Evaluations in machine learning rarely use the latest metrics, datasets, or human evaluation in favor of remaining compatible with prior work. The compatibility, often facilitated through leaderboards, thus leads to outdated but standardized evaluation practices. We pose that the standardization is taking place in the wrong spot. Evaluation infrastructure should enable researchers to use the latest methods and what should be standardized instead is how to incorporate these new evaluation advances. We introduce GEMv2, the new version of the Generation, Evaluation, and Metrics Benchmark which uses a modular infrastructure for dataset, model, and metric developers to benefit from each other’s work. GEMv2 supports 40 documented datasets in 51 languages, ongoing online evaluation for all datasets, and our interactive tools make it easier to add new datasets to the living benchmark.

We introduce GEM, a living benchmark for natural language Generation (NLG), its Evaluation, and Metrics. Measuring progress in NLG relies on a constantly evolving ecosystem of automated metrics, datasets, and human evaluation standards. Due to this moving target, new models often still evaluate on divergent anglo-centric corpora with well-established, but flawed, metrics. This disconnect makes it challenging to identify the limitations of current models and opportunities for progress. Addressing this limitation, GEM provides an environment in which models can easily be applied to a wide set of tasks and in which evaluation strategies can be tested. Regular updates to the benchmark will help NLG research become more multilingual and evolve the challenge alongside models. This paper serves as the description of the data for the 2021 shared task at the associated GEM Workshop.

We propose EASE, a simple diagnostic tool for Visual Question Answering (VQA) which quantifies the difficulty of an image, question sample. EASE is based on the pattern of answers provided by multiple annotators to a given question. In particular, it considers two aspects of the answers: (i) their Entropy; (ii) their Semantic content. First, we prove the validity of our diagnostic to identify samples that are easy/hard for state-of-art VQA models. Second, we show that EASE can be successfully used to select the most-informative samples for training/fine-tuning. Crucially, only information that is readily available in any VQA dataset is used to compute its scores.

Generating images from textual descriptions has recently attracted a lot of interest. While current models can generate photo-realistic images of individual objects such as birds and human faces, synthesising images with multiple objects is still very difficult. In this paper, we propose an effective way to combine Text-to-Image (T2I) synthesis with Visual Question Answering (VQA) to improve the image quality and image-text alignment of generated images by leveraging the VQA 2.0 dataset. We create additional training samples by concatenating question and answer (QA) pairs and employ a standard VQA model to provide the T2I model with an auxiliary learning signal. We encourage images generated from QA pairs to look realistic and additionally minimize an external VQA loss. Our method lowers the FID from 27.84 to 25.38 and increases the R-prec. from 83.82% to 84.79% when compared to the baseline, which indicates that T2I synthesis can successfully be improved using a standard VQA model.

Rephrasings or paraphrases are sentences with similar meanings expressed in different ways. Visual Question Answering (VQA) models are closing the gap with the oracle performance for datasets like VQA2.0. However, these models fail to perform well on rephrasings of a question, which raises some important questions like Are these models robust towards linguistic variations? Is it the architecture or the dataset that we need to optimize? In this paper, we analyzed VQA models in the space of paraphrasing. We explored the role of language & cross-modal pre-training to investigate the robustness of VQA models towards lexical variations. Our experiments find that pre-trained language encoders generate efficient representations of question rephrasings, which help VQA models correctly infer these samples. We empirically determine why pre-training language encoders improve lexical robustness. Finally, we observe that although pre-training all VQA components obtain state-of-the-art results on the VQA-Rephrasings dataset, it still fails to completely close the performance gap between original and rephrasing validation splits.

Recent progress through advanced neural models pushed the performance of task-oriented dialog systems to almost perfect accuracy on existing benchmark datasets for intent classification and slot labeling. However, in evolving real-world dialog systems, where new functionality is regularly added, a major additional challenge is the lack of annotated training data for such new functionality, as the necessary data collection efforts are laborious and time-consuming. A potential solution to reduce the effort is to augment initial seed data by paraphrasing existing utterances automatically. In this paper, we propose a new, data-efficient approach following this idea. Using an interpretation-to-text model for paraphrase generation, we are able to rely on existing dialog system training data, and, in combination with shuffling-based sampling techniques, we can obtain diverse and novel paraphrases from small amounts of seed data. In experiments on a public dataset and with a real-world dialog system, we observe improvements for both intent classification and slot labeling, demonstrating the usefulness of our approach.