Related papers: Conditional Variational Autoencoder for Neural Mac…
In this work, we propose to model the interaction between visual and textual features for multi-modal neural machine translation (MMT) through a latent variable model. This latent variable can be seen as a multi-modal stochastic embedding…
Partially inspired by successful applications of variational recurrent neural networks, we propose a novel variational recurrent neural machine translation (VRNMT) model in this paper. Different from the variational NMT, VRNMT introduces a…
Models of neural machine translation are often from a discriminative family of encoderdecoders that learn a conditional distribution of a target sentence given a source sentence. In this paper, we propose a variational model to learn this…
Recently it was shown that linguistic structure predicted by a supervised parser can be beneficial for neural machine translation (NMT). In this work we investigate a more challenging setup: we incorporate sentence structure as a latent…
Although attention-based Neural Machine Translation have achieved great success, attention-mechanism cannot capture the entire meaning of the source sentence because the attention mechanism generates a target word depending heavily on the…
Variational Neural Machine Translation (VNMT) is an attractive framework for modeling the generation of target translations, conditioned not only on the source sentence but also on some latent random variables. The latent variable modeling…
Neural Machine Translation (NMT) models often lack diversity in their generated translations, even when paired with search algorithm, like beam search. A challenge is that the diversity in translations are caused by the variability in the…
We introduce Generative Neural Machine Translation (GNMT), a latent variable architecture which is designed to model the semantics of the source and target sentences. We modify an encoder-decoder translation model by adding a latent…
Posterior collapse plagues VAEs for text, especially for conditional text generation with strong autoregressive decoders. In this work, we address this problem in variational neural machine translation by explicitly promoting mutual…
A latent-variable model is introduced for text matching, inferring sentence representations by jointly optimizing generative and discriminative objectives. To alleviate typical optimization challenges in latent-variable models for text, we…
Translation into morphologically-rich languages challenges neural machine translation (NMT) models with extremely sparse vocabularies where atomic treatment of surface forms is unrealistic. This problem is typically addressed by either…
Generative classifiers offer potential advantages over their discriminative counterparts, namely in the areas of data efficiency, robustness to data shift and adversarial examples, and zero-shot learning (Ng and Jordan,2002; Yogatama et…
Recently, discrete latent variable models have received a surge of interest in both Natural Language Processing (NLP) and Computer Vision (CV), attributed to their comparable performance to the continuous counterparts in representation…
While recent neural encoder-decoder models have shown great promise in modeling open-domain conversations, they often generate dull and generic responses. Unlike past work that has focused on diversifying the output of the decoder at…
We introduce multi-modal, attention-based neural machine translation (NMT) models which incorporate visual features into different parts of both the encoder and the decoder. We utilise global image features extracted using a pre-trained…
Attention-based Neural Machine Translation (NMT) models suffer from attention deficiency issues as has been observed in recent research. We propose a novel mechanism to address some of these limitations and improve the NMT attention.…
Learning target side syntactic structure has been shown to improve Neural Machine Translation (NMT). However, incorporating syntax through latent variables introduces additional complexity in inference, as the models need to marginalize…
Non-autoregressive neural machine translation (NAT) offers substantial translation speed up compared to autoregressive neural machine translation (AT) at the cost of translation quality. Latent variable modeling has emerged as a promising…
Recent advances in neural variational inference have spawned a renaissance in deep latent variable models. In this paper we introduce a generic variational inference framework for generative and conditional models of text. While traditional…
Most existing document-level neural machine translation (NMT) models leverage a fixed number of the previous or all global source sentences to handle the context-independent problem in standard NMT. However, the translating of each source…