Visual question answering (VQA) is challenging not only because the model has to handle multi-modal information, but also because it is just so hard to collect sufficient training examples --- there are too many questions one can ask about an image.
As a result, a VQA model trained solely on human-annotated examples could easily over-fit specific question styles or image contents that are being asked, leaving the model largely ignorant about the sheer diversity of questions. Existing methods address this issue primarily by introducing an auxiliary task such as visual grounding, cycle consistency, or debiasing. In this paper, we take a drastically different approach. We found that many of the unknowns'' to the learned VQA model are indeed known'' in the dataset implicitly. For instance, questions asking about the same object in different images are likely paraphrases; the number of detected or annotated objects in an image already provides the answer to the how many'' question, even if the question has not been annotated for that image. Building upon these insights, we present a simple data augmentation pipeline SimpleAug to turn this known'' knowledge into training examples for VQA. We show that these augmented examples can notably improve the learned VQA models' performance, not only on the VQA-CP dataset with language prior shifts but also on the VQA v2 dataset without such shifts. Our method further opens up the door to leverage weakly-labeled or unlabeled images in a principled way to enhance VQA models. Our code and data are publicly available at https://github.com/heendung/simpleAUG.
Hate speech has grown significantly on social media, causing serious consequences for victims of all demographics. Despite much attention being paid to characterize and detect discriminatory speech, most work has focused on explicit or overt hate spe
ech, failing to address a more pervasive form based on coded or indirect language. To fill this gap, this work introduces a theoretically-justified taxonomy of implicit hate speech and a benchmark corpus with fine-grained labels for each message and its implication. We present systematic analyses of our dataset using contemporary baselines to detect and explain implicit hate speech, and we discuss key features that challenge existing models. This dataset will continue to serve as a useful benchmark for understanding this multifaceted issue.
Abstract Meaning Representation (AMR) has become popular for representing the meaning of natural language in graph structures. However, AMR does not represent scope information, posing a problem for its overall expressivity and specifically for drawi
ng inferences from negated statements. This is the case with so-called positive interpretations'' of negated statements, in which implicit positive meaning is identified by inferring the opposite of the negation's focus. In this work, we investigate how potential positive interpretations (PPIs) can be represented in AMR. We propose a logically motivated AMR structure for PPIs that makes the focus of negation explicit and sketch an initial proposal for a systematic methodology to generate this more expressive structure.
Humans make appropriate responses not only based on previous dialogue utterances but also on implicit background knowledge such as common sense. Although neural response generation models seem to produce human-like responses, they are mostly end-to-e
nd and not generating intermediate grounds between a dialogue history and responses. This work aims to study if and how we can train an RG model that talks with itself to generate implicit knowledge before making responses. We further investigate can such models identify when to generate implicit background knowledge and when it is not necessary. Experimental results show that compared with models that directly generate responses given a dialogue history, self-talk models produce better-quality responses according to human evaluation on grammaticality, coherence, and engagingness. And models that are trained to identify when to self-talk further improves the response quality. Analysis on generated implicit knowledge shows that models mostly use the knowledge appropriately in the responses.
Pre-trained language models learn socially harmful biases from their training corpora, and may repeat these biases when used for generation. We study gender biases associated with the protagonist in model-generated stories. Such biases may be express
ed either explicitly (women can't park'') or implicitly (e.g. an unsolicited male character guides her into a parking space). We focus on implicit biases, and use a commonsense reasoning engine to uncover them. Specifically, we infer and analyze the protagonist's motivations, attributes, mental states, and implications on others. Our findings regarding implicit biases are in line with prior work that studied explicit biases, for example showing that female characters' portrayal is centered around appearance, while male figures' focus on intellect.
Implicit event argument extraction (EAE) is a crucial document-level information extraction task that aims to identify event arguments beyond the sentence level. Despite many efforts for this task, the lack of enough training data has long impeded th
e study. In this paper, we take a new perspective to address the data sparsity issue faced by implicit EAE, by bridging the task with machine reading comprehension (MRC). Particularly, we devise two data augmentation regimes via MRC, including: 1) implicit knowledge transfer, which enables knowledge transfer from other tasks, by building a unified training framework in the MRC formulation, and 2) explicit data augmentation, which can explicitly generate new training examples, by treating MRC models as an annotator. The extensive experiments have justified the effectiveness of our approach --- it not only obtains state-of-the-art performance on two benchmarks, but also demonstrates superior results in a data-low scenario.
Implicit discourse relation recognition (IDRR) is a critical task in discourse analysis. Previous studies only regard it as a classification task and lack an in-depth understanding of the semantics of different relations. Therefore, we first view IDR
R as a generation task and further propose a method joint modeling of the classification and generation. Specifically, we propose a joint model, CG-T5, to recognize the relation label and generate the target sentence containing the meaning of relations simultaneously. Furthermore, we design three target sentence forms, including the question form, for the generation model to incorporate prior knowledge. To address the issue that large discourse units are hardly embedded into the target sentence, we also propose a target sentence construction mechanism that automatically extracts core sentences from those large discourse units. Experimental results both on Chinese MCDTB and English PDTB datasets show that our model CG-T5 achieves the best performance against several state-of-the-art systems.
In implicit discourse relation classification, we want to predict the relation between adjacent sentences in the absence of any overt discourse connectives. This is challenging even for humans, leading to shortage of annotated data, a fact that makes
the task even more difficult for supervised machine learning approaches. In the current study, we perform implicit discourse relation classification without relying on any labeled implicit relation. We sidestep the lack of data through explicitation of implicit relations to reduce the task to two sub-problems: language modeling and explicit discourse relation classification, a much easier problem. Our experimental results show that this method can even marginally outperform the state-of-the-art, in spite of being much simpler than alternative models of comparable performance. Moreover, we show that the achieved performance is robust across domains as suggested by the zero-shot experiments on a completely different domain. This indicates that recent advances in language modeling have made language models sufficiently good at capturing inter-sentence relations without the help of explicit discourse markers.
Broad-coverage meaning representations in NLP mostly focus on explicitly expressed content. More importantly, the scarcity of datasets annotating diverse implicit roles limits empirical studies into their linguistic nuances. For example, in the web r
eview Great service!'', the provider and consumer are implicit arguments of different types. We examine an annotated corpus of fine-grained implicit arguments (Cui and Hershcovich, 2020) by carefully re-annotating it, resolving several inconsistencies. Subsequently, we present the first transition-based neural parser that can handle implicit arguments dynamically, and experiment with two different transition systems on the improved dataset. We find that certain types of implicit arguments are more difficult to parse than others and that the simpler system is more accurate in recovering implicit arguments, despite having a lower overall parsing score, attesting current reasoning limitations of NLP models. This work will facilitate a better understanding of implicit and underspecified language, by incorporating it holistically into meaning representations.
In this work we leverage commonsense knowledge in form of knowledge paths to establish connections between sentences, as a form of explicitation of implicit knowledge. Such connections can be direct (singlehop paths) or require intermediate concepts
(multihop paths). To construct such paths we combine two model types in a joint framework we call Co-nnect: a relation classifier that predicts direct connections between concepts; and a target prediction model that generates target or intermediate concepts given a source concept and a relation, which we use to construct multihop paths. Unlike prior work that relies exclusively on static knowledge sources, we leverage language models finetuned on knowledge stored in ConceptNet, to dynamically generate knowledge paths, as explanations of implicit knowledge that connects sentences in texts. As a central contribution we design manual and automatic evaluation settings for assessing the quality of the generated paths. We conduct evaluations on two argumentative datasets and show that a combination of the two model types generates meaningful, high-quality knowledge paths between sentences that reveal implicit knowledge conveyed in text.
