Zobrazeno 1 - 10
of 38
pro vyhledávání: '"Stanojevic, Milos"'
Humans understand sentences word-by-word, in the order that they hear them. This incrementality entails resolving temporary ambiguities about syntactic relationships. We investigate how humans process these syntactic ambiguities by correlating predic
Externí odkaz:
http://arxiv.org/abs/2401.18046
Autor:
Stanojević, Miloš, Sartran, Laurent
The development of deep learning software libraries enabled significant progress in the field by allowing users to focus on modeling, while letting the library to take care of the tedious and time-consuming task of optimizing execution for modern har
Externí odkaz:
http://arxiv.org/abs/2308.03291
To model behavioral and neural correlates of language comprehension in naturalistic environments researchers have turned to broad-coverage tools from natural-language processing and machine learning. Where syntactic structure is explicitly modeled, p
Externí odkaz:
http://arxiv.org/abs/2210.16147
Autor:
Stanojević, Miloš
Most computational models of dependency syntax consist of distributions over spanning trees. However, the majority of dependency treebanks require that every valid dependency tree has a single edge coming out of the ROOT node, a constraint that is no
Externí odkaz:
http://arxiv.org/abs/2205.12621
Autor:
Sartran, Laurent, Barrett, Samuel, Kuncoro, Adhiguna, Stanojević, Miloš, Blunsom, Phil, Dyer, Chris
We introduce Transformer Grammars (TGs), a novel class of Transformer language models that combine (i) the expressive power, scalability, and strong performance of Transformers and (ii) recursive syntactic compositions, which here are implemented thr
Externí odkaz:
http://arxiv.org/abs/2203.00633
Publikováno v:
In Proceedings of CASE 2021, pages 31-42, online. Association for Computational Linguistics
Language provides speakers with a rich system of modality for expressing thoughts about events, without being committed to their actual occurrence. Modality is commonly used in the political news domain, where both actual and possible courses of even
Externí odkaz:
http://arxiv.org/abs/2109.09393
Autor:
Stanojevic, Milos
Název práce: Rozsáhlé diskriminativní modely pro trénování strojového překladu do morfologicky bohatých jazyků Autor: Miloš Stanojevi'c Katedra: Institute of Formal and Applied Linguistics, Faculty of Mathematics and Physics, Charles Uni
Externí odkaz:
http://www.nusl.cz/ntk/nusl-328551
Autor:
Stanojevic, Milos
Title: Large-Scale Discriminative Training for Machine Translation into Morphologically-Rich Languages Author: Miloš Stanojević Department: Institute of Formal and Applied Linguistics, Faculty of Mathematics and Physics, Charles University in Pragu
Externí odkaz:
http://www.nusl.cz/ntk/nusl-305131
Autor:
Stanojević, Miloš
Most trainable machine translation (MT) metrics train their weights on human judgments of state-of-the-art MT systems outputs. This makes trainable metrics biases in many ways. One of them is preferring longer translations. These biased metrics when
Externí odkaz:
http://arxiv.org/abs/1508.02445
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.