Recently BERT has been adopted in state-of-the-art text summarization models for document encoding. However, such BERT-based extractive models use the sentence as the minimal selection unit, which often results in redundant or uninformative phrases in the generated summaries. As BERT is pre-trained on sentence pairs, not documents, the long-range dependencies between sentences are not well captured. To address these issues, we present a graph-based discourse-aware neural summarization model - DiscoBert. By utilizing discourse segmentation to extract discourse units (instead of sentences) as candidates, DiscoBert provides a fine-grained granularity for extractive selection, which helps reduce redundancy in extracted summaries. Based on this, two discourse graphs are further proposed: ($i$) RST Graph based on RST discourse trees; and ($ii$) Coreference Graph based on coreference mentions in the document. DiscoBert first encodes the extracted discourse units with BERT, and then uses a graph convolutional network to capture the long-range dependencies among discourse units through the constructed graphs. Experimental results on two popular summarization datasets demonstrate that DiscoBert outperforms state-of-the-art methods by a significant margin.
There are two main lines of research on visual reasoning: neural module network (NMN) with \emph{explicit} multi-hop reasoning through handcrafted neural modules, and monolithic network with \emph{implicit} reasoning in the latent feature space. The former excels in interpretability and compositionality, while the latter usually achieves better performance due to model flexibility and parameter efficiency. In order to bridge the gap of the two, we present Meta Module Network (MMN), a novel hybrid approach that can efficiently utilize a Meta Module to perform versatile functionalities, while preserving compositionality and interpretability through modularized design. The proposed model first parses an input question into a functional program through a Program Generator. Instead of handcrafting a task-specific network to represent each function like traditional NMN, we use Recipe Encoder to translate the functions into their corresponding recipes (specifications), which are used to dynamically instantiate the Meta Module into Instance Modules. To endow different instance modules with designated functionality, a Teacher-Student framework is proposed, where a symbolic teacher pre-executes against the scene graphs to provide guidelines for the instantiated modules (student) to follow. In a nutshell, MMN adopts the meta module to increase its parameterization efficiency and uses recipe encoding to improve its generalization ability over NMN. Experiments conducted on the GQA benchmark demonstrates that: ($i$) MMN achieves significant improvement over both NMN and monolithic network baselines; ($ii$) MMN is able to generalize to unseen but related functions.
Adversarial training, which minimizes the maximal risk for label-preserving input perturbations, has proved to be effective for improving the generalization of language models. In this work, we propose a novel adversarial training algorithm - FreeLB, that promotes higher robustness and invariance in the embedding space, by adding adversarial perturbations to word embeddings and minimizing the resultant adversarial risk inside different regions around input samples. To validate the effectiveness of the proposed approach, we apply it to Transformer-based models for natural language understanding and commonsense reasoning tasks. Experiments on the GLUE benchmark show that when applied only to the finetuning stage, it is able to improve the overall test scores of BERT-based model from 78.3 to 79.4, and RoBERTa-large model from 88.5 to 88.8. In addition, the proposed approach achieves state-of-the-art single-model test accuracies of 85.44% and 67.75% on ARC-Easy and ARC-Challenge. Experiments on CommonsenseQA benchmark further demonstrate that FreeLB can be generalized and boost the performance of RoBERTa-large model on other tasks as well.
The performance of many network learning applications crucially hinges on the success of network embedding algorithms, which aim to encode rich network information into low-dimensional vertex-based vector representations. This paper considers a novel variational formulation of network embeddings, with special focus on textual networks. Different from most existing methods that optimize a discriminative objective, we introduce Variational Homophilic Embedding (VHE), a fully generative model that learns network embeddings by modeling the semantic (textual) information with a variational autoencoder, while accounting for the structural (topology) information through a novel homophilic prior design. Homophilic vertex embeddings encourage similar embedding vectors for related (connected) vertices. The proposed VHE promises better generalization for downstream tasks, robustness to incomplete observations, and the ability to generalize to unseen vertices. Extensive experiments on real-world networks, for multiple tasks, demonstrate that the proposed method consistently achieves superior performance relative to competing state-of-the-art approaches.
Joint image-text embedding is the bedrock for most Vision-and-Language (V+L) tasks, where multimodality inputs are jointly processed for visual and textual understanding. In this paper, we introduce UNITER, a UNiversal Image-TExt Representation, learned through large-scale pre-training over four image-text datasets (COCO, Visual Genome, Conceptual Captions, and SBU Captions), which can power heterogeneous downstream V+L tasks with joint multimodal embeddings. We design three pre-training tasks: Masked Language Modeling (MLM), Image-Text Matching (ITM), and Masked Region Modeling (MRM, with three variants). Different from concurrent work on multimodal pre-training that apply joint random masking to both modalities, we use conditioned masking on pre-training tasks (i.e., masked language/region modeling is conditioned on full observation of image/text). Comprehensive analysis shows that conditioned masking yields better performance than unconditioned masking. We also conduct a thorough ablation study to find an optimal setting for the combination of pre-training tasks. Extensive experiments show that UNITER achieves new state of the art across six V+L tasks (over nine datasets), including Visual Question Answering, Image-Text Retrieval, Referring Expression Comprehension, Visual Commonsense Reasoning, Visual Entailment, and NLVR2.
Recent unsupervised approaches to domain adaptation primarily focus on minimizing the gap between the source and the target domains through refining the feature generator, in order to learn a better alignment between the two domains. This minimization can be achieved via a domain classifier to detect target-domain features that are divergent from source-domain features. However, by optimizing via such domain classification discrepancy, ambiguous target samples that are not smoothly distributed on the low-dimensional data manifold are often missed. To solve this issue, we propose a novel Contrastively Smoothed Class Alignment (CoSCA) model, that explicitly incorporates both intra- and inter-class domain discrepancy to better align ambiguous target samples with the source domain. CoSCA estimates the underlying label hypothesis of target samples, and simultaneously adapts their feature representations by optimizing a proposed contrastive loss. In addition, Maximum Mean Discrepancy (MMD) is utilized to directly match features between source and target samples for better global alignment. Experiments on several benchmark datasets demonstrate that CoSCA can outperform state-of-the-art approaches for unsupervised domain adaptation by producing more discriminative features.
Previous storytelling approaches mostly focused on optimizing traditional metrics such as BLEU, ROUGE and CIDEr. In this paper, we re-examine this problem from a different angle, by looking deep into what defines a realistically-natural and topically-coherent story. To this end, we propose three assessment criteria: relevance, coherence and expressiveness, which we observe through empirical analysis could constitute a "high-quality" story to the human eye. Following this quality guideline, we propose a reinforcement learning framework, ReCo-RL, with reward functions designed to capture the essence of these quality criteria. Experiments on the Visual Storytelling Dataset (VIST) with both automatic and human evaluations demonstrate that our ReCo-RL model achieves better performance than state-of-the-art baselines on both traditional metrics and the proposed new criteria.
This paper presents a new metric called TIGEr for the automatic evaluation of image captioning systems. Popular metrics, such as BLEU and CIDEr, are based solely on text matching between reference captions and machine-generated captions, potentially leading to biased evaluations because references may not fully cover the image content and natural language is inherently ambiguous. Building upon a machine-learned text-image grounding model, TIGEr allows to evaluate caption quality not only based on how well a caption represents image content, but also on how well machine-generated captions match human-generated captions. Our empirical tests show that TIGEr has a higher consistency with human judgments than alternative existing metrics. We also comprehensively assess the metric's effectiveness in caption evaluation by measuring the correlation between human judgments and metric scores.