Zobrazeno 1 - 10
of 76
pro vyhledávání: '"Lori Levin"'
Publikováno v:
COLING
Interlinear Glossed Text (IGT) is a widely used format for encoding linguistic information in language documentation projects and scholarly papers. Manual production of IGT takes time and requires linguistic expertise. We attempt to address this issu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::22d7c7c636db8187fe406b5238a1aaf3
https://doi.org/10.18653/v1/2020.coling-main.471
https://doi.org/10.18653/v1/2020.coling-main.471
Publikováno v:
EMNLP (Findings)
Recently, pre-training contextualized encoders with language model (LM) objectives has been shown an effective semi-supervised method for structured prediction. In this work, we empirically explore an alternative pre-training method for contextualize
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::eaa84f435d1e78b26daa60c753f84bc2
https://doi.org/10.18653/v1/2020.findings-emnlp.160
https://doi.org/10.18653/v1/2020.findings-emnlp.160
Publikováno v:
Transactions of the Association for Computational Linguistics. 5:117-133
This paper explores extending shallow semantic parsing beyond lexical-unit triggers, using causal relations as a test case. Semantic parsing becomes difficult in the face of the wide variety of linguistic realizations that causation can take on. We t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b6080221582a6e74eaa2e9acf7a3a0f3
https://doi.org/10.1162/tacl_a_00050
https://doi.org/10.1162/tacl_a_00050
Autor:
Francis M. Tyers, Hiroaki Hayashi, Alan W. Black, Graham Horwood, Steve Sloto, Teruko Mitamura, David R. Mortensen, Yiming Yang, Lori Levin, Emily Tagtow, Tian Tian, Zaid Sheikh, Eduard Hovy, Ruochen Xu, Patrick Littell
Publikováno v:
Machine Translation. 32:105-126
The LoReHLT16 evaluation challenged participants to extract Situation Frames (SFs)—structured descriptions of humanitarian need situations—from monolingual Uyghur text. The ARIEL-CMU SF detector combines two classification paradigms, a manually c
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::13e0f609daad47dc0e72d7028066a101
https://doi.org/10.1007/s10590-017-9205-3
https://doi.org/10.1007/s10590-017-9205-3
Publikováno v:
EMNLP
This paper introduces the surface construction labeling (SCL) task, which expands the coverage of Shallow Semantic Parsing (SSP) to include frames triggered by complex constructions. We present DeepCx, a neural, transition-based system for SCL. As a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e36e500a73682046b47a540d9eedcef0
https://doi.org/10.18653/v1/d18-1196
https://doi.org/10.18653/v1/d18-1196
Autor:
David R. Mortensen, Graham Neubig, Chunting Zhou, Jaime G. Carbonell, Aditi Chaudhary, Lori Levin
Publikováno v:
EMNLP
Much work in Natural Language Processing (NLP) has been for resource-rich languages, making generalization to new, less-resourced languages challenging. We present two approaches for improving generalization to low-resourced languages by adapting con
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::135d952924997acd0f4812f4b1c15fb8
Autor:
Rachel Reynolds, Alon Lavie, Richard J. Cohen, Stephan Vogel, Ariadna Font Llitjós, Katharina Probst, Lori Levin, Jaime G. Carbonell, Erik J. Peterson
We describe an experiment designed to evaluate the capabilities of our trainable transfer-based (Xfer) machine translation approach, as applied to the task of Hindi-to-English translation, and trained under an extremely limited data scenario. We comp
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bde59dd60e657f52b6594b6721a05db8
Publikováno v:
LAW@ACL
Language of cause and effect captures an essential component of the semantics of a text. However, causal language is also intertwined with other semantic relations, such as temporal precedence and correlation. This makes it difficult to determine whe
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::12850760eeee3282c887ed040cd1d4e2
https://doi.org/10.18653/v1/w17-0812
https://doi.org/10.18653/v1/w17-0812
Publikováno v:
EACL (2)
We introduce the URIEL knowledge base for massively multilingual NLP and the lang2vec utility, which provides information-rich vector identifications of languages drawn from typological, geographical, and phylogenetic databases and normalized to have
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3475f92699025cfb8f0216f342167c69
https://doi.org/10.18653/v1/e17-2002
https://doi.org/10.18653/v1/e17-2002