Related papers: StructVAE: Tree-structured Latent Variable Models …

We present a comparative evaluation of latent space organization in three Variational Autoencoders (VAEs) for musical timbre generation: an unsupervised VAE, a descriptor-conditioned VAE, and a VAE conditioned on continuous perceptual…

Achieving precise semantic control over the latent spaces of Variational AutoEncoders (VAEs) holds significant value for downstream tasks in NLP as the underlying generative mechanisms could be better localised, explained and improved upon.…

An ability to model a generative process and learn a latent representation for speech in an unsupervised fashion will be crucial to process vast quantities of unlabelled speech data. Recently, deep probabilistic generative models such as…

Natural language understanding (NLU) converts sentences into structured semantic forms. The paucity of annotated training samples is still a fundamental challenge of NLU. To solve this data sparsity problem, previous work based on…

We study the problem of self-supervised structured representation learning using autoencoders for downstream tasks such as generative modeling. Unlike most methods which rely on matching an arbitrary, relatively unstructured, prior…

Discourse information, as postulated by popular discourse theories, such as RST and PDTB, has been shown to improve an increasing number of downstream NLP tasks, showing positive effects and synergies of discourse with important real-world…

Data scarcity is one of the main obstacles of domain adaptation in spoken language understanding (SLU) due to the high cost of creating manually tagged SLU datasets. Recent works in neural text generative models, particularly latent…

Word representations induced from models with discrete latent variables (e.g.\ HMMs) have been shown to be beneficial in many NLP applications. In this work, we exploit labeled syntactic dependency trees and formalize the induction problem…

We present a new flavor of Variational Autoencoder (VAE) that interpolates seamlessly between unsupervised, semi-supervised and fully supervised learning domains. We show that unlabeled datapoints not only boost unsupervised tasks, but also…

Identifying implicit discourse relations between text spans is a challenging task because it requires understanding the meaning of the text. To tackle this task, recent studies have tried several deep learning methods but few of them…

Variational auto-encoders (VAEs) are widely used in natural language generation due to the regularization of the latent space. However, generating sentences from the continuous latent space does not explicitly model the syntactic…

For natural language processing systems, two kinds of evidence support the use of text representations from neural language models "pretrained" on large unannotated corpora: performance on application-inspired benchmarks (Peters et al.,…

We propose a novel dependency-based hybrid tree model for semantic parsing, which converts natural language utterance into machine interpretable meaning representations. Unlike previous state-of-the-art models, the semantic information is…

Syntactic Language Models (SLMs) can be trained efficiently to reach relatively high performance; however, they have trouble with inference efficiency due to the explicit generation of syntactic structures. In this paper, we propose a new…

We introduce a neural semantic parser that converts natural language utterances to intermediate representations in the form of predicate-argument structures, which are induced with a transition system and subsequently mapped to target…

Reinforcement Learning (RL) agents often struggle to generalize knowledge to new tasks, even those structurally similar to ones they have mastered. Although recent approaches have attempted to mitigate this issue via zero-shot transfer,…

Language exhibits inherent structures, a property that explains both language acquisition and language change. Given this characteristic, we expect language models to manifest their own internal structures as well. While interpretability…

Novel contexts may often arise in complex querying scenarios such as in evidence-based medicine (EBM) involving biomedical literature, that may not explicitly refer to entities or canonical concept forms occurring in any fact- or rule-based…

Learning meaningful latent representations from nonlinear fMRI data remains a fundamental challenge in neuroimaging analysis. Traditional independent component analysis, widely used due to its ability to estimate interpretable functional…

Neural networks with tree-based sentence encoders have shown better results on many downstream tasks. Most of existing tree-based encoders adopt syntactic parsing trees as the explicit structure prior. To study the effectiveness of…