Zobrazeno 1 - 10
of 38
pro vyhledávání: '"Julia Hockenmaier"'
Publikováno v:
ACL/IJCNLP (Findings)
Text-to-Graph extraction aims to automatically extract information graphs consisting of mentions and types from natural language texts. Existing approaches, such as table filling and pairwise scoring, have shown impressive performance on various info
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e57f631862f55401c2dfbded9460df16
Publikováno v:
ACL
The ability to match pieces of code to their corresponding natural language descriptions and vice versa is fundamental for natural language search interfaces to software repositories. In this paper, we propose a novel multi-perspective cross-lingual
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::fb8abd3eac567b8dc453660297a4808a
Publikováno v:
ACL
The Minecraft Collaborative Building Task is a two-player game in which an Architect (A) instructs a Builder (B) to construct a target structure in a simulated Blocks World Environment. We define the subtask of predicting correct action sequences (bl
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8864e9c89b49c0ecf4c7130aedc1cbd1
https://doi.org/10.18653/v1/2020.acl-main.232
https://doi.org/10.18653/v1/2020.acl-main.232
Autor:
Charlotte Yoder, Julia Hockenmaier, Sahand Mozaffari, Aidana Karipbayeva, Bryan Lunt, Marc Canby
Publikováno v:
SIGMORPHON
The objective of this shared task is to produce an inflected form of a word, given its lemma and a set of tags describing the attributes of the desired form. In this paper, we describe a transformer-based model that uses a bidirectional decoder to pe
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::31976510af69bf67193df29338807d1b
https://doi.org/10.18653/v1/2020.sigmorphon-1.15
https://doi.org/10.18653/v1/2020.sigmorphon-1.15
Publikováno v:
Automation in Construction. 134:104036
In construction, schedule mistakes causing delays beyond substantial completion dates cost contractors expensive liquidated damages. Hence, several industry guidelines, such as the DCMA's 14 point assessment, define schedule quality and offer systema
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ddae751be032ee5385dc03fdd0ba3b35
https://doi.org/10.1016/j.autcon.2021.104036
https://doi.org/10.1016/j.autcon.2021.104036
Autor:
Jiacheng Liu, Julia Hockenmaier
Publikováno v:
EMNLP/IJCNLP (1)
The phrase grounding task aims to ground each entity mention in a given caption of an image to a corresponding region in that image. Although there are clear dependencies between how different mentions of the same caption should be grounded, previous
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::40524abcbd8acee37fe13327fc29d149
http://arxiv.org/abs/1909.00301
http://arxiv.org/abs/1909.00301
Publikováno v:
ACL (1)
We wish to develop interactive agents that can communicate with humans to collaboratively solve tasks in grounded scenarios. Since computer games allow us to simulate such tasks without the need for physical robots, we define a Minecraft-based collab
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0eb412438ef484348565c68586f014e2
https://doi.org/10.18653/v1/p19-1537
https://doi.org/10.18653/v1/p19-1537
Publikováno v:
Transactions of the Association for Computational Linguistics. 2:67-78
We propose to use the visual denotations of linguistic expressions (i.e. the set of images they describe) to define novel denotational similarity metrics, which we show to be at least as beneficial as distributional similarities for two tasks that re
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4afbb4e9a8a8ae80e362900ca11c69c4
https://doi.org/10.1162/tacl_a_00166
https://doi.org/10.1162/tacl_a_00166
Autor:
Julia Hockenmaier, Alice Lai
Publikováno v:
EACL (1)
We propose a framework that captures the denotational probabilities of words and phrases by embedding them in a vector space, and present a method to induce such an embedding from a dataset of denotational probabilities. We show that our model succes
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d02ad00281ff40463069d79ab2763f90
https://doi.org/10.18653/v1/e17-1068
https://doi.org/10.18653/v1/e17-1068
Autor:
Yonatan Bisk, Julia Hockenmaier
Publikováno v:
Transactions of the Association for Computational Linguistics. 1:75-88
We introduce a novel nonparametric Bayesian model for the induction of Combinatory Categorial Grammars from POS-tagged text. It achieves state of the art performance on a number of languages, and induces linguistically plausible lexicons.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4bd060859a44f769ca7eaac9e40dfb00
https://doi.org/10.1162/tacl_a_00211
https://doi.org/10.1162/tacl_a_00211