Zobrazeno 1 - 10
of 18
pro vyhledávání: '"Shrimai Prabhumoye"'
Publikováno v:
NAACL-HLT
Document grounded generation is the task of using the information provided in a document to improve text generation. This work focuses on two different document grounded generation tasks: Wikipedia Update Generation task and Dialogue response generat
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::fe16688110b3290eda825a9006fd1820
http://arxiv.org/abs/2104.12714
http://arxiv.org/abs/2104.12714
Publikováno v:
NAACL-HLT
Recent work in natural language processing (NLP) has focused on ethical challenges such as understanding and mitigating bias in data and algorithms; identifying objectionable content like hate speech, stereotypes and offensive language; and building
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0826b8906574cd1e660932d60a7e3f27
https://doi.org/10.18653/v1/2021.naacl-main.297
https://doi.org/10.18653/v1/2021.naacl-main.297
Autor:
Dirk Hovy, Shrimai Prabhumoye
Publikováno v:
Language and linguistics compass. 15(8)
Recently, there has been an increased interest in demographically grounded bias in natural language processing (NLP) applications. Much of the recent work has focused on describing bias and providing an overview of bias in a larger context. Here, we
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2548adb55cd872a0b0776cd186e01c3d
https://pubmed.ncbi.nlm.nih.gov/35864931
https://pubmed.ncbi.nlm.nih.gov/35864931
Publikováno v:
COLING
Neural controllable text generation is an important area gaining attention due to its plethora of applications. Although there is a large body of prior work in controllable text generation, there is no unifying theme. In this work, we provide a new s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e063aa3d74aa9b442312a89a6d926ac7
http://arxiv.org/abs/2005.01822
http://arxiv.org/abs/2005.01822
Autor:
Alan W. Black, Aman Madaan, Yiming Yang, Shrimai Prabhumoye, Amrith Setlur, Graham Neubig, Barnabás Póczos, Tanmay Parekh, Ruslan Salakhutdinov
Publikováno v:
ACL
This paper introduces a new task of politeness transfer which involves converting non-polite sentences to polite sentences while preserving the meaning. We also provide a dataset of more than 1.39 instances automatically labeled for politeness to enc
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1b5ba622785ea4278b45388698217c40
https://doi.org/10.18653/v1/2020.acl-main.169
https://doi.org/10.18653/v1/2020.acl-main.169
Publikováno v:
ACL
Sentence ordering is the task of arranging the sentences of a given text in the correct order. Recent work using deep neural networks for this task has framed it as a sequence prediction problem. In this paper, we propose a new framing of this task a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::638b5481945b34641e8631fc205cd427
https://doi.org/10.18653/v1/2020.acl-main.248
https://doi.org/10.18653/v1/2020.acl-main.248
Autor:
Shrimai Prabhumoye, Ryan Lowe, Kurt Shuster, Joelle Pineau, Alexander H. Miller, Emily Dinan, Douwe Kiela, Jack Urbanek, Iulian Vlad Serban, Valentin Malykh, Arthur Szlam, Alexander I. Rudnicky, Varvara Logacheva, Mikhail S. Burtsev, Jason D. Williams, Jason Weston, Alan W. Black
Publikováno v:
The NeurIPS '18 Competition ISBN: 9783030291341
We describe the setting and results of the ConvAI2 NeurIPS competition that aims to further the state-of-the-art in open-domain chatbots. Some key takeaways from the competition are: (1) pretrained Transformer variants are currently the best performi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::baea3ac4d285aa0d6565323f702a3437
https://doi.org/10.1007/978-3-030-29135-8_7
https://doi.org/10.1007/978-3-030-29135-8_7
Autor:
Jack Urbanek, Emma Qian, Siddharth Karamcheti, Emily Dinan, Tim Rocktäschel, Jason Weston, Shrimai Prabhumoye, Pratik Ringshia, Angela Fan, Arthur Szlam, Douwe Kiela
Publikováno v:
AAAI
Procedurally generating cohesive and interesting game environments is challenging and time-consuming. In order for the relationships between the game elements to be natural, common-sense has to be encoded into arrangement of the elements. In this wor
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ec86bb34d45834d86ab41b74ae0e8d63
http://arxiv.org/abs/1911.09194
http://arxiv.org/abs/1911.09194
Visual storytelling is the task of generating stories based on a sequence of images. Inspired by the recent works in neural generation focusing on controlling the form of text, this paper explores the idea of generating these stories in different per
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c4e9c8f631a8232ed3ec77d18c5d1f65
http://arxiv.org/abs/1906.06401
http://arxiv.org/abs/1906.06401
Publikováno v:
NAACL-HLT (1)
Recent work in neural generation has attracted significant interest in controlling the form of text, such as style, persona, and politeness. However, there has been less work on controlling neural text generation for content. This paper introduces th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::42bb9f22495ddda7fb51568b8349218e
http://arxiv.org/abs/1905.05293
http://arxiv.org/abs/1905.05293