By supporting multi-modal retrieval training and evaluation, image captioning datasets have spurred remarkable progress on representation learning. Unfortunately, datasets have limited cross-modal associations: images are not paired with other images, captions are only paired with other captions of the same image, there are no negative associations and there are missing positive cross-modal associations. This undermines research into how inter-modality learning impacts intra-modality tasks. We address this gap with Crisscrossed Captions (CxC), an extension of the MS-COCO dataset with human semantic similarity judgments for 267,095 intra- and inter-modality pairs. We report baseline results on CxC for strong existing unimodal and multimodal models. We also evaluate a multitask dual encoder trained on both image-caption and caption-caption pairs that crucially demonstrates CxC’s value for measuring the influence of intra- and inter-modality learning.
We present a novel approach to the problem of text style transfer. Unlike previous approaches requiring style-labeled training data, our method makes use of readily-available unlabeled text by relying on the implicit connection in style between adjacent sentences, and uses labeled data only at inference time. We adapt T5 (Raffel et al., 2020), a strong pretrained text-to-text model, to extract a style vector from text and use it to condition the decoder to perform style transfer. As our label-free training results in a style vector space encoding many facets of style, we recast transfers as “targeted restyling” vector operations that adjust specific attributes of the input while preserving others. We demonstrate that training on unlabeled Amazon reviews data results in a model that is competitive on sentiment transfer, even compared to models trained fully on labeled data. Furthermore, applying our novel method to a diverse corpus of unlabeled web text results in a single model capable of transferring along multiple dimensions of style (dialect, emotiveness, formality, politeness, sentiment) despite no additional training and using only a handful of exemplars at inference time.
Pairwise data automatically constructed from weakly supervised signals has been widely used for training deep learning models. Pairwise datasets such as parallel texts can have uneven quality levels overall, but usually contain data subsets that are more useful as learning examples. We present two methods to refine data that are aimed to obtain that kind of subsets in a self-supervised way. Our methods are based on iteratively training dual-encoder models to compute similarity scores. We evaluate our methods on de-noising parallel texts and training neural machine translation models. We find that: (i) The self-supervised refinement achieves most machine translation gains in the first iteration, but following iterations further improve its intrinsic evaluation. (ii) Machine translations can improve the de-noising performance when combined with selection steps. (iii) Our methods are able to reach the performance of a supervised method. Being entirely self-supervised, our methods are well-suited to handle pairwise data without the need of prior knowledge or human annotations.
Most data selection research in machine translation focuses on improving a single domain. We perform data selection for multiple domains at once. This is achieved by carefully introducing instance-level domain-relevance features and automatically constructing a training curriculum to gradually concentrate on multi-domain relevant and noise-reduced data batches. Both the choice of features and the use of curriculum are crucial for balancing and improving all domains, including out-of-domain. In large-scale experiments, the multi-domain curriculum simultaneously reaches or outperforms the individual performance and brings solid gains over no-curriculum training.
The task of retrieving clips within videos based on a given natural language query requires cross-modal reasoning over multiple frames. Prior approaches such as sliding window classifiers are inefficient, while text-clip similarity driven ranking-based approaches such as segment proposal networks are far more complicated. In order to select the most relevant video clip corresponding to the given text description, we propose a novel extractive approach that predicts the start and end frames by leveraging cross-modal interactions between the text and video - this removes the need to retrieve and re-rank multiple proposal segments. Using recurrent networks we encode the two modalities into a joint representation which is then used in different variants of start-end frame predictor networks. Through extensive experimentation and ablative analysis, we demonstrate that our simple and elegant approach significantly outperforms state of the art on two datasets and has comparable performance on a third.
RLIE-DQN is a recently proposed Reinforcement Learning-based Information Extraction (IE) technique which is able to incorporate external evidence during the extraction process. RLIE-DQN trains a single agent sequentially, training on one instance at a time. This results in significant training slowdown which is undesirable. We leverage recent advances in parallel RL training using asynchronous methods and propose RLIE-A3C. RLIE-A3C trains multiple agents in parallel and is able to achieve upto 6x training speedup over RLIE-DQN, while suffering no loss in average accuracy.