Výsledky vyhledávání

Akademický článek

An Empirical Study of Encoders and Decoders in Graph-Based Dependency Parsing

Autor: Ge Wang, Ziyuan Hu, Zechuan Hu, Kewei Tu

Publikováno v: IEEE Access, Vol 8, Pp 35770-35776 (2020)

Graph-based dependency parsing consists of two steps: first, an encoder produces a feature representation for each parsing substructure of the input sentence, which is then used to compute a score for the substructure; and second, a decoder finds the

Externí odkaz: https://doaj.org/article/a6dd274883b14498a8fabccfd0b4a7c1

Zobrazit plný text záznamu

Akademický článek

Projective Latent Dependency Forest Models

Autor: Yong Jiang, Yang Zhou, Kewei Tu

Publikováno v: IEEE Access, Vol 7, Pp 12328-12338 (2019)

Latent dependence forest models (LDFM) are a new type of probabilistic models with the advantage of not requiring the difficult procedure of structure learning in model learning. However, normalized joint probability computation and marginal inferenc

Externí odkaz: https://doaj.org/article/55773109b9fb49eab776cd2e5ab85a80

Zobrazit plný text záznamu

Akademický článek

Latent Variable Autoencoder

Autor: Wenjuan Han, Ge Wang, Kewei Tu

Publikováno v: IEEE Access, Vol 7, Pp 48514-48523 (2019)

Learning to discover hidden variables from unlabeled data is an important task. Traditional generative methods model the generation process of the observed variables as well as the hidden variables. However, tractable inference and learning on these

Externí odkaz: https://doaj.org/article/462056a0cfd14526a12d17f5ca7d6460

Zobrazit plný text záznamu

Span-Based Semantic Role Labeling with Argument Pruning and Second-Order Inference

Autor: Zixia Jia, Zhaohui Yan, Haoyi Wu, Kewei Tu

Publikováno v: Proceedings of the AAAI Conference on Artificial Intelligence. 36:10822-10830

We study graph-based approaches to span-based semantic role labeling. This task is difficult due to the need to enumerate all possible predicate-argument pairs and the high degree of imbalance between positive and negative samples. Based on these dif

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::fd21cb965e334f0fdab18cc298ff3681
https://doi.org/10.1609/aaai.v36i10.21328

Zobrazit plný text záznamu

Dynamic Programming in Rank Space: Scaling Structured Inference with Low-Rank HMMs and PCFGs

Autor: Songlin Yang, Wei Liu, Kewei Tu

Hidden Markov Models (HMMs) and Probabilistic Context-Free Grammars (PCFGs) are widely used structured models, both of which can be represented as factor graph grammars (FGGs), a powerful formalism capable of describing a wide range of models. Recent

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2cea5adb74ebc8f9c974c5eaf5948719
http://arxiv.org/abs/2205.00484

Zobrazit plný text záznamu

Robust unsupervised discriminative dependency parsing

Autor: Kewei Tu, Jiong Cai, Yong Jiang

Publikováno v: Tsinghua Science and Technology. 25:192-202

Discriminative approaches have shown their effectiveness in unsupervised dependency parsing. However, due to their strong representational power, discriminative approaches tend to quickly converge to poor local optima during unsupervised training. In

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::59dff9b1f954ab80b851a4e5af0854ff
https://doi.org/10.26599/tst.2018.9010145

Zobrazit plný text záznamu

Nested Named Entity Recognition as Latent Lexicalized Constituency Parsing

Autor: Chao Lou, Songlin Yang, Kewei Tu

Nested named entity recognition (NER) has been receiving increasing attention. Recently, (Fu et al, 2021) adapt a span-based constituency parser to tackle nested NER. They treat nested entities as partially-observed constituency trees and propose the

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c30074d4678d32dc38a6aeb7a225a69b
http://arxiv.org/abs/2203.04665

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání