Zobrazeno 1 - 10
of 88
pro vyhledávání: '"Ralph Weischedel"'
Autor:
Ralph Weischedel, Elizabeth Boschee
Publikováno v:
Computational Linguistics, Vol 44, Iss 4, Pp 651-658 (2018)
Though information extraction (IE) research has more than a 25-year history, F1 scores remain low. Thus, one could question continued investment in IE research. In this article, we present three applications where information extraction of entities,
Externí odkaz:
https://doaj.org/article/4c92d412ebc841ce8cd0641d32823268
Publikováno v:
AAAI
User engagement is a critical metric for evaluating the quality of open-domain dialogue systems. Prior work has focused on conversation-level engagement by using heuristically constructed features such as the number of turns and the total time of the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::27c161315328d48db69651c8955a51d9
https://doi.org/10.1609/aaai.v34i05.6283
https://doi.org/10.1609/aaai.v34i05.6283
Our goal is to deliver a new task and leaderboard to stimulate research on question answering and pre-trained language models (PTLMs) to understand a significant instructional document, e.g., an introductory college textbook or a manual. PTLMs have s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::20e49e554395cb9ac3049d0d1bed9e55
http://arxiv.org/abs/2110.01552
http://arxiv.org/abs/2110.01552
Publikováno v:
NAACL-HLT
With the recent advances of open-domain story generation, the lack of reliable automatic evaluation metrics becomes an increasingly imperative issue that hinders the fast development of story generation. According to conducted researches in this rega
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a3a0b44c4e7088c13ad8d384b3480770
http://arxiv.org/abs/2104.05801
http://arxiv.org/abs/2104.05801
Publikováno v:
EMNLP (Findings)
We consider problems of making sequences of decisions to accomplish tasks, interacting via the medium of language. These problems are often tackled with reinforcement learning approaches. We find that these models do not generalize well when applied
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::970db81d1f2b06f522d38b791b4b9dbf
https://doi.org/10.18653/v1/2020.findings-emnlp.273
https://doi.org/10.18653/v1/2020.findings-emnlp.273
Autor:
Emile Servan-Schreiber, Colin L. Widmer, Ralph Weischedel, Othalia Larue, Ion Juvina, Srikanth Nadella, Maurice Balick, Brandon S. Minnery, Subhashini Ganapathy, Lance Ramshaw
Publikováno v:
Human–Computer Interaction Series ISBN: 9783030388249
Geopolitical forecasting is the process of generating judgments of probability for a wide variety of future geopolitical events, such as political elections, international conflict, disease outbreaks, and macro-economic indicators. Governmental polic
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::40529b436bd0d844a78f4efa6966074b
https://doi.org/10.1007/978-3-030-38825-6_12
https://doi.org/10.1007/978-3-030-38825-6_12
Publikováno v:
EMNLP (1)
Long-form narrative text generated from large language models manages a fluent impersonation of human writing, but only at the local sentence level, and lacks structure or global cohesion. We posit that many of the problems of story generation can be
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b1bcbb9335c96114ad699e178882a822
Publikováno v:
Machine Translation. 32:31-43
We describe a multifaceted approach to named entity recognition that can be deployed with minimal data resources and a handful of hours of non-expert annotation. We describe how this approach was applied in the 2016 LoReHLT evaluation and demonstrate
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::957f2b3ccae9553520e0f825c07a12d5
https://doi.org/10.1007/s10590-017-9208-0
https://doi.org/10.1007/s10590-017-9208-0
Publikováno v:
CoNLL
We propose a novel deep structured learning framework for event temporal relation extraction. The model consists of 1) a recurrent neural network (RNN) to learn scoring functions for pair-wise relations, and 2) a structured support vector machine (SS
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::db7ddbc39554d4f2628416bed2c8a466
http://arxiv.org/abs/1909.10094
http://arxiv.org/abs/1909.10094
Autor:
Emily Budlong, Carrie Pine, Mark Zappavigna, James Homer, Charles Proefrock, John Gucwa, Michael Crystal, Ralph Weischedel
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence. 27:1493-1500
This paper describes the Advanced Text Exploitation Assistant (ATEA), a system developed to enable intelligence analysts to perform link analysis and visualization (A&V) from information in large volumes of unstructured text. One of the key design ch
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::367a99bc7f431f666c45a71976ad4624
https://doi.org/10.1609/aaai.v27i2.18988
https://doi.org/10.1609/aaai.v27i2.18988