Filters








32,639 Hits in 6.0 sec

A Framework for Decoding Event-Related Potentials from Text [article]

Shaorong Yan, Aaron Steven White
2019 arXiv   pre-print
We propose a novel framework for modeling event-related potentials (ERPs) collected during reading that couples pre-trained convolutional decoders with a language model.  ...  Using this framework, we compare the abilities of a variety of existing and novel sentence processing models to reconstruct ERPs.  ...  Stefan Frank for sharing the EEG data, sentence materials, and language model predictors.  ... 
arXiv:1902.10296v2 fatcat:lvbtmplatvggfjigpornr6keaa

A Framework for Decoding Event-Related Potentials from Text

Shaorong Yan, Aaron Steven White
2019 Proceedings of the Workshop on Cognitive Modeling and Computational Linguistics   unpublished
We propose a novel framework for modeling event-related potentials (ERPs) collected during reading that couples pre-trained convolutional decoders with a language model.  ...  Using this framework, we compare the abilities of a variety of existing and novel sentence processing models to reconstruct ERPs.  ...  Stefan Frank for sharing the EEG data, sentence materials, and language model predictors.  ... 
doi:10.18653/v1/w19-2910 fatcat:dzpfucuafnaptex3wnycahzfti

Diffsound: Discrete Diffusion Model for Text-to-sound Generation [article]

Dongchao Yang, Jianwei Yu, Helin Wang, Wen Wang, Chao Weng, Yuexian Zou, Dong Yu
2022 arXiv   pre-print
The framework first uses the decoder to transfer the text features extracted from the text encoder to a mel-spectrogram with the help of VQ-VAE, and then the vocoder is used to transform the generated  ...  In this study, we investigate generating sound conditioned on a text prompt and propose a novel text-to-sound generation framework that consists of a text encoder, a Vector Quantized Variational Autoencoder  ...  The diagram of the text-to-sound generation framework includes four parts: a text encoder that extracts text features from the text input, a decoder that generates mel-spectrogram tokens, a pre-trained  ... 
arXiv:2207.09983v1 fatcat:hvq5xxf66jaqbp6v5rupgeie24

A Novel Sequence Tagging Framework for Consumer Event-Cause Extraction [article]

Congqing He, Jie Zhang, Xiangyu Zhu, Huan Liu, Yukun Huang
2021 arXiv   pre-print
To this end, we introduce a fresh perspective to revisit the relational event-cause extraction task and propose a novel sequence tagging framework, instead of extracting event types and events-causes separately  ...  Consumer Event-Cause Extraction, the task aimed at extracting the potential causes behind certain events in the text, has gained much attention in recent years due to its wide applications.  ...  We are very grateful to the organizing team Xindong Wu and Kang Liu for their great efforts during the challenge.  ... 
arXiv:2110.15722v1 fatcat:xabr5qi6zjhmldl4x5ft4tn7dm

Semantic Interpretation of Structured Log Files

Piyush Nimbalkar, Varish Mulwad, Nikhil Puranik, Anupam Joshi, Tim Finin
2016 2016 IEEE 17th International Conference on Information Reuse and Integration (IRI)  
We describe a framework for analyzing logs and automatically generating a semantic description of their schema and content in RDF.  ...  Data from computer log files record traces of events involving user activity, applications, system software and network traffic.  ...  ACKNOWLEDGMENT Support for this work was provided by NSF grants 1250627, 1228198 and a gift from Microsoft. One of the authors also acknowledges support from the Oros Family Professorship endowment.  ... 
doi:10.1109/iri.2016.81 dblp:conf/iri/NimbalkarMPJF16 fatcat:m5wqe3att5bjtn54i4qbp3x6cq

Graph-Based Decoding for Event Sequencing and Coreference Resolution [article]

Zhengzhong Liu, Teruko Mitamura, Eduard Hovy
2018 arXiv   pre-print
Events in text documents are interrelated in complex ways. In this paper, we study two types of relation: Event Coreference and Event Sequencing.  ...  We show that the popular tree-like decoding structure for automated Event Coreference is not suitable for Event Sequencing.  ...  In LAG, however, one node is allowed to link to multiple antecedents, creating a potential problem for decoding.  ... 
arXiv:1806.05099v1 fatcat:xkdzw3keeze3vglf6bfsuleh2m

Behaviour in social media for floods and heat waves in disaster response via Artificial Intelligence [article]

Victor Ponce-López, Catalina Spataru
2022 arXiv   pre-print
The positiveness of messages is around 8% for disaster, 1% for disaster and medical response, 7% for disaster and humanitarian related messages.  ...  We further analyse a set of behavioural indicators and match them with climate variables via decoding synoptical records to analyse thermal comfort.  ...  for events that could potentially cause major disruption.  ... 
arXiv:2203.08753v1 fatcat:bash7jpyevabtffe6ohpdqogtu

Event Extraction as Dependency Parsing

David McClosky, Mihai Surdeanu, Christopher D. Manning
2011 Annual Meeting of the Association for Computational Linguistics  
We explore a rich feature space that models both the events to be parsed and context from the original supporting text.  ...  We propose a simple approach for the extraction of such structures by taking the tree of event-argument relations and using it directly as the representation in a reranking dependency parser.  ...  Acknowledgments The authors would like to thank Mark Johnson for helpful discussions on the reranker component and the BioNLP shared task organizers, Sampo Pyysalo and Jin-Dong Kim, for answering questions  ... 
dblp:conf/acl/McCloskySM11 fatcat:3d664whvhbehhdeveqmq27m2me

Learning Sentence Representations over Tree Structures for Target-Dependent Classification

Junwen Duan, Xiao Ding, Ting Liu
2018 Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)  
Semantic compositions over tree structures are promising for such tasks, as they can potentially capture long-distance interactions between targets and their contexts.  ...  The underlying model is a RNN encoder-decoder that explores possible binary tree structures and a reward mechanism that encourages structures that improve performances on downstream tasks.  ...  Acknowledgements We would like to thank the anonymous reviewers for their insightful comments and suggestions to help improve this paper.  ... 
doi:10.18653/v1/n18-1051 dblp:conf/naacl/DuanDL18 fatcat:ep3biknc3jdrvl746mqmb2myui

Social Media Behaviour Analysis in Disaster-Response Messages of Floods and Heat Waves via Artificial Intelligence

Víctor Ponce-López, Catalina Spataru
2022 Computer and Information Science  
The resulting models are applied to perform a qualitative analysis via topic inference in text data.  ...  The positiveness of messages is around 8% for disaster, 1% for disaster and medical response, 7% for disaster and humanitarian related messages.  ...  Collaborative Research Action 2019: Disaster Risk, Reduction and Resilience (DR32019) which was supported by the Ministry of Science and Technology (MOST) of Chinese Taipei in partnership with funders from  ... 
doi:10.5539/cis.v15n3p18 fatcat:3eudvlq3jvcdxoqsk4siwnlknu

Experiences with the development of an MPEG-4-oriented PC multimedia application

Thomas Stingl, Rico Dreier, Olaf Barheine, Andrew G. Tescher, Bhaskaran Vasudev, V. Michael Bove, Jr., Barbara Derryberry
1999 Multimedia Systems and Applications  
Two different approaches for system integration were taken during the project term, one being a flexible combination of a Java System framework with native Decoder-software, the other a more MPEG-4 phase  ...  Based on this a general framework for system design comparison is outlined.  ...  The latter transfers colour values to the Material2D node of a Text node. Therefore the colour changes from the background colour (invisible text) to visible colour.  ... 
doi:10.1117/12.337453 fatcat:4p6xirtwjnaqvp74xc5boxmqgm

Forecasting People's Needs in Hurricane Events from Social Network [article]

Long Nguyen, Zhou Yang, Jia Li, Guofeng Cao, Fang Jin
2018 arXiv   pre-print
This paper presents a new sequence to sequence based framework for forecasting people's needs during disasters using social media and weather data.  ...  Social networks can serve as a valuable communication channel for calls for help, offering assistance, and coordinating rescue activities in disaster.  ...  This internal state plays as the context of the decoder in the second step. • The decoder: This is also a LSTM architecture that decodes the context received from encoder, and its output from previous  ... 
arXiv:1811.04577v1 fatcat:hnfq3p6tlfao3bxz7zi5hyze3i

Abstract Meaning Representation for Multi-Document Summarization [article]

Kexin Liao, Logan Lebanoff, Fei Liu
2018 arXiv   pre-print
Generating an abstract from a collection of documents is a desirable capability for many real-world applications.  ...  We also describe opportunities and challenges for advancing this line of research.  ...  Acknowledgements We are grateful to the anonymous reviewers for their insightful comments. The authors thank Chuan Wang, Jeffrey Flanigan, and Nathan Schneider for useful discussions.  ... 
arXiv:1806.05655v1 fatcat:w5iel6cyr5bdfh7nkhxbwd3wu4

Audio-Visual Interpretable and Controllable Video Captioning

Yapeng Tian, Chenxiao Guan, Justin Goodman, Marc Moore, Chenliang Xu
2019 Computer Vision and Pattern Recognition  
, audiorelated, or both audio-and visual-related words for sentence generation and discover corresponding events from audio or visual modalities.  ...  The second challenge lies on the computational framework. Recurrent neural networks (RNNs) are widely used as decoders for video captioning.  ... 
dblp:conf/cvpr/TianGGMX19 fatcat:pvfazxjwa5cexcno7xdwt54vme

Spelling Correction as a Foreign Language [article]

Yingbo Zhou, Utkarsh Porwal, Roberto Konow
2019 arXiv   pre-print
In this paper, we reformulated the spell correction problem as a machine translation task under the encoder-decoder framework.  ...  This reformulation enabled us to use a single model for solving the problem that is traditionally formulated as learning a language model and an error model.  ...  Our heuristic for finding potential spelling related queries is based on consecutive user actions in one search session.  ... 
arXiv:1705.07371v2 fatcat:4is2exy6jzai7h4xghv4bytvgq
« Previous Showing results 1 — 15 out of 32,639 results