Zobrazeno 1 - 10
of 41
pro vyhledávání: '"Basirat, Ali"'
Autor:
Basirat, Ali, Nivre, Joakim
Standard models for syntactic dependency parsing take words to be the elementary units that enter into dependency relations. In this paper, we investigate whether there are any benefits from enriching these models with the more abstract notion of nuc
Externí odkaz:
http://arxiv.org/abs/2101.11959
Autor:
Chen, Shifei, Basirat, Ali
We explore the transferability of a multilingual neural machine translation model to unseen languages when the transfer is grounded solely on the cross-lingual word embeddings. Our experimental results show that the translation knowledge can transfer
Externí odkaz:
http://arxiv.org/abs/2011.01682
Autor:
Veeman, Hartger, Basirat, Ali
The vector representation of words, known as word embeddings, has opened a new research approach in linguistic studies. These representations can capture different types of information about words. The grammatical gender of nouns is a typical classif
Externí odkaz:
http://arxiv.org/abs/2008.01946
Autor:
Allassonnière-Tang, Marc, Basirat, Ali
We analyze the information provided by the word embeddings about the grammatical gender in Swedish. We wish that this paper may serve as one of the bridges to connect the methods of computational linguistics and general linguistics. Taking nominal cl
Externí odkaz:
http://arxiv.org/abs/2007.14222
Autor:
Basirat, Ali, Nivre, Joakim
We study the effect of rich supertag features in greedy transition-based dependency parsing. While previous studies have shown that sparse boolean features representing the 1-best supertag of a word can improve parsing accuracy, we show that we can g
Externí odkaz:
http://arxiv.org/abs/2007.04686
We generalize principal component analysis for embedding words into a vector space. The generalization is made in two major levels. The first is to generalize the concept of the corpus as a counting process which is defined by three key elements voca
Externí odkaz:
http://arxiv.org/abs/2007.04629
Autor:
Basirat, Ali
We extend the randomized singular value decomposition (SVD) algorithm \citep{Halko2011finding} to estimate the SVD of a shifted data matrix without explicitly constructing the matrix in the memory. With no loss in the accuracy of the original algorit
Externí odkaz:
http://arxiv.org/abs/1911.11772
Autor:
Nivre, Joakim1 (AUTHOR) joakim.nivre@lingfil.uu.se, Basirat, Ali2 (AUTHOR) ali.basirat@liu.se, Durlich, Luise3 (AUTHOR) luise.durlich@ri.se, Moss, Adam4 (AUTHOR) adam.moss@lingfil.uu.se
Publikováno v:
Computational Linguistics. Dec2022, Vol. 48 Issue 4, p849-886. 38p.
Autor:
Basirat, Ali, Faili, Heshaam
Publikováno v:
In Computer Speech & Language August 2013 27(5):1085-1104
Publikováno v:
Contributions to the History of Concepts (Berghahn Books); Winter2022, Vol. 17 Issue 2, p95-122, 28p