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

A Generative Approach for Financial Causality Extraction

Apr 12, 2022
Tapas Nayak, Soumya Sharma, Yash Butala, Koustuv Dasgupta, Pawan Goyal, Niloy Ganguly

Causality represents the foremost relation between events in financial documents such as financial news articles, financial reports. Each financial causality contains a cause span and an effect span. Previous works proposed sequence labeling approaches to solve this task. But sequence labeling models find it difficult to extract multiple causalities and overlapping causalities from the text segments. In this paper, we explore a generative approach for causality extraction using the encoder-decoder framework and pointer networks. We use a causality dataset from the financial domain, \textit{FinCausal}, for our experiments and our proposed framework achieves very competitive performance on this dataset.

* Accepted at FinWeb 2022 workshop of WWW 2022 

  Access Paper or Ask Questions

Infusing Knowledge from Wikipedia to Enhance Stance Detection

Apr 08, 2022
Zihao He, Negar Mokhberian, Kristina Lerman

Stance detection infers a text author's attitude towards a target. This is challenging when the model lacks background knowledge about the target. Here, we show how background knowledge from Wikipedia can help enhance the performance on stance detection. We introduce Wikipedia Stance Detection BERT (WS-BERT) that infuses the knowledge into stance encoding. Extensive results on three benchmark datasets covering social media discussions and online debates indicate that our model significantly outperforms the state-of-the-art methods on target-specific stance detection, cross-target stance detection, and zero/few-shot stance detection.


  Access Paper or Ask Questions

GIFAIR-FL: An Approach for Group and Individual Fairness in Federated Learning

Aug 05, 2021
Xubo Yue, Maher Nouiehed, Raed Al Kontar

In this paper we propose \texttt{GIFAIR-FL}: an approach that imposes group and individual fairness to federated learning settings. By adding a regularization term, our algorithm penalizes the spread in the loss of client groups to drive the optimizer to fair solutions. Theoretically, we show convergence in non-convex and strongly convex settings. Our convergence guarantees hold for both $i.i.d.$ and non-$i.i.d.$ data. To demonstrate the empirical performance of our algorithm, we apply our method on image classification and text prediction tasks. Compared to existing algorithms, our method shows improved fairness results while retaining superior or similar prediction accuracy.


  Access Paper or Ask Questions

[email protected] at SemEval-2021 Task 5: Semi-Supervised Learning and Dice Loss for Toxic Spans Detection

Apr 04, 2021
Archit Bansal, Abhay Kaushik, Ashutosh Modi

In this work, we present our approach and findings for SemEval-2021 Task 5 - Toxic Spans Detection. The task's main aim was to identify spans to which a given text's toxicity could be attributed. The task is challenging mainly due to two constraints: the small training dataset and imbalanced class distribution. Our paper investigates two techniques, semi-supervised learning and learning with Self-Adjusting Dice Loss, for tackling these challenges. Our submitted system (ranked ninth on the leader board) consisted of an ensemble of various pre-trained Transformer Language Models trained using either of the above-proposed techniques.

* Accepted at SemEval 2021 Task 5, 9 Pages (6 Pages main content + 1 Page for references + 2 Pages Appendix) 

  Access Paper or Ask Questions

Non-Autoregressive Translation by Learning Target Categorical Codes

Mar 21, 2021
Yu Bao, Shujian Huang, Tong Xiao, Dongqi Wang, Xinyu Dai, Jiajun Chen

Non-autoregressive Transformer is a promising text generation model. However, current non-autoregressive models still fall behind their autoregressive counterparts in translation quality. We attribute this accuracy gap to the lack of dependency modeling among decoder inputs. In this paper, we propose CNAT, which learns implicitly categorical codes as latent variables into the non-autoregressive decoding. The interaction among these categorical codes remedies the missing dependencies and improves the model capacity. Experiment results show that our model achieves comparable or better performance in machine translation tasks, compared with several strong baselines.

* 11 pages, 3 figures, 7 tables. Accepted by NAACL-2021 

  Access Paper or Ask Questions

GAN Vocoder: Multi-Resolution Discriminator Is All You Need

Mar 09, 2021
Jaeseong You, Dalhyun Kim, Gyuhyeon Nam, Geumbyeol Hwang, Gyeongsu Chae

Several of the latest GAN-based vocoders show remarkable achievements, outperforming autoregressive and flow-based competitors in both qualitative and quantitative measures while synthesizing orders of magnitude faster. In this work, we hypothesize that the common factor underlying their success is the multi-resolution discriminating framework, not the minute details in architecture, loss function, or training strategy. We experimentally test the hypothesis by evaluating six different generators paired with one shared multi-resolution discriminating framework. For all evaluative measures with respect to text-to-speech syntheses and for all perceptual metrics, their performances are not distinguishable from one another, which supports our hypothesis.


  Access Paper or Ask Questions

MixUp Training Leads to Reduced Overfitting and Improved Calibration for the Transformer Architecture

Feb 22, 2021
Wancong Zhang, Ieshan Vaidya

MixUp is a computer vision data augmentation technique that uses convex interpolations of input data and their labels to enhance model generalization during training. However, the application of MixUp to the natural language understanding (NLU) domain has been limited, due to the difficulty of interpolating text directly in the input space. In this study, we propose MixUp methods at the Input, Manifold, and sentence embedding levels for the transformer architecture, and apply them to finetune the BERT model for a diverse set of NLU tasks. We find that MixUp can improve model performance, as well as reduce test loss and model calibration error by up to 50%.


  Access Paper or Ask Questions

Patterns, predictions, and actions: A story about machine learning

Feb 10, 2021
Moritz Hardt, Benjamin Recht

This graduate textbook on machine learning tells a story of how patterns in data support predictions and consequential actions. Starting with the foundations of decision making, we cover representation, optimization, and generalization as the constituents of supervised learning. A chapter on datasets as benchmarks examines their histories and scientific bases. Self-contained introductions to causality, the practice of causal inference, sequential decision making, and reinforcement learning equip the reader with concepts and tools to reason about actions and their consequences. Throughout, the text discusses historical context and societal impact. We invite readers from all backgrounds; some experience with probability, calculus, and linear algebra suffices.


  Access Paper or Ask Questions

Combining pre-trained language models and structured knowledge

Feb 05, 2021
Pedro Colon-Hernandez, Catherine Havasi, Jason Alonso, Matthew Huggins, Cynthia Breazeal

In recent years, transformer-based language models have achieved state of the art performance in various NLP benchmarks. These models are able to extract mostly distributional information with some semantics from unstructured text, however it has proven challenging to integrate structured information, such as knowledge graphs into these models. We examine a variety of approaches to integrate structured knowledge into current language models and determine challenges, and possible opportunities to leverage both structured and unstructured information sources. From our survey, we find that there are still opportunities at exploiting adapter-based injections and that it may be possible to further combine various of the explored approaches into one system.

* Updated references 

  Access Paper or Ask Questions

<<
956
957
958
959
960
961
962
963
964
965
966
967
968
>>