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

Chrome logo Add to Chrome

Firefox logo Add to Firefox

"Text": models, code, and papers

Multi-modal Ensemble Models for Predicting Video Memorability

Feb 01, 2021
Tony Zhao, Irving Fang, Jeffrey Kim, Gerald Friedland

Modeling media memorability has been a consistent challenge in the field of machine learning. The Predicting Media Memorability task in MediaEval2020 is the latest benchmark among similar challenges addressing this topic. Building upon techniques developed in previous iterations of the challenge, we developed ensemble methods with the use of extracted video, image, text, and audio features. Critically, in this work we introduce and demonstrate the efficacy and high generalizability of extracted audio embeddings as a feature for the task of predicting media memorability.

  Access Paper or Ask Questions

UniCase -- Rethinking Casing in Language Models

Oct 22, 2020
Rafal Powalski, Tomasz Stanislawek

In this paper, we introduce a new approach to dealing with the problem of case-sensitiveness in Language Modelling (LM). We propose simple architecture modification to the RoBERTa language model, accompanied by a new tokenization strategy, which we named Unified Case LM (UniCase). We tested our solution on the GLUE benchmark, which led to increased performance by 0.42 points. Moreover, we prove that the UniCase model works much better when we have to deal with text data, where all tokens are uppercased (+5.88 point).

  Access Paper or Ask Questions

Document Similarity from Vector Space Densities

Sep 01, 2020
Ilia Rushkin

We propose a computationally light method for estimating similarities between text documents, which we call the density similarity (DS) method. The method is based on a word embedding in a high-dimensional Euclidean space and on kernel regression, and takes into account semantic relations among words. We find that the accuracy of this method is virtually the same as that of a state-of-the-art method, while the gain in speed is very substantial. Additionally, we introduce generalized versions of the top-k accuracy metric and of the Jaccard metric of agreement between similarity models.

* In: Arai K., Kapoor S., Bhatia R. (eds) Intelligent Systems and Applications. IntelliSys 2020. Advances in Intelligent Systems and Computing, vol 1251. Springer, Cham 
* 12 pages, 3 figures 

  Access Paper or Ask Questions

Topological Sort for Sentence Ordering

May 01, 2020
Shrimai Prabhumoye, Ruslan Salakhutdinov, Alan W Black

Sentence ordering is the task of arranging the sentences of a given text in the correct order. Recent work using deep neural networks for this task has framed it as a sequence prediction problem. In this paper, we propose a new framing of this task as a constraint solving problem and introduce a new technique to solve it. Additionally, we propose a human evaluation for this task. The results on both automatic and human metrics across four different datasets show that this new technique is better at capturing coherence in documents.

* Will be published at the Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (ACL) 2020 

  Access Paper or Ask Questions

An In-depth Walkthrough on Evolution of Neural Machine Translation

Apr 10, 2020
Rohan Jagtap, Dr. Sudhir N. Dhage

Neural Machine Translation (NMT) methodologies have burgeoned from using simple feed-forward architectures to the state of the art; viz. BERT model. The use cases of NMT models have been broadened from just language translations to conversational agents (chatbots), abstractive text summarization, image captioning, etc. which have proved to be a gem in their respective applications. This paper aims to study the major trends in Neural Machine Translation, the state of the art models in the domain and a high level comparison between them.

* 10 pages, 10 figures 

  Access Paper or Ask Questions

An Efficient Model for Sentiment Analysis of Electronic Product Reviews in Vietnamese

Oct 29, 2019
Suong N. Hoang, Linh V. Nguyen, Tai Huynh, Vuong T. Pham

In the past few years, the growth of e-commerce and digital marketing in Vietnam has generated a huge volume of opinionated data. Analyzing those data would provide enterprises with insight for better business decisions. In this work, as part of the Advosights project, we study sentiment analysis of product reviews in Vietnamese. The final solution is based on Self-attention neural networks, a flexible architecture for text classification task with about 90.16% of accuracy in 0.0124 second, a very fast inference time.

  Access Paper or Ask Questions

Ellipsis and Coreference Resolution as Question Answering

Aug 29, 2019
Rahul Aralikatte, Matthew Lamm, Daniel Hardt, Anders Søgaard

Coreference and many forms of ellipsis are similar to reading comprehension questions, in that in order to resolve these, we need to identify an appropriate text span in the previous discourse. This paper exploits this analogy and proposes to use an architecture developed for machine comprehension for ellipsis and coreference resolution. We present both single-task and joint models and evaluate them across standard benchmarks, outperforming the current state of the art for ellipsis by up to 48.5% error reduction -- and for coreference by 37.5% error reduction.

* Preprint. Work in progress 

  Access Paper or Ask Questions

Variational Gaussian Processes with Signature Covariances

Jun 19, 2019
Csaba Toth, Harald Oberhauser

We introduce a Bayesian approach to learn from stream-valued data by using Gaussian processes with the recently introduced signature kernel as covariance function. To cope with the computational complexity in time and memory that arises with long streams that evolve in large state spaces, we develop a variational Bayes approach with sparse inducing tensors. We provide an implementation based on GPFlow and benchmark this variational Gaussian process model on supervised classification tasks for time series and text (a stream of words).

  Access Paper or Ask Questions

Fashion-Gen: The Generative Fashion Dataset and Challenge

Jul 30, 2018
Negar Rostamzadeh, Seyedarian Hosseini, Thomas Boquet, Wojciech Stokowiec, Ying Zhang, Christian Jauvin, Chris Pal

We introduce a new dataset of 293,008 high definition (1360 x 1360 pixels) fashion images paired with item descriptions provided by professional stylists. Each item is photographed from a variety of angles. We provide baseline results on 1) high-resolution image generation, and 2) image generation conditioned on the given text descriptions. We invite the community to improve upon these baselines. In this paper, we also outline the details of a challenge that we are launching based upon this dataset.

  Access Paper or Ask Questions

The mind as a computational system

Dec 01, 2017
Christoph Adami

The present document is an excerpt of an essay that I wrote as part of my application material to graduate school in Computer Science (with a focus on Artificial Intelligence), in 1986. I was not invited by any of the schools that received it, so I became a theoretical physicist instead. The essay's full title was "Some Topics in Philosophy and Computer Science". I am making this text (unchanged from 1985, preserving the typesetting as much as possible) available now in memory of Jerry Fodor, whose writings had influenced me significantly at the time (even though I did not always agree).

* 17 pages with three figures. In memory of Jerry Fodor 

  Access Paper or Ask Questions