Výsledky vyhledávání - "Nils Holzenberger"

Factoring Statutory Reasoning as Language Understanding Challenges

Autor: Benjamin Van Durme, Nils Holzenberger

Publikováno v: ACL/IJCNLP (1)

Statutory reasoning is the task of determining whether a legal statute, stated in natural language, applies to the text description of a case. Prior work introduced a resource that approached statutory reasoning as a monolithic textual entailment pro

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3cc6cd2e3b690c8bec4728dbb07be920
http://arxiv.org/abs/2105.07903

Zobrazit plný text záznamu

Tilting at wave beams: a new perspective on the St. Andrew’s Cross

Autor: T. R. Akylas, Takeshi Kataoka, S. J. Ghaemsaidi, Thomas Peacock, Nils Holzenberger

Publikováno v: Journal of Fluid Mechanics. 830:660-680

The generation of internal gravity waves by a vertically oscillating cylinder that is tilted to the horizontal in a stratified Boussinesq fluid of constant buoyancy frequency, $N$, is investigated. This variant of the widely studied horizontal config

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::6bd9a64c39296783ee7099588edbb148
https://doi.org/10.1017/jfm.2017.615

Zobrazit plný text záznamu

Learning from Multiview Correlations in Open-Domain Videos

Autor: Florian Metze, Pranava Madhyastha, Shruti Palaskar, Raman Arora, Nils Holzenberger

Publikováno v: ICASSP

An increasing number of datasets contain multiple views, such as video, sound and automatic captions. A basic challenge in representation learning is how to leverage multiple views to learn better representations. This is further complicated by the e

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::63791503bec8fae677ca8433a62dce28
http://arxiv.org/abs/1811.08890

Zobrazit plný text záznamu

Learning Word Embeddings: Unsupervised Methods for Fixed-size Representations of Variable-length Speech Segments

Autor: Nils Holzenberger, Julien Karadayi, Emmanuel Dupoux, Rachid Riad, Mingxing Du

Publikováno v: Interspeech 2018
Interspeech 2018, Sep 2018, Hyderabad, India. ⟨10.21437/Interspeech.2018-2364⟩
INTERSPEECH

International audience; Fixed-length embeddings of words are very useful for a variety of tasks in speech and language processing. Here we systematically explore two methods of computing fixed-length embeddings for variable-length sequences. We evalu

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8f00e680becaee39b9ed49773f8d6717
https://hal.archives-ouvertes.fr/hal-01888708/document

Zobrazit plný text záznamu

Large-scale, diverse, paraphrastic bitexts via sampling and clustering

Autor: Matt Post, Nils Holzenberger, Benjamin Van Durme, Abhinav Singh, J. Edward Hu

Publikováno v: Scopus-Elsevier
CoNLL

Producing diverse paraphrases of a sentence is a challenging task. Natural paraphrase corpora are scarce and limited, while existing large-scale resources are automatically generated via back-translation and rely on beam search, which tends to lack d

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a9569a1c38c4f8a4a079bb9547768ca8
http://www.scopus.com/inward/record.url?eid=2-s2.0-85084331385&partnerID=MN8TOARS

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání