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
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
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
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
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
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
Publikováno v:
Degraded Environments: Sensing, Processing, and Display 2018.
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
Autor:
Carlos Sanchez Amaro, Anton Leuski, Cory J. Hayes, Clare R. Voss, Pooja Moolchandani, Felix Gervits, David Traum, Stephanie M. Lukin, John G. Rogers, Matthew Marge
Publikováno v:
ACL (4)
ScoutBot is a dialogue interface to physical and simulated robots that supports collaborative exploration of environments. The demonstration will allow users to issue unconstrained spoken language commands to ScoutBot. ScoutBot will prompt for clarif