Thailand

Deep learning algorithms have shown promising results in visual question answering (VQA) tasks, but a more careful look reveals that they often do not understand the rich signal they are being fed with. To understand and better measure the generalization capabilities of VQA systems, we look at their robustness to counterfactually augmented data. Our proposed augmentations are designed to make a focused intervention on a specific property of the question such that the answer changes. Using these augmentations, we propose a new robustness measure, Robustness to Augmented Data (RAD), which measures the consistency of model predictions between original and augmented examples. Through extensive experimentation, we show that RAD, unlike classical accuracy measures, can quantify when state-of-the-art systems are not robust to counterfactuals. We find substantial failure cases which reveal that current VQA systems are still brittle. Finally, we connect between robustness and generalization, demonstrating the predictive power of RAD for performance on unseen augmentations.

IJCNLP-AACL 2021

Are VQA Systems RAD? Measuring Robustness to Augmented Data with Focused Interventions

visual question answering

data augmentation

generalization

robustness

**Welcome to ACL-IJCNLP 2021!**

The great event is jointly organized by the Association for Computational Linguistics (ACL) and Asian Federation of Natural Language Processing (AFNLP). 

As in previous years, the program of the conference includes a poster session, tutorials, workshops and demonstrations in addition to the main conference.


We were able to keep the registration fees similar to those charged for the virtual ACL 2020. The one fee allows attendance at the main conference and any/all tutorials and workshops. These fees would be $125 Regular Early and $175 Regular Late; $50 Student Early and $75 Student Late. Early registration closes at midnight July 11, 2021 (Eastern Daylight Time).

**Reminder:** It is ACL’s policy that at least one author of each accepted paper (including ACL Finding papers) must register for the conference.

**Reminder2:** Underline site will open closer to the event. If you already registered you will receive access detail

Registration is now open

The great event is jointly organized by the Association for Computational Linguistics (ACL) and Asian Federation of Natural Language Processing (AFNLP).

technical paper

Vision-language pre-training (VLP) on large-scale image-text pairs has achieved huge success for the cross-modal downstream tasks. The most existing pre-training methods mainly adopt a two-step training procedure, which firstly employs a pre-trained object detector to extract region-based visual features, then concatenates the image representation and text embedding as the input of Transformer to train. However, these methods face problems of using task-specific visual representation of the specific object detector for generic cross-modal understanding, and the computation inefficiency of two-stage pipeline.

In this paper, we propose the first end-to-end vision-language pre-trained model for both V+L understanding and generation, namely E2E-VLP, where we build a unified Transformer framework to jointly learn visual representation, and semantic alignments between image and text. We incorporate the tasks of object detection and image captioning into pre-training with a unified Transformer encoder-decoder architecture for enhancing visual learning. An extensive set of experiments have been conducted on well-established vision-language downstream tasks to demonstrate the effectiveness of this novel VLP paradigm.

E2E-VLP: End-to-End Vision-Language Pre-training Enhanced by Visual Learning

Despite the achievements of large-scale multimodal pre-training approaches, cross-modal retrieval, e.g., image-text retrieval, remains a challenging task. To bridge the semantic gap between the two modalities, previous studies mainly focus on word-region alignment at the object level, lacking the matching between the linguistic relation among the words and the visual relation among the regions. The neglect of such relation consistency impairs the contextualized representation of image-text pairs and hinders the model performance and the interpretability. In this paper, we first propose a novel metric, Intra-modal Self-attention Distance (ISD), to quantify the relation consistency by measuring the semantic distance between linguistic and visual relations. In response, we present Inter-modal Alignment on Intra-modal Self-attentions (IAIS), a regularized training method to optimize the ISD and calibrate intra-modal self-attentions from the two modalities mutually via inter-modal alignment. The IAIS regularizer boosts the performance of prevailing models on Flickr30k and MS COCO datasets by a considerable margin, which demonstrates the superiority of our approach.

Learning Relation Alignment for Calibrated Cross-modal Retrieval

We present Knowledge Enhanced Multimodal BART (KM-BART), which is a Transformer-based sequence-to-sequence model capable of reasoning about commonsense knowledge from multimodal inputs of images and texts. We adapt the generative BART architecture (Lewis et al., 2020) to a multimodal model with visual and textual inputs. We further develop novel pretraining tasks to improve the model performance on the Visual Commonsense Generation (VCG) task. In particular, our pretraining task of Knowledge-based Commonsense Generation (KCG) boosts model performance on the VCG task by leveraging commonsense knowledge from a large language model pretrained on external commonsense knowledge graphs. To the best of our knowledge, we are the first to propose a dedicated task for improving model performance on the VCG task. Experimental results show that our model reaches state-of-the-art performance on the VCG task (Park et al., 2020) by applying these novel pretraining tasks.

KM-BART: Knowledge Enhanced Multimodal BART for Visual Commonsense Generation

Video paragraph captioning aims to generate a set of coherent sentences to describe a video that contains several events. Most previous methods simplify this task by using ground-truth event segments. In this work, we propose a novel framework by taking this task as a text summarization task. We first generate lots of sentence-level captions focusing on different video clips and then summarize these captions to obtain the final paragraph caption. Our method does not depend on ground-truth event segments. Experiments on two popular datasets ActivityNet Captions and YouCookII demonstrate the advantages of our new framework. On the ActivityNet dataset, our method even outperforms some previous methods using ground-truth event segment labels.

Video Paragraph Captioning as a Text Summarization Task

Structural syntax knowledge has been proven effective for semantic role labeling (SRL), while existing works mostly use only one singleton syntax, such as either syntactic dependency or constituency tree. In this paper, we explore the integration of heterogeneous syntactic representations for SRL. We first consider a TreeLSTM-based integration, collaboratively learning the phrasal boundaries from the constituency and the semantic relations from dependency. We further introduce a label-aware GCN solution for simultaneously modeling the syntactic edges and labels. Experimental results demonstrate that by effectively combining the heterogeneous syntactic representations, our methods yield task improvements on both span-based and dependency-based SRL. Also our system achieves new state-of-the-art SRL performances, meanwhile bringing explainable task improvements.

Better Combine Them Together! Integrating Syntactic Constituency and Dependency Representations for Semantic Role Labeling

Paraphrase generation is an important but challenging natural language generation problem. In this work, we propose a new Identification-then-Aggregation (IA) framework to tackle this task. 
In the identification step, the input tokens are sorted into two groups by a novel Primary/Secondary Identification (PSI) algorithm. In the aggregation step, these groups are separately encoded, before being aggregated by a custom designed decoder, which autoregressively generates the paraphrased sentence. In extensive experiments on two benchmark datasets, we demonstrate that our model outperforms previous studies by a notable margin. We also show that the proposed approach can generate paraphrases in an interpretable and controllable way.

Keep the Primary, Rewrite the Secondary: A Two-Stage Approach for Paraphrase Generation

The performance of state-of-the-art neural rankers can deteriorate substantially when exposed to noisy inputs or applied to a new domain. In this paper, we present a novel method for fine-tuning neural rankers that can significantly improve their robustness to out-of-domain data and query perturbations. Specifically, a contrastive loss that compares data points in the representation space is combined with the standard ranking loss during fine-tuning. We use relevance labels to denote similar/dissimilar pairs, which allows the model to learn the underlying matching semantics across different query-document pairs and leads to improved robustness. In experiments with four passage ranking datasets, the proposed contrastive fine-tuning method obtains improvements on robustness to query reformulations, noise perturbations, and zero-shot transfer for both BERT and BART-based rankers. Additionally, our experiments show that contrastive fine-tuning outperforms data augmentation for robustifying neural rankers.

Contrastive Fine-tuning Improves Robustness for Neural Rankers

Cross-language entity linking grounds mentions written in several languages to a monolingual knowledge base.
We use a simple neural ranking architecture for this task that uses multilingual BERT representations of both the mention and the context as input, so as to explore the ability of a transformer model to perform well on this task.
We find that the multilingual ability of BERT leads to good performance in monolingual and multilingual settings.
Furthermore, we explore zero-shot language transfer and find surprisingly robust performance. 
We conduct several analyses to identify the sources of performance degradation in the zero-shot setting. Results indicate that while multilingual transformer models transfer well between languages, issues remain in disambiguating similar entities unseen in training.

Cross-Lingual Transfer in Zero-Shot Cross-Language Entity Linking

Answering questions about why characters perform certain actions is central to understanding and reasoning about narratives. Despite recent progress in QA, it is not clear if existing models have the ability to answer "why'' questions that may require commonsense knowledge external to the input narrative. In this work, we introduce TellMeWhy, a new crowd-sourced dataset that consists of more than 30k questions and free-form answers concerning why characters in short narratives perform the actions described. For a third of this dataset, the answers are not present within the narrative. Given the limitations of automated evaluation for this task, we also present a systematized human evaluation interface for this dataset. Our evaluation of state-of-the-art models show that they are far below human performance on answering such questions. They are especially worse on questions whose answers are external to the narrative, thus providing a challenge for future QA and narrative understanding research.

TellMeWhy: A Dataset for Answering Why-Questions in Narratives

Much of NLP research has focused on crowdsourced static datasets and the supervised learning paradigm of training once and then evaluating test performance. As argued in de Vries et al. (2020), crowdsourced data has the issues of lack of naturalness and relevance to real-world use cases, while the static dataset paradigm does not allow for a model to learn from its experiences of using language (Silver et al., 2013). In contrast, one might hope for machine learning systems that become more useful as they interact with people. In this work, we build and deploy a role-playing game, whereby human players converse with learning agents situated in an open-domain fantasy world. We show that by training models on the conversations they have with humans in the game the models progressively improve, as measured by automatic metrics and online engagement scores. This learning is shown to be more efficient than crowdsourced data when applied to conversations with real users, as well as being far cheaper to collect.

Are VQA Systems RAD? Measuring Robustness to Augmented Data with Focused Interventions

Downloads

Next from IJCNLP-AACL 2021

E2E-VLP: End-to-End Vision-Language Pre-training Enhanced by Visual Learning

Similar lecture

DuReader_robust: A Chinese Dataset Towards Evaluating Robustness and Generalization of Machine Reading Comprehension in Real-World Applications

Are VQA Systems RAD? Measuring Robustness to Augmented Data with Focused Interventions

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from IJCNLP-AACL 2021

E2E-VLP: End-to-End Vision-Language Pre-training Enhanced by Visual Learning

Similar lecture

DuReader_robust: A Chinese Dataset Towards Evaluating Robustness and Generalization of Machine Reading Comprehension in Real-World Applications

Downloads