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

PENELOPIE: Enabling Open Information Extraction for the Greek Language through Machine Translation

Mar 28, 2021
Dimitris Papadopoulos, Nikolaos Papadakis, Nikolaos Matsatsinis

In this paper we present our submission for the EACL 2021 SRW; a methodology that aims at bridging the gap between high and low-resource languages in the context of Open Information Extraction, showcasing it on the Greek language. The goals of this paper are twofold: First, we build Neural Machine Translation (NMT) models for English-to-Greek and Greek-to-English based on the Transformer architecture. Second, we leverage these NMT models to produce English translations of Greek text as input for our NLP pipeline, to which we apply a series of pre-processing and triple extraction tasks. Finally, we back-translate the extracted triples to Greek. We conduct an evaluation of both our NMT and OIE methods on benchmark datasets and demonstrate that our approach outperforms the current state-of-the-art for the Greek natural language.

* 16th conference of the European Chapter of the Association for Computational Linguistics Student Research Workshop (EACL 2021 SRW) 

  Access Paper or Ask Questions

Gradient Descent on Neural Networks Typically Occurs at the Edge of Stability

Feb 26, 2021
Jeremy M. Cohen, Simran Kaur, Yuanzhi Li, J. Zico Kolter, Ameet Talwalkar

We empirically demonstrate that full-batch gradient descent on neural network training objectives typically operates in a regime we call the Edge of Stability. In this regime, the maximum eigenvalue of the training loss Hessian hovers just above the numerical value $2 / \text{(step size)}$, and the training loss behaves non-monotonically over short timescales, yet consistently decreases over long timescales. Since this behavior is inconsistent with several widespread presumptions in the field of optimization, our findings raise questions as to whether these presumptions are relevant to neural network training. We hope that our findings will inspire future efforts aimed at rigorously understanding optimization at the Edge of Stability. Code is available at

* To appear in ICLR 2021. 72 pages, 107 figures 

  Access Paper or Ask Questions

Exclusive Topic Modeling

Feb 06, 2021
Hao Lei, Ying Chen

We propose an Exclusive Topic Modeling (ETM) for unsupervised text classification, which is able to 1) identify the field-specific keywords though less frequently appeared and 2) deliver well-structured topics with exclusive words. In particular, a weighted Lasso penalty is imposed to reduce the dominance of the frequently appearing yet less relevant words automatically, and a pairwise Kullback-Leibler divergence penalty is used to implement topics separation. Simulation studies demonstrate that the ETM detects the field-specific keywords, while LDA fails. When applying to the benchmark NIPS dataset, the topic coherence score on average improves by 22% and 10% for the model with weighted Lasso penalty and pairwise Kullback-Leibler divergence penalty, respectively.

  Access Paper or Ask Questions

Spell Correction for Azerbaijani Language using Deep Neural Networks

Feb 05, 2021
Ahmad Ahmadzade, Saber Malekzadeh

Spell correction is used to detect and correct orthographic mistakes in texts. Most of the time, traditional dictionary lookup with string similarity methods is suitable for the languages that have a less complex structure such as the English language. However, the Azerbaijani language has a more complex structure and due to its morphological structure, the derivation of words is plenty that several words are derived from adding suffices, affixes to the words. Therefore, in this paper sequence to sequence model with an attention mechanism is used to develop spelling correction for Azerbaijani. Total 12000 wrong and correct sentence pairs used for training, and the model is tested on 1000 real-world misspelled words and F1-score results are 75% for distance 0, 90% for distance 1, and 96% for distance 2.

  Access Paper or Ask Questions

Variance Based Samples Weighting for Supervised Deep Learning

Jan 28, 2021
Paul Novello, Gaël Poëtte, David Lugato, Pietro Congedo

In the context of supervised learning of a function by a Neural Network (NN), we claim and empirically justify that a NN yields better results when the distribution of the data set focuses on regions where the function to learn is steeper. We first traduce this assumption in a mathematically workable way using Taylor expansion. Then, theoretical derivations allow to construct a methodology that we call Variance Based Samples Weighting (VBSW). VBSW uses local variance of the labels to weight the training points. This methodology is general, scalable, cost effective, and significantly increases the performances of a large class of NNs for various classification and regression tasks on image, text and multivariate data. We highlight its benefits with experiments involving NNs from shallow linear NN to Resnet or Bert.

  Access Paper or Ask Questions

KM-BART: Knowledge Enhanced Multimodal BART for Visual Commonsense Generation

Jan 02, 2021
Yiran Xing, Zai Shi, Zhao Meng, Yunpu Ma, Roger Wattenhofer

We present Knowledge Enhanced Multimodal BART (KM-BART), which is a Transformer-based sequence-to-sequence model capable of reasoning about commonsense knowledge from multimodal inputs of images and texts. We extend the popular BART architecture to a multi-modal model. We design a new pretraining task to improve the model performance on Visual Commonsense Generation task. Our pretraining task improves the Visual Commonsense Generation performance by leveraging knowledge from a large language model pretrained on an external knowledge graph. To the best of our knowledge, we are the first to propose a dedicated task for improving model performance on Visual Commonsense Generation. Experimental results show that by pretraining, our model reaches state-of-the-art performance on the Visual Commonsense Generation task.

* Work in progress. The first three authors contribute equally to this work 

  Access Paper or Ask Questions

No Budget? Don't Flex! Cost Consideration when Planning to Adopt NLP for Your Business

Dec 16, 2020
Made Nindyatama Nityasya, Haryo Akbarianto Wibowo, Radityo Eko Prasojo, Alham Fikri Aji

Recent advances in Natural Language Processing (NLP) have largely pushed deep transformer-based models as the go-to state-of-the-art technique without much regard to the production and utilization cost. Companies planning to adopt these methods into their business face difficulties because of the lack of machine and human resources to build them. In this work, we compare both the performance and the cost of classical learning algorithms to the latest ones in common sequence and text labeling tasks. We find that classical models often perform on par with deep neural ones despite the lower cost. We argue that under many circumstances the smaller and lighter models fit better for AI-pivoting businesses and that we call for more research into low-cost models, especially for under-resourced languages.

* 9 pages, 2 figures 

  Access Paper or Ask Questions

Hey Alexa what did I just type? Decoding smartphone sounds with a voice assistant

Dec 01, 2020
Almos Zarandy, Ilia Shumailov, Ross Anderson

Voice assistants are now ubiquitous and listen in on our everyday lives. Ever since they became commercially available, privacy advocates worried that the data they collect can be abused: might private conversations be extracted by third parties? In this paper we show that privacy threats go beyond spoken conversations and include sensitive data typed on nearby smartphones. Using two different smartphones and a tablet we demonstrate that the attacker can extract PIN codes and text messages from recordings collected by a voice assistant located up to half a meter away. This shows that remote keyboard-inference attacks are not limited to physical keyboards but extend to virtual keyboards too. As our homes become full of always-on microphones, we need to work through the implications.

  Access Paper or Ask Questions

Using IPA-Based Tacotron for Data Efficient Cross-Lingual Speaker Adaptation and Pronunciation Enhancement

Nov 12, 2020
Hamed Hemati, Damian Borth

Recent neural Text-to-Speech (TTS) models have been shown to perform very well when enough data is available. However, fine-tuning them towards a new speaker or a new language is not as straight-forward in a low-resource setup. In this paper, we show that by applying minor changes to a Tacotron model, one can transfer an existing TTS model for a new speaker with the same or a different language using only 20 minutes of data. For this purpose, we first introduce a baseline multi-lingual Tacotron with language-agnostic input, then show how transfer learning is done for different scenarios of speaker adaptation without exploiting any pre-trained speaker encoder or code-switching technique. We evaluate the transferred model in both subjective and objective ways.

* 5 pages 

  Access Paper or Ask Questions