Related papers: Efficient probabilistic top-down and left-corner p…
The top-down and bottom-up methods are two mainstreams of referring segmentation, while both methods have their own intrinsic weaknesses. Top-down methods are chiefly disturbed by Polar Negative (PN) errors owing to the lack of fine-grained…
We present a self-training approach to unsupervised dependency parsing that reuses existing supervised and unsupervised parsing algorithms. Our approach, called `iterated reranking' (IR), starts with dependency trees generated by an…
Due to its great importance in deep natural language understanding and various down-stream applications, text-level parsing of discourse rhetorical structure (DRS) has been drawing more and more attention in recent years. However, all the…
We present a phenomenon-oriented comparative analysis of the two dominant approaches in task-independent semantic parsing: classic, knowledge-intensive and neural, data-intensive models. To reflect state-of-the-art neural NLP technologies,…
Large Language Models (LLMs) have significantly impacted many facets of natural language processing and information retrieval. Unlike previous encoder-based approaches, the enlarged context window of these generative models allows for…
How to best integrate linguistic and perceptual processing in multi-modal tasks that involve language and vision is an important open problem. In this work, we argue that the common practice of using language in a top-down manner, to direct…
Latent tree learning models represent sentences by composing their words according to an induced parse tree, all based on a downstream task. These models often outperform baselines which use (externally provided) syntax trees to drive the…
Top-down induction of decision trees has been observed to suffer from the inadequate functioning of the pruning phase. In particular, it is known that the size of the resulting tree grows linearly with the sample size, even though the…
We present a system for bottom-up cumulative learning of myriad concepts corresponding to meaningful character strings, and their part-related and prediction edges. The learning is self-supervised in that the concepts discovered are used as…
Top-down visual attention mechanisms have been used extensively in image captioning and visual question answering (VQA) to enable deeper image understanding through fine-grained analysis and even multiple steps of reasoning. In this work,…
Bottom-up layout algorithms for compound graphs are suitable for presenting the microscale view of models and are often used in model-driven engineering. However, they have difficulties at the macroscale where maintaining the overview of…
Parsing sentences into syntax trees can benefit downstream applications in NLP. Transition-based parsers build trees by executing actions in a state transition system. They are computationally efficient, and can leverage machine learning to…
Transformer-based pre-trained language models (PLMs) have dramatically improved the state of the art in NLP across many tasks. This has led to substantial interest in analyzing the syntactic knowledge PLMs learn. Previous approaches to this…
Brain-inspired machine learning is gaining increasing consideration, particularly in computer vision. Several studies investigated the inclusion of top-down feedback connections in convolutional networks; however, it remains unclear how and…
First-order knowledge compilation techniques have proven efficient for lifted inference. They compile a relational probability model into a target circuit on which many inference queries can be answered efficiently. Early methods used data…
Inspired by "predictive coding" - a theory in neuroscience, we develop a bi-directional and dynamic neural network with local recurrent processing, namely predictive coding network (PCN). Unlike feedforward-only convolutional neural…
Link prediction is pervasively employed to uncover the missing links in the snapshots of real-world networks, which are usually obtained from kinds of sampling methods. Contrarily, in the previous literature, in order to evaluate the…
A series of recent papers has used a parsing algorithm due to Shen et al. (2018) to recover phrase-structure trees based on proxies for "syntactic depth." These proxy depths are obtained from the representations learned by recurrent…
Conventional deep networks rely on one-way backpropagation that overlooks reconciling high-level predictions with lower-level representations. We propose \emph{Contextual Feedback Loops} (CFLs), a lightweight mechanism that re-injects…
Conformal prediction (CP) is widely presented as distribution-free predictive inference with finite-sample marginal coverage under exchangeability. We argue that CP is best understood as a rank-calibrated descendant of the…