Zobrazeno 1 - 10
of 40
pro vyhledávání: '"Clare R. Voss"'
Autor:
Daniel Napierski, Manling Li, Spencer Whitehead, Heng Ji, Clare R. Voss, Ying Lin, Marjorie Freedman, Brian Chen, Xiaoman Pan, Bo Wu, Alireza Zareian, Shih-Fu Chang
Publikováno v:
ACL (demo)
We present the first comprehensive, open source multimedia knowledge extraction system that takes a massive stream of unstructured, heterogeneous multimedia data from various sources and languages as input, and creates a coherent, structured knowledg
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7e49cdb9129866884b81e456784295af
https://doi.org/10.18653/v1/2020.acl-demos.11
https://doi.org/10.18653/v1/2020.acl-demos.11
Publikováno v:
WANLP@ACL 2019
In this paper, we tackle the problem of “root extraction” from words in the Semitic language family. A challenge in applying natural language processing techniques to these languages is the data sparsity problem that arises from their rich intern
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6face0bf5f4c30996e9d9ef1db4da2a6
https://doi.org/10.18653/v1/w19-4610
https://doi.org/10.18653/v1/w19-4610
Autor:
Clare R. Voss, Matthew Marge, Stephanie M. Lukin, Cory J. Hayes, Jesse Bloecker, Eric Holder, Stephen M. Nogar
Publikováno v:
NAACL-HLT (Demonstrations)
This paper presents a research platform that supports spoken dialogue interaction with multiple robots. The demonstration showcases our crafted MultiBot testing scenario in which users can verbally issue search, navigate, and follow instructions to t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::12e84622c625dd49f19f5554ac220a64
https://doi.org/10.18653/v1/n19-4023
https://doi.org/10.18653/v1/n19-4023
Publikováno v:
EMNLP/IJCNLP (1)
The identification of complex semantic structures such as events and entity relations, already a challenging Information Extraction task, is doubly difficult from sources written in under-resourced and under-annotated languages. We investigate the su
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::156c0229407f23b5444f51174f61f068
https://doi.org/10.18653/v1/d19-1030
https://doi.org/10.18653/v1/d19-1030
Autor:
Ying Lin, Manling Li, Spencer Whitehead, Joe Hoover, Morteza Dehghani, Clare R. Voss, Heng Ji
Publikováno v:
NAACL-HLT (Demonstrations)
This paper demonstrates a state-of-the-art end-to-end multilingual (English, Russian, and Ukrainian) knowledge extraction system that can perform entity discovery and linking, relation extraction, event extraction, and coreference. It extracts and ag
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e471398f56b13af213ab292544a0aec5
https://doi.org/10.18653/v1/n19-4019
https://doi.org/10.18653/v1/n19-4019
Autor:
Stephen Tratz, David Traum, Lucia Donatelli, Ron Artstein, Clare R. Voss, Stephanie M. Lukin, Claire Bonial
Publikováno v:
Proceedings of the First International Workshop on Designing Meaning Representations.
We detail refinements made to Abstract Meaning Representation (AMR) that make the representation more suitable for supporting a situated dialogue system, where a human remotely controls a robot for purposes of search and rescue and reconnaissance. We
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9e214612f198c6abcf843bc0ae1e826e
https://doi.org/10.18653/v1/w19-3322
https://doi.org/10.18653/v1/w19-3322
Publikováno v:
Degraded Environments: Sensing, Processing, and Display 2018.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f6661c1f11d7e79739d1eecae801dbf0
https://doi.org/10.1117/12.2309414
https://doi.org/10.1117/12.2309414
Publikováno v:
Proceedings of the First Workshop on Storytelling.
Computational visual storytelling produces a textual description of events and interpretations depicted in a sequence of images. These texts are made possible by advances and cross-disciplinary approaches in natural language processing, generation, a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::10f94af1144446856b76f125ea22bc00
https://doi.org/10.18653/v1/w18-1503
https://doi.org/10.18653/v1/w18-1503
Autor:
Clare R. Voss, Claire Bonial, Ron Artstein, Cassidy Henry, Kimberly A. Pollard, Stephanie M. Lukin, David Traum, Matthew Marge
Publikováno v:
SIGDIAL Conference
This paper identifies stylistic differences in instruction-giving observed in a corpus of human-robot dialogue. Differences in verbosity and structure (i.e., single-intent vs. multi-intent instructions) arose naturally without restrictions or prior g
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::24b05d41c7ccd0117fed89443b832e2f
Publikováno v:
EMNLP
Most previous efforts toward video captioning focus on generating generic descriptions, such as, “A man is talking.” We collect a news video dataset to generate enriched descriptions that include important background knowledge, such as named enti
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::752f05c1336852c9593facdf278b4de9
https://doi.org/10.18653/v1/d18-1433
https://doi.org/10.18653/v1/d18-1433