BIBI System Description: Building with CNNs and Breaking with Deep Reinforcement Learning

2017-09-01 · WS 2017 9 · Yitong Li, Trevor Cohn, Timothy Baldwin

This paper describes our submission to the sentiment analysis sub-task of {``}Build It, Break It: The Language Edition (BIBI){''}, on both the builder and breaker sides. As a builder, we use convolutional neural nets, trained on both phrase and sentence data. As a breaker, we use Q-learning to learn minimal change pairs, and apply a token substitution method automatically. We analyse the results to gauge the robustness of NLP systems.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Deep Reinforcement LearningQ-Learningreinforcement-learning Reinforcement Learning Reinforcement Learning (RL)SentenceSentiment Analysis Text Classification

Methods 이 논문이 사용한 방법론

Q-Learning Q-Learning is an off-policy temporal difference control algorithm: $$Q\left(S\_{t}, A\_{t}\right) \leftarrow Q\left(S\_{t}, A\_{t}\right) + \alpha\left[R_{t+1} +…

BIBI: Bayesian Inference of Breed Composition

2017-09-26

The aim of this paper was to develop statistical models to estimate individual breed composition based on the previously proposed idea of regressing discrete random variables corresponding to counts of reference alleles …

Bayesian Inference regression

Habibi: Laying the Open-Source Foundation of Unified-Dialectal Arabic Speech Synthesis

2026-01-20 · Yushen Chen, Junzhe Liu, Yujie Tu, Zhikang Niu 외 arxiv

Arabic spans over 30 spoken varieties, yet no open-source text-to-speech system unifies them. Key barriers include substantial cross-dialect lexical and phonological divergence, scarce synthesis-grade data, and the absen…

Speech Synthesis

Comment on "On the Extraction of Purely Motor EEG Neural Correlates during an Upper Limb Visuomotor Task"

2022-07-22 · Patrick Ofner, Joana Pereira, Reinmar Kobler, Andreas Schwarz 외

Bibian et al. show in their recent paper (Bibi\'an et al. 2021) that eye and head movements can affect the EEG-based classification in a reaching motor task. These movements can generate artefacts that can cause an overo…

Classification EEG Electroencephalogram (EEG)

Simulation and Prediction of Countercurrent Spontaneous Imbibition at Early and Late Times Using Physics-Informed Neural Networks

2023-05-06 · Jassem Abbasi, Pål Østebø Andersen

The application of Physics-Informed Neural Networks (PINNs) is investigated for the first time in solving the one-dimensional Countercurrent spontaneous imbibition (COUCSI) problem at both early and late time (i.e., befo…

BiBiKit - A Bilingual Bimodal Reading and Writing Tool for Sign Language Users

2012-05-01 · LREC 2012 5 · Nedelina Ivanova, Olle Eriksen

Sign language is used by many people who were born deaf or who became deaf early in life use as their first and/or preferred language. There is no writing system for sign languages; texts are signed on video. As a conseq…

Navigate Part-Of-Speech Tagging Sentence