Backward-Forward Sequence Generative Network for Multiple Lexical Constraints - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2020

Backward-Forward Sequence Generative Network for Multiple Lexical Constraints


Advancements in Long Short Term Memory (LSTM) Networks have shown remarkable success in various Natural Language Generation (NLG) tasks. However, generating sequence from pre-specified lexical constraints is a new, challenging and less researched area in NLG. Lexical constraints take the form of words in the language model’s output to create fluent and meaningful sequences. Furthermore, most of the previous approaches cater this problem by allowing the inclusion of pre-specified lexical constraints during the decoding process, which increases the decoding complexity exponentially or linearly with the number of constraints. Moreover, some of the previous approaches can only deal with single constraint. Additionally, most of the previous approaches only deal with single constraints. In this paper, we propose a novel neural probabilistic architecture based on backward-forward language model and word embedding substitution method that can cater multiple lexical constraints for generating quality sequences. Experiments shows that our proposed architecture outperforms previous methods in terms of intrinsic evaluation.
Fichier principal
Vignette du fichier
500087_1_En_4_Chapter.pdf (518.52 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-04060686 , version 1 (06-04-2023)


Attribution - CC BY 4.0



Seemab Latif, Sarmad Bashir, Mir Agha, Rabia Latif. Backward-Forward Sequence Generative Network for Multiple Lexical Constraints. 16th IFIP International Conference on Artificial Intelligence Applications and Innovations (AIAI), Jun 2020, Neos Marmaras, Greece. pp.39-50, ⟨10.1007/978-3-030-49186-4_4⟩. ⟨hal-04060686⟩
6 View
4 Download



Gmail Facebook Twitter LinkedIn More