We believe that this dataset will be useful for uncovering the possible relationships between named entity recognition and stance detection in tweets.

* 4 pages; resource URLs are made properly accessible (by clicking them) 

  Access Paper or Ask Questions

WikiHow: A Large Scale Text Summarization Dataset

Oct 18, 2018
Mahnaz Koupaee, William Yang Wang

Sequence-to-sequence models have recently gained the state of the art performance in summarization. However, not too many large-scale high-quality datasets are available and almost all the available ones are mainly news articles with specific writing style. Moreover, abstractive human-style systems involving description of the content at a deeper level require data with higher levels of abstraction. In this paper, we present WikiHow, a dataset of more than 230,000 article and summary pairs extracted and constructed from an online knowledge base written by different human authors. The articles span a wide range of topics and therefore represent high diversity styles. We evaluate the performance of the existing methods on WikiHow to present its challenges and set some baselines to further improve it.


  Access Paper or Ask Questions

Sparse Three-parameter Restricted Indian Buffet Process for Understanding International Trade

Jun 29, 2018
Melanie F. Pradier, Viktor Stojkoski, Zoran Utkovski, Ljupco Kocarev, Fernando Perez-Cruz

This paper presents a Bayesian nonparametric latent feature model specially suitable for exploratory analysis of high-dimensional count data. We perform a non-negative doubly sparse matrix factorization that has two main advantages: not only we are able to better approximate the row input distributions, but the inferred topics are also easier to interpret. By combining the three-parameter and restricted Indian buffet processes into a single prior, we increase the model flexibility, allowing for a full spectrum of sparse solutions in the latent space. We demonstrate the usefulness of our approach in the analysis of countries' economic structure. Compared to other approaches, empirical results show our model's ability to give easy-to-interpret information and better capture the underlying sparsity structure of data.

* To appear in the proceedings of ICASSP 2018 

  Access Paper or Ask Questions

Expression Empowered ResiDen Network for Facial Action Unit Detection

Jun 13, 2018
Shreyank Jyoti, Abhinav Dhall

The paper explores the topic of Facial Action Unit (FAU) detection in the wild. In particular, we are interested in answering the following questions: (1) how useful are residual connections across dense blocks for face analysis? (2) how useful is the information from a network trained for categorical Facial Expression Recognition (FER) for the task of FAU detection? The proposed network (ResiDen) exploits dense blocks along with residual connections and uses auxiliary information from a FER network. The experiments are performed on the EmotionNet and DISFA datasets. The experiments show the usefulness of facial expression information for AU detection. The proposed network achieves state-of-art results on the two databases. Analysis of the results for cross database protocol shows the effectiveness of the network.


  Access Paper or Ask Questions

Learning Joint Gaussian Representations for Movies, Actors, and Literary Characters

Apr 06, 2018
Hannah Kim, Denys Katerenchuk, Daniel Billet, Haesun Park, Boyang Li

Understanding of narrative content has become an increasingly popular topic. However, narrative semantics pose difficult challenges as the effects of multiple narrative facets, such as the text, events, character types, and genres, are tightly intertwined. We present a joint representation learning framework for embedding actors, literary characters, movies, genres, and descriptive keywords as Gaussian distributions and translation vectors on the Gaussian means. The Gaussian variance naturally corresponds to actors' versatility, a central concept in acting. Our estimate of actors' versatility agree with domain experts' rankings 65.95% of the time. This is, to our knowledge, the first computational technique for estimating this semantic concept. Additionally, the model substantially outperforms a TransE baseline in prediction of actor casting choices.


  Access Paper or Ask Questions

Anomaly Detection by Robust Statistics

Oct 14, 2017
Peter J. Rousseeuw, Mia Hubert

Real data often contain anomalous cases, also known as outliers. These may spoil the resulting analysis but they may also contain valuable information. In either case, the ability to detect such anomalies is essential. A useful tool for this purpose is robust statistics, which aims to detect the outliers by first fitting the majority of the data and then flagging data points that deviate from it. We present an overview of several robust methods and the resulting graphical outlier detection tools. We discuss robust procedures for univariate, low-dimensional, and high-dimensional data, such as estimating location and scatter, linear regression, principal component analysis, classification, clustering, and functional data analysis. Also the challenging new topic of cellwise outliers is introduced.

* To appear in WIREs Data Mining and Knowledge Discovery 

  Access Paper or Ask Questions

Contrastive Learning for Image Captioning

Oct 06, 2017
Bo Dai, Dahua Lin

Image captioning, a popular topic in computer vision, has achieved substantial progress in recent years. However, the distinctiveness of natural descriptions is often overlooked in previous work. It is closely related to the quality of captions, as distinctive captions are more likely to describe images with their unique aspects. In this work, we propose a new learning method, Contrastive Learning (CL), for image captioning. Specifically, via two constraints formulated on top of a reference model, the proposed method can encourage distinctiveness, while maintaining the overall quality of the generated captions. We tested our method on two challenging datasets, where it improves the baseline model by significant margins. We also showed in our studies that the proposed method is generic and can be used for models with various structures.

* accepted to 31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA 

  Access Paper or Ask Questions

Sub-domain Modelling for Dialogue Management with Hierarchical Reinforcement Learning

Jul 17, 2017
Paweł Budzianowski, Stefan Ultes, Pei-Hao Su, Nikola Mrkšić, Tsung-Hsien Wen, Iñigo Casanueva, Lina Rojas-Barahona, Milica Gašić

Human conversation is inherently complex, often spanning many different topics/domains. This makes policy learning for dialogue systems very challenging. Standard flat reinforcement learning methods do not provide an efficient framework for modelling such dialogues. In this paper, we focus on the under-explored problem of multi-domain dialogue management. First, we propose a new method for hierarchical reinforcement learning using the option framework. Next, we show that the proposed architecture learns faster and arrives at a better policy than the existing flat ones do. Moreover, we show how pretrained policies can be adapted to more complex systems with an additional set of new actions. In doing that, we show that our approach has the potential to facilitate policy optimisation for more sophisticated multi-domain dialogue systems.

* Update of the section 4 and the bibliography 

  Access Paper or Ask Questions

<<
238
239
240
241
242
243
244
245
246
247
248
249
250
>>