Zobrazeno 1 - 10 of 26 pro vyhledávání: '"David VanDyke"'
5
Non-Autoregressive Text Generation with Pre-trained Language Models
Autor: David Vandyke, Deng Cai, Yixuan Su, Simon Baker, Yan Wang, Piji Li, Nigel Collier
Publikováno v: EACL
Non-autoregressive generation (NAG) has recently attracted great attention due to its fast inference speed. However, the generation quality of existing NAG models still lags behind their autoregressive counterparts. In this work, we show that BERT ca
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::be8fc9dff6b1f5a599febde0b43b4be2
Zobrazit plný text záznamu
6
A Generative Model for Joint Natural Language Understanding and Generation
Autor: Bo-Hsiang Tseng, David Vandyke, Yimai Fang, Jianpeng Cheng
Publikováno v: ACL
Natural language understanding (NLU) and natural language generation (NLG) are two fundamental and related tasks in building task-oriented dialogue systems with opposite objectives: NLU tackles the transformation from natural language to formal repre
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0218cf1a0e68759618014848b1d1f50c
http://arxiv.org/abs/2006.07499
Zobrazit plný text záznamu
7
Elektronická kniha
The Capitol Riots : Digital Media, Disinformation, and Democracy Under Attack
Autor: Sandra Jeppesen, Michael Hoechsmann, iowyth hezel ulthiin, David VanDyke, Miranda McKee
The Capitol Riots maps out the events of the January 6, 2021 insurrectionary riots at the United States Capitol building, providing context for understanding the contributing factors and ongoing implications of the uprising.This definitive text explo
Zobrazit plný text záznamu
9
A Network-based End-to-End Trainable Task-oriented Dialogue System
Autor: Lina Maria Rojas-Barahona, Stefan Ultes, Tsung-Hsien Wen, David Vandyke, Milica Gasic, Nikola Mrkšić, Steve Young, Pei-Hao Su
Publikováno v: EACL (1)
Teaching machines to accomplish tasks by conversing naturally with humans is challenging. Currently, developing task-oriented dialogue systems requires creating multiple components and typically this involves either a large amount of handcrafting, or
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6ee83b4357ad4fe79aff7404a40700be
https://doi.org/10.18653/v1/e17-1042
Zobrazit plný text záznamu
10
Counter-fitting Word Vectors to Linguistic Constraints
Autor: Blaise Thomson, Tsung-Hsien Wen, Milica Gasic, Nikola Mrkšić, Steve Young, Pei-Hao Su, Lina Maria Rojas-Barahona, Diarmuid Ó Séaghdha, David Vandyke
Publikováno v: HLT-NAACL
In this work, we present a novel counter-fitting method which injects antonymy and synonymy constraints into vector space representations in order to improve the vectors' capability for judging semantic similarity. Applying this method to publicly av
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d1316f93a3dff88f1c1af763f965f7f3
http://arxiv.org/abs/1603.00892
Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání

Omezení vyhledávání
Plný text Recenzováno Digitální knihovna AV ČR
Zdroje