Zobrazeno 1 - 10
of 16
pro vyhledávání: '"Semih Yavuz"'
Publikováno v:
Proceedings of the 2nd Workshop on Evaluation and Comparison of NLP Systems.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::fd0bd0896385a74aa86ab240f656fbe6
https://doi.org/10.18653/v1/2021.eval4nlp-1.8
https://doi.org/10.18653/v1/2021.eval4nlp-1.8
Publikováno v:
ACL (student)
Graph-to-text generation has benefited from pre-trained language models (PLMs) in achieving better performance than structured graph encoders. However, they fail to fully utilize the structure information of the input graph. In this paper, we aim to
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8a323b794a2d4eac936e388b0f24e025
https://doi.org/10.18653/v1/2021.acl-srw.2
https://doi.org/10.18653/v1/2021.acl-srw.2
Dense neural text retrieval has achieved promising results on open-domain Question Answering (QA), where latent representations of questions and passages are exploited for maximum inner product search in the retrieval process. However, current dense
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::fb4e0a1bbdfe8b32bc3109abc0c0d8ce
Autor:
Nitish Shirish Keskar, Caiming Xiong, Wenhao Liu, Kazuma Hashimoto, Richard Socher, Semih Yavuz
Publikováno v:
EMNLP (1)
The concept of Dialogue Act (DA) is universal across different task-oriented dialogue domains - the act of ``request" carries the same speaker intention whether it is for restaurant reservation or flight booking. However, DA taggers trained on one do
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0fb6fadaa352e899be88de050dd7b95f
https://doi.org/10.18653/v1/2020.emnlp-main.412
https://doi.org/10.18653/v1/2020.emnlp-main.412
Publikováno v:
ICDM
In this work we study the hierarchical organization of technical documents, where given a set of documents and a hierarchy of categories, the goal is to assign documents to their corresponding categories. Unlike prior work on supervised hierarchical
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7846e99df938951b72091fb5019626dd
https://doi.org/10.1109/icdm.2019.00048
https://doi.org/10.1109/icdm.2019.00048
Publikováno v:
ViGIL@NeurIPS
Understanding and conversing about dynamic scenes is one of the key capabilities of AI agents that navigate the environment and convey useful information to humans. Video question answering is a specific scenario of such AI-human interaction where an
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::78838aea2c593401c07521b810c1f13f
http://arxiv.org/abs/1907.13280
http://arxiv.org/abs/1907.13280
Autor:
Chung-Cheng Chiu, Colin Raffel, Naveen Arivazhagan, Ruoming Pang, Colin Cherry, Wei Li, Semih Yavuz, Wolfgang Macherey
Publikováno v:
ACL (1)
Simultaneous machine translation begins to translate each source sentence before the source speaker is finished speaking, with applications to live and streaming scenarios. Simultaneous systems must carefully schedule their reading of the source sent
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a327f333a7c39fddce90ade95b3c7e51
http://arxiv.org/abs/1906.05218
http://arxiv.org/abs/1906.05218
Autor:
Daniel Duckworth, Semih Yavuz, Chinnadhurai Sankar, Ben Goodrich, Andy Cedilnik, Bill Byrne, Arvind Neelakantan, Kyu-Young Kim, Amit Dubey, Karthik Krishnamoorthi
Publikováno v:
EMNLP/IJCNLP (1)
A significant barrier to progress in data-driven approaches to building dialog systems is the lack of high quality, goal-oriented conversational data. To help satisfy this elementary requirement, we introduce the initial release of the Taskmaster-1 d
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a7c333bc774a89080a7537fc37193813
https://doi.org/10.18653/v1/d19-1459
https://doi.org/10.18653/v1/d19-1459
Publikováno v:
EMNLP
Maximum-likelihood estimation (MLE) is one of the most widely used approaches for training structured prediction models for text-generation based natural language processing applications. However, besides exposure bias, models trained with MLE suffer
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::fa1e53f6966e143ffe03cee196c57843
https://doi.org/10.18653/v1/d18-1406
https://doi.org/10.18653/v1/d18-1406
Publikováno v:
ACL (1)
The recent advance in deep learning and semantic parsing has significantly improved the translation accuracy of natural language questions to structured queries. However, further improvement of the existing approaches turns out to be quite challengin
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::afb17fe047973d2aae218af834b8ff56
https://doi.org/10.18653/v1/p18-1124
https://doi.org/10.18653/v1/p18-1124