Filters








8,168 Hits in 5.1 sec

Linking artificial and human neural representations of language

Jon Gauthier, Roger Levy
2019 Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)  
Our results constrain the space of NLU models that could best account for human neural representations of language, but also suggest limits on the possibility of decoding fine-grained syntactic information  ...  Through further task ablations and representational analyses, we find that tasks which produce syntax-light representations yield significant improvements in brain decoding performance.  ...  Mitchell et al. (2008) first demonstrated that distributional word representations could be used to predict human brain activations, when subjects were presented with individual words in isolation.  ... 
doi:10.18653/v1/d19-1050 dblp:conf/emnlp/GauthierL19 fatcat:gaaqsgzx3fdb5cgi353625x2py

Linking artificial and human neural representations of language [article]

Jon Gauthier, Roger Levy
2019 arXiv   pre-print
Our results constrain the space of NLU models that could best account for human neural representations of language, but also suggest limits on the possibility of decoding fine-grained syntactic information  ...  Through further task ablations and representational analyses, we find that tasks which produce syntax-light representations yield significant improvements in brain decoding performance.  ...  Mitchell et al. (2008) first demonstrated that distributional word representations could be used to predict human brain activations, when subjects were presented with individual words in isolation.  ... 
arXiv:1910.01244v1 fatcat:6kxuvlw65zachbnccv7ywme2au

Fine-Grained Attention Mechanism for Neural Machine Translation [article]

Heeyoul Choi, Kyunghyun Cho, Yoshua Bengio
2018 arXiv   pre-print
In experiments with the task of En-De and En-Fi translation, the fine-grained attention method improves the translation quality in terms of BLEU score.  ...  Neural machine translation (NMT) has been a new paradigm in machine translation, and the attention mechanism has become the dominant approach with the state-of-the-art records in many language pairs.  ...  With alignment analysis, the fine-grained attention method revealed that the different dimensions of context play different roles in neural machine translation.  ... 
arXiv:1803.11407v2 fatcat:7pksn55hrzc75mshb4r2m2ruiq

What Makes Different People's Representations Alike: Neural Similarity Space Solves the Problem of Across-subject fMRI Decoding

Rajeev D. S. Raizada, Andrew C. Connolly
2012 Journal of Cognitive Neuroscience  
However, the goal of being able to decode across subjects is still challenging: It has remained unclear what population-level regularities of neural representation there might be.  ...  The key to finding this solution was questioning the seemingly obvious idea that neural decoding should work directly on neural activation patterns.  ...  Across-subject decoding of fine-grained neural representations has therefore remained a challenge.  ... 
doi:10.1162/jocn_a_00189 pmid:22220728 fatcat:43an7wpfxnfd3o647nlvhzu3ha

Innovative Deep Neural Network Modeling for Fine-grained Chinese Entity Recognition

Jingang Liu, Chunhe Xia, Haihua Yan, Wenjing Xu
2020 Electronics  
feature extraction and information representation of deep neural models.  ...  In this paper, we propose an innovative neural network model named En2BiLSTM-CRF to improve the effect of fine-grained Chinese entity recognition tasks.  ...  These enhanced representations and weights play an essential role in the process of fine-grained entity recognition; (3) We conducted sufficient experiments on the latest fine-grained public dataset and  ... 
doi:10.3390/electronics9061001 fatcat:lzbl2gx3mzg3pgiwi4epukref4

Exploring the Representations of Individual Entities in the Brain Combining EEG and Distributional Semantics

Andrea Bruera, Massimo Poesio
2022 Frontiers in Artificial Intelligence  
In the second set of analyses, we learn to decode from evoked responses to distributional word vectors.  ...  ., the referents of proper names such as Jacinta Ardern) is fine-grained, episodic, and strongly social in nature, when compared with knowledge about generic entities (the referents of common nouns such  ...  been shown to perform well with neural data (Jat et al., 2019) .  ... 
doi:10.3389/frai.2022.796793 pmid:35280237 pmcid:PMC8905499 doaj:cc9b484391c74bde98bb833975f0f872 fatcat:zxavy6w5qrarriglf4y2qp2wi4

Fine-Grained and Semantic-Guided Visual Attention for Image Captioning

Zongjian Zhang, Qiang Wu, Yang Wang, Fang Chen
2018 2018 IEEE Winter Conference on Applications of Computer Vision (WACV)  
In this way, a mechanism of fine-grained and semantic-guided visual attention is created, which can better link the relevant visual information with each semantic meaning inside the text through LSTM.  ...  Based on the end-to-end CNN-LSTM framework, it tries to link the relevant visual information on the image with the semantic representation in the text (i.e. captioning) for the first time.  ...  To the best of our knowledge, our FCN-LSTM model is the first work to propose a novel attention mechanism that combines the grid-wise visual representation with gridwise semantic label at a fine-grained  ... 
doi:10.1109/wacv.2018.00190 dblp:conf/wacv/ZhangWWC18 fatcat:m2ofhqjsgbb6ddsof2mkbdd5ki

Improving End-to-End Contextual Speech Recognition with Fine-Grained Contextual Knowledge Selection [article]

Minglun Han, Linhao Dong, Zhenlin Liang, Meng Cai, Shiyu Zhou, Zejun Ma, Bo Xu
2022 arXiv   pre-print
In this work, we focus on mitigating confusion problems with fine-grained contextual knowledge selection (FineCoS).  ...  In FineCoS, we introduce fine-grained knowledge to reduce the uncertainty of token predictions.  ...  and meanwhile fully use fine-grained knowledge.  ... 
arXiv:2201.12806v2 fatcat:upitfw6jsnd4lbgb4bvp6dvpd4

Hierarchical Multi-Grained Generative Model for Expressive Speech Synthesis [article]

Yukiya Hono, Kazuna Tsuboi, Kei Sawada, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, Keiichi Tokuda
2021 arXiv   pre-print
This paper proposes a hierarchical generative model with a multi-grained latent variable to synthesize expressive speech.  ...  In recent years, fine-grained latent variables are introduced into the text-to-speech synthesis that enable the fine control of the prosody and speaking styles of synthesized speech.  ...  These representations have a hierarchical linguistic dependency and correlate with the content of the text. These fine-grained representations also have temporal coherency.  ... 
arXiv:2009.08474v2 fatcat:cvdnfbhvwvb2tlp5nmzjpgxd4y

Hierarchical Multi-Grained Generative Model for Expressive Speech Synthesis

Yukiya Hono, Kazuna Tsuboi, Kei Sawada, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, Keiichi Tokuda
2020 Interspeech 2020  
This paper proposes a hierarchical generative model with a multi-grained latent variable to synthesize expressive speech.  ...  In recent years, fine-grained latent variables are introduced into the text-to-speech synthesis that enable the fine control of the prosody and speaking styles of synthesized speech.  ...  These representations have a hierarchical linguistic dependency and correlate with the content of the text. These fine-grained representations also have temporal coherency.  ... 
doi:10.21437/interspeech.2020-2477 dblp:conf/interspeech/HonoTSHONT20 fatcat:gwmaqc6fmrfg7krx2azwwr4qiq

Focus-Constrained Attention Mechanism for CVAE-based Response Generation [article]

Zhi Cui, Yanran Li, Jiayi Zhang, Jianwei Cui, Chen Wei, Bin Wang
2020 arXiv   pre-print
To tackle it, our idea is to transform the coarse-grained discourse-level information into fine-grained word-level information.  ...  Specifically, we firstly measure the semantic concentration of corresponding target response on the post words by introducing a fine-grained focus signal.  ...  This focus captures to what extent the response semantics is related to the post words, which will serve as fine-grained signals for the decoder.  ... 
arXiv:2009.12102v1 fatcat:ekdbsoju25g6zewgrldshhtyla

Layer-Wise Multi-View Decoding for Improved Natural Language Generation [article]

Fenglin Liu, Xuancheng Ren, Guangxiang Zhao, Chenyu You, Xian Wu, Xu Sun
2022 arXiv   pre-print
In this work, we propose layer-wise multi-view decoding, where for each decoder layer, together with the representations from the last encoder layer, which serve as a global view, those from other encoder  ...  ., natural language generation, the decoder relies on the attention mechanism to efficiently extract information from the encoder.  ...  Following See et al. (2017) , we truncate each source sentence to 400 words and each target sentence to 100 words. ROUGE-1, -2 and  ... 
arXiv:2005.08081v6 fatcat:ozcvveewvva2dgiyul6riu2fru

A Survey on Deep Learning for Named Entity Recognition [article]

Jing Li, Aixin Sun, Jianglei Han, Chenliang Li
2020 arXiv   pre-print
Then, we systematically categorize existing works based on a taxonomy along three axes: distributed representations for input, context encoder, and tag decoder.  ...  Finally, we present readers with the challenges faced by NER systems and outline future directions in this area.  ...  Fine-grained NER and Boundary Detection.  ... 
arXiv:1812.09449v3 fatcat:36tnstbyo5h4xizjpqn4cevgui

CopyCat2: A Single Model for Multi-Speaker TTS and Many-to-Many Fine-Grained Prosody Transfer [article]

Sri Karlapati, Penny Karanasou, Mateusz Lajszczak, Ammar Abbas, Alexis Moinet, Peter Makarov, Ray Li, Arent van Korlaar, Simon Slangen, Thomas Drugman
2022 arXiv   pre-print
In Stage I, the model learns speaker-independent word-level prosody representations from speech which it uses for many-to-many fine-grained prosody transfer.  ...  We compare CC2 to two strong baselines, one in TTS with contextually appropriate prosody, and one in fine-grained prosody transfer.  ...  We hypothesise that training on a multi-speaker dataset at the word-level, helped get denser and fine-grained, acoustic and duration prosody representations.  ... 
arXiv:2206.13443v1 fatcat:t47abhn3ifbsvkwlhbsmwrdipu

Lessons From Deep Neural Networks for Studying the Coding Principles of Biological Neural Networks

Hyojin Bae, Sang Jeong Kim, Chang-Eop Kim
2021 Frontiers in Systems Neuroscience  
/irrelevant features or overestimating the network feature representation/noise correlation.  ...  Additionally, we present studies investigating neural coding principles in biological neural networks to which our points can be applied.  ...  model) and the actual situation (fine-grained representation model).  ... 
doi:10.3389/fnsys.2020.615129 pmid:33519390 pmcid:PMC7843526 fatcat:4rvgny3irnhuxn6qha3t66e5h4
« Previous Showing results 1 — 15 out of 8,168 results