Výsledky vyhledávání

Value-Agnostic Conversational Semantic Parsing

Autor: Sam Thomson, Emmanouil Antonios Platanios, Alexander Kyte, Adam Pauls, Subhro Roy, Dan Klein, Yuchen Zhang, Jason Wolfe, Jacob Andreas, Jayant Krishnamurthy, Alan Guo

Publikováno v: ACL/IJCNLP (1)

Conversational semantic parsers map user utterances to executable programs given dialogue histories composed of previous utterances, programs, and system responses. Existing parsers typically condition on rich representations of history that include

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::c8d0a67b1b90869c4f2fe03d28ecfee7
https://doi.org/10.18653/v1/2021.acl-long.284

Zobrazit plný text záznamu

Compositional Generalization for Neural Semantic Parsing via Span-level Supervised Attention

Autor: Graham Neubig, Hao Fang, Adam Pauls, Sam Thomson, Yu Su, Emmanouil Antonios Platanios, Pengcheng Yin, Jacob Andreas

Publikováno v: NAACL-HLT

We describe a span-level supervised attention loss that improves compositional generalization in semantic parsers. Our approach builds on existing losses that encourage attention maps in neural sequence-to-sequence models to imitate the output of cla

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::39a0c9bd0f5f70a129ac248dd493b485
https://doi.org/10.18653/v1/2021.naacl-main.225

Zobrazit plný text záznamu

MULTI-DOCUMENT SUMMARIZATION OF EVALUATIVE TEXT

Autor: Giuseppe Carenini, Jackie Chi Kit Cheung, Adam Pauls

Publikováno v: Computational Intelligence. 29:545-576

In many decision-making scenarios, people can benefit from knowing what other people's opinions are. As more and more evaluative documents are posted on the Web, summarizing these useful resources becomes a critical task for many organizations and in

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::f069ffc50ef05d0cfa2ff25432d25dbf
https://doi.org/10.1111/j.1467-8640.2012.00417.x

Zobrazit plný text záznamu

Decoherence time scales for 'meteoroid streams'

Autor: Adam Pauls, Brett Gladman

Publikováno v: Meteoritics & Planetary Science. 40:1241-1256

We explore the orbital dynamics of Earth-crossing objects with the intent to understand the time scales under which an "orbital stream" of material could produce time-correlated meteorite falls. These meteoroid streams have been suggested to be assoc

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::61998e389b2e6fcb95d9644b286cde53
https://doi.org/10.1111/j.1945-5100.2005.tb00186.x

Zobrazit plný text záznamu

Efficient parsing for transducer grammars

Autor: John DeNero, Adam Pauls, Mohit Bansal, Dan Klein

Publikováno v: HLT-NAACL

The tree-transducer grammars that arise in current syntactic machine translation systems are large, flat, and highly lexicalized. We address the problem of parsing efficiently with such grammars in three ways. First, we present a pair of grammar tran

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::2e35f0c548685bb0fd761da5c0d29ba3
https://doi.org/10.3115/1620754.1620788

Zobrazit plný text záznamu

Hierarchical search for parsing

Autor: Adam Pauls, Dan Klein

Publikováno v: HLT-NAACL

Both coarse-to-fine and A* parsing use simple grammars to guide search in complex ones. We compare the two approaches in a common, agenda-based framework, demonstrating the tradeoffs and relative strengths of each method. Overall, coarse-to-fine is m

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::80f5e9b12b479196a0191cf51374aa53
https://doi.org/10.3115/1620754.1620835

Zobrazit plný text záznamu

k-best A* parsing

Autor: Adam Pauls, Dan Klein

Publikováno v: ACL/IJCNLP

A* parsing makes 1-best search efficient by suppressing unlikely 1-best items. Existing k-best extraction methods can efficiently search for top derivations, but only after an exhaustive 1-best pass. We present a unified algorithm for k-best A* parsi

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::6292210e2af0ae71c256ee9a3c2f772d
https://doi.org/10.3115/1690219.1690281

Zobrazit plný text záznamu

Consensus training for consensus decoding in machine translation

Autor: John DeNero, Dan Klein, Adam Pauls

Publikováno v: EMNLP

We propose a novel objective function for discriminatively tuning log-linear machine translation models. Our objective explicitly optimizes the BLEU score of expected n-gram counts, the same quantities that arise in forest-based consensus and minimum

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::4d8acf10a3bc6f6d349f92b9547bb250
https://doi.org/10.3115/1699648.1699688

Zobrazit plný text záznamu

Asynchronous binarization for synchronous grammars

Autor: Adam Pauls, Dan Klein, John DeNero

Publikováno v: ACL/IJCNLP (Short Papers)

Binarization of n-ary rules is critical for the efficiency of syntactic machine translation decoding. Because the target side of a rule will generally reorder the source side, it is complex (and sometimes impossible) to find synchronous rule binariza

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::e405bfa540470b2f09a74d5a902f1939
https://doi.org/10.3115/1667583.1667627

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání