Related papers: Latent Variable Model for Multi-modal Translation
Unsupervised machine translation (MT) has recently achieved impressive results with monolingual corpora only. However, it is still challenging to associate source-target sentences in the latent space. As people speak different languages…
Multimodal Machine Translation (MMT) focuses on enhancing text-only translation with visual features, which has attracted considerable attention from both natural language processing and computer vision communities. Recent advances still…
This paper addresses the problem of simultaneous machine translation (SiMT) by exploring two main concepts: (a) adaptive policies to learn a good trade-off between high translation quality and low latency; and (b) visual information to…
Recent research in the field of multimodal machine translation (MMT) has indicated that the visual modality is either dispensable or offers only marginal advantages. However, most of these conclusions are drawn from the analysis of…
Recently, there has been a surge in research in multimodal machine translation (MMT), where additional modalities such as images are used to improve translation quality of textual systems. A particular use for such multimodal systems is the…
We present a generative model for multitask conditional language generation. Our guiding hypothesis is that a shared set of latent skills underlies many disparate language generation tasks, and that explicitly modelling these skills in a…
Neural Machine Translation (NMT) has made remarkable progress using large-scale textual data, but the potential of incorporating multimodal inputs, especially visual information, remains underexplored in high-resource settings. While prior…
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…
Latent variable models have been a preferred choice in conversational modeling compared to sequence-to-sequence (seq2seq) models which tend to generate generic and repetitive responses. Despite so, training latent variable models remains to…
Unsupervised neural machine translation (UNMT) has recently achieved remarkable results with only large monolingual corpora in each language. However, the uncertainty of associating target with source sentences makes UNMT theoretically an…
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…
Adding linguistic information (syntax or semantics) to neural machine translation (NMT) has mostly focused on using point estimates from pre-trained models. Directly using the capacity of massive pre-trained contextual word embedding models…
Neural chat translation aims to translate bilingual conversational text, which has a broad application in international exchanges and cooperation. Despite the impressive performance of sentence-level and context-aware Neural Machine…
In state-of-the-art Neural Machine Translation (NMT), an attention mechanism is used during decoding to enhance the translation. At every step, the decoder uses this mechanism to focus on different parts of the source sentence to gather the…
Image captioning model is a cross-modality knowledge discovery task, which targets at automatically describing an image with an informative and coherent sentence. To generate the captions, the previous encoder-decoder frameworks directly…
While language reasoning models excel in many tasks, visual reasoning remains challenging for current large multimodal models (LMMs). As a result, most LMMs default to verbalizing perceptual content into text, a strong limitation for tasks…
Multimodal machine translation (MMT) systems have been shown to outperform their text-only neural machine translation (NMT) counterparts when visual context is available. However, recent studies have also shown that the performance of MMT…
Multi-modal machine translation (MMT) improves translation quality by introducing visual information. However, the existing MMT model ignores the problem that the image will bring information irrelevant to the text, causing much noise to…
Visual information has been introduced for enhancing machine translation (MT), and its effectiveness heavily relies on the availability of large amounts of bilingual parallel sentence pairs with manual image annotations. In this paper, we…
Linguistic knowledge has brought great benefits to scene text recognition by providing semantics to refine character sequences. However, since linguistic knowledge has been applied individually on the output sequence, previous methods have…