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

2nd Place Solution to the GQA Challenge 2019

Aug 16, 2019
Shijie Geng, Ji Zhang, Hang Zhang, Ahmed Elgammal, Dimitris N. Metaxas

We present a simple method that achieves unexpectedly superior performance for Complex Reasoning involved Visual Question Answering. Our solution collects statistical features from high-frequency words of all the questions asked about an image and use them as accurate knowledge for answering further questions of the same image. We are fully aware that this setting is not ubiquitously applicable, and in a more common setting one should assume the questions are asked separately and they cannot be gathered to obtain a knowledge base. Nonetheless, we use this method as an evidence to demonstrate our observation that the bottleneck effect is more severe on the feature extraction part than it is on the knowledge reasoning part. We show significant gaps when using the same reasoning model with 1) ground-truth features; 2) statistical features; 3) detected features from completely learned detectors, and analyze what these gaps mean to researches on visual reasoning topics. Our model with the statistical features achieves the 2nd place in the GQA Challenge 2019.

  Access Paper or Ask Questions

Graph Star Net for Generalized Multi-Task Learning

Jun 21, 2019
Lu Haonan, Seth H. Huang, Tian Ye, Guo Xiuyan

In this work, we present graph star net (GraphStar), a novel and unified graph neural net architecture which utilizes message-passing relay and attention mechanism for multiple prediction tasks - node classification, graph classification and link prediction. GraphStar addresses many earlier challenges facing graph neural nets and achieves non-local representation without increasing the model depth or bearing heavy computational costs. We also propose a new method to tackle topic-specific sentiment analysis based on node classification and text classification as graph classification. Our work shows that 'star nodes' can learn effective graph-data representation and improve on current methods for the three tasks. Specifically, for graph classification and link prediction, GraphStar outperforms the current state-of-the-art models by 2-5% on several key benchmarks.

  Access Paper or Ask Questions

Neural Legal Judgment Prediction in English

Jun 05, 2019
Ilias Chalkidis, Ion Androutsopoulos, Nikolaos Aletras

Legal judgment prediction is the task of automatically predicting the outcome of a court case, given a text describing the case's facts. Previous work on using neural models for this task has focused on Chinese; only feature-based models (e.g., using bags of words and topics) have been considered in English. We release a new English legal judgment prediction dataset, containing cases from the European Court of Human Rights. We evaluate a broad variety of neural models on the new dataset, establishing strong baselines that surpass previous feature-based models in three tasks: (1) binary violation classification; (2) multi-label classification; (3) case importance prediction. We also explore if models are biased towards demographic information via data anonymization. As a side-product, we propose a hierarchical version of BERT, which bypasses BERT's length limitation.

* 7 pages, short paper at ACL 2019 

  Access Paper or Ask Questions

"President Vows to Cut <Taxes> Hair": Dataset and Analysis of Creative Text Editing for Humorous Headlines

Jun 01, 2019
Nabil Hossain, John Krumm, Michael Gamon

We introduce, release, and analyze a new dataset, called Humicroedit, for research in computational humor. Our publicly available data consists of regular English news headlines paired with versions of the same headlines that contain simple replacement edits designed to make them funny. We carefully curated crowdsourced editors to create funny headlines and judges to score a to a total of 15,095 edited headlines, with five judges per headline. The simple edits, usually just a single word replacement, mean we can apply straightforward analysis techniques to determine what makes our edited headlines humorous. We show how the data support classic theories of humor, such as incongruity, superiority, and setup/punchline. Finally, we develop baseline classifiers that can predict whether or not an edited headline is funny, which is a first step toward automatically generating humorous headlines as an approach to creating topical humor.

* Accepted in NAACL 2019 

  Access Paper or Ask Questions

A Comparative Analysis of Distributional Term Representations for Author Profiling in Social Media

May 21, 2019
Miguel Á. Álvarez-Carmona, Esaú Villatoro-Tello, Manuel Montes-y-Gómez, Luis Villaseñor-Pienda

Author Profiling (AP) aims at predicting specific characteristics from a group of authors by analyzing their written documents. Many research has been focused on determining suitable features for modeling writing patterns from authors. Reported results indicate that content-based features continue to be the most relevant and discriminant features for solving this task. Thus, in this paper, we present a thorough analysis regarding the appropriateness of different distributional term representations (DTR) for the AP task. In this regard, we introduce a novel framework for supervised AP using these representations and, supported on it. We approach a comparative analysis of representations such as DOR, TCOR, SSR, and word2vec in the AP problem. We also compare the performance of the DTRs against classic approaches including popular topic-based methods. The obtained results indicate that DTRs are suitable for solving the AP task in social media domains as they achieve competitive results while providing meaningful interpretability.

* Journal of Intelligent & Fuzzy Systems, vol. 36, no. 5, pp. 4857-4868, 2019 

  Access Paper or Ask Questions

PL-NMF: Parallel Locality-Optimized Non-negative Matrix Factorization

Apr 16, 2019
Gordon E. Moon, Aravind Sukumaran-Rajam, Srinivasan Parthasarathy, P. Sadayappan

Non-negative Matrix Factorization (NMF) is a key kernel for unsupervised dimension reduction used in a wide range of applications, including topic modeling, recommender systems and bioinformatics. Due to the compute-intensive nature of applications that must perform repeated NMF, several parallel implementations have been developed in the past. However, existing parallel NMF algorithms have not addressed data locality optimizations, which are critical for high performance since data movement costs greatly exceed the cost of arithmetic/logic operations on current computer systems. In this paper, we devise a parallel NMF algorithm based on the HALS (Hierarchical Alternating Least Squares) scheme that incorporates algorithmic transformations to enhance data locality. Efficient realizations of the algorithm on multi-core CPUs and GPUs are developed, demonstrating significant performance improvement over existing state-of-the-art parallel NMF algorithms.

* 11 pages, 5 tables, 9 figures 

  Access Paper or Ask Questions

A Two-Step Pursuit-Evasion Algorithm for Autonomous Underwater Vehicles

Feb 22, 2019
Özer Özkahraman, Petter Ögren

In this paper, we consider the problem of pursuit-evasion using multiple Autonomous Underwater Vehicles (AUVs) in a 3D water volume, with and without obstacles in terms of islands and the seabed topography. Pursuit-evasion is a well studied topic in robotics, but the results are mostly set in 2D environments, using unlimited line-of-sight sensing. We propose an algorithm for range-limited sensing in 3D environments that captures a finite-speed evader based on a single previous observation of its location. The pursuers are first moved to form a cage formation that contains the evader while minimizing the number of pursuers required. Upon completion of the initial cage, the cage is then changed to a smaller spherical cage that is shrunk until every part of the volume containing the evader is sensed, capturing the evader. The pursuers only need minimal communication and computation while the mission is carried out and most of the computation is done beforehand, allowing for easy implementation.

* 8 pages, submitted to RA-L 2019 

  Access Paper or Ask Questions

Measuring Issue Ownership using Word Embeddings

Oct 31, 2018
Amaru Cuba Gyllensten, Magnus Sahlgren

Sentiment and topic analysis are common methods used for social media monitoring. Essentially, these methods answers questions such as, "what is being talked about, regarding X", and "what do people feel, regarding X". In this paper, we investigate another venue for social media monitoring, namely issue ownership and agenda setting, which are concepts from political science that have been used to explain voter choice and electoral outcomes. We argue that issue alignment and agenda setting can be seen as a kind of semantic source similarity of the kind "how similar is source A to issue owner P, when talking about issue X", and as such can be measured using word/document embedding techniques. We present work in progress towards measuring that kind of conditioned similarity, and introduce a new notion of similarity for predictive embeddings. We then test this method by measuring the similarity between politically aligned media and political parties, conditioned on bloc-specific issues.

* Accepted to the 9th Workshop on Computational Approaches to Subjectivity, Sentiment & Social Media Analysis (WASSA), held in conjunction with the EMNLP 2018 conference 

  Access Paper or Ask Questions

WiSeBE: Window-based Sentence Boundary Evaluation

Aug 27, 2018
Carlos-Emiliano González-Gallardo, Juan-Manuel Torres-Moreno

Sentence Boundary Detection (SBD) has been a major research topic since Automatic Speech Recognition transcripts have been used for further Natural Language Processing tasks like Part of Speech Tagging, Question Answering or Automatic Summarization. But what about evaluation? Do standard evaluation metrics like precision, recall, F-score or classification error; and more important, evaluating an automatic system against a unique reference is enough to conclude how well a SBD system is performing given the final application of the transcript? In this paper we propose Window-based Sentence Boundary Evaluation (WiSeBE), a semi-supervised metric for evaluating Sentence Boundary Detection systems based on multi-reference (dis)agreement. We evaluate and compare the performance of different SBD systems over a set of Youtube transcripts using WiSeBE and standard metrics. This double evaluation gives an understanding of how WiSeBE is a more reliable metric for the SBD task.

* In proceedings of the 17th Mexican International Conference on Artificial Intelligence (MICAI), 2018 

  Access Paper or Ask Questions