Language
Adapting Unsupervised Syntactic Parsing Methodology for Discourse Dependency Parsing
Download Abstract: One of the main bottlenecks in developing discourse dependency parsers is the lack of annotated training data. A potential solution is to utilize abundant unlabeled data by using unsupervised techniques, but there is so far little research in unsupervised discourse dependency parsing. Fortunately, unsupervised syntactic dependency parsing has been studied by decades, which …
Adapting Unsupervised Syntactic Parsing Methodology for Discourse Dependency Parsing Read More »
Robust Transfer Learning with Pretrained Language Models through Adapters
Download Abstract: Transfer learning with large pretrained transformer-based language models like BERT has become a dominating approach for most NLP tasks. Simply fine-tuning those large language models on downstream tasks or combining it with task-specific pretraining is often not robust. In particular, the performance considerably varies as the random seed changes or the number of …
Robust Transfer Learning with Pretrained Language Models through Adapters Read More »
Unsupervised Vision-Language Parsing: Seamlessly Bridging Visual Scene Graphs with Language Structures via Dependency Relationships
Download Abstract: Understanding realistic visual scene images together with language descriptions is a fundamental task towards generic visual understanding. Previous works have shown compelling comprehensive results by building hierarchical structures for visual scenes (e.g., scene graphs) and natural languages (e.g., dependency trees), individually. However, how to construct a joint vision-language (VL) structure has barely been …
SHARP: Search-Based Adversarial Attack for Structured Prediction
Download Abstract: Adversarial attack of structured prediction models faces various challenges such as the difficulty of perturbing discrete words, the sentence quality issue, and the sensitivity of outputs to small perturbations. In this work, we introduce SHARP, a new attack method that formulates the black-box adversarial attack as a search-based optimization problem with a specially …
SHARP: Search-Based Adversarial Attack for Structured Prediction Read More »
Unsupervised Vision-Language Grammar Induction with Shared Structure Modeling
Download Abstract: We introduce a new task, unsupervised vision-language (VL) grammar induction. Given an image-caption pair, the goal is to extract a shared hierarchical structure for both image and language simultaneously. We argue that such structured output, grounded in both modalities, is a clear step towards the high-level understanding of multimodal information. Besides challenges existing …
Unsupervised Vision-Language Grammar Induction with Shared Structure Modeling Read More »