Related papers: Joint Learning Templates and Slots for Event Schem…

Event mentions in text correspond to real-world events of varying degrees of granularity. The task of subevent detection aims to resolve this granularity issue, recognizing the membership of multi-granular events in event complexes. Since…

Rational decision-making under uncertainty requires coherent degrees of belief in events. However, event probabilities generated by Large Language Models (LLMs) have been shown to exhibit incoherence, violating the axioms of probability…

Optimization of machine learning models is commonly performed through stochastic gradient updates on randomly ordered training examples. This practice means that sub-epochs comprise of independent random samples of the training data that…

Event detection (ED) is aimed to identify the key trigger words in unstructured text and predict the event types accordingly. Traditional ED models are too data-hungry to accommodate real applications with scarce labeled data. Besides,…

One-shot semantic image segmentation aims to segment the object regions for the novel class with only one annotated image. Recent works adopt the episodic training strategy to mimic the expected situation at testing time. However, these…

We propose a novel probabilistic dimensionality reduction framework that can naturally integrate the generative model and the locality information of data. Based on this framework, we present a new model, which is able to learn a smooth…

Sparse autoencoders (SAEs) are used to decompose neural network activations into human-interpretable features. Typically, features learned by a single SAE are used for downstream applications. However, it has recently been shown that SAEs…

Model ensembling is a technique to combine the predicted distributions of two or more models, often leading to improved robustness and performance. For ensembling in text generation, the next token's probability distribution is derived from…

Object-centric architectures usually apply a differentiable module to the entire feature map to decompose it into sets of entity representations called slots. Some of these methods structurally resemble clustering algorithms, where the…

Word embeddings are effective intermediate representations for capturing semantic regularities between words, when learning the representations of text sequences. We propose to view text classification as a label-word joint embedding…

Intent classification and slot filling are two critical tasks for natural language understanding. Traditionally the two tasks have been deemed to proceed independently. However, more recently, joint models for intent classification and slot…

Automatic extraction of temporal relations between event pairs is an important task for several natural language processing applications such as Question Answering, Information Extraction, and Summarization. Since most existing methods are…

Explainability poses a major challenge to artificial intelligence (AI) techniques. Current studies on explainable AI (XAI) lack the efficiency of extracting global knowledge about the learning task, thus suffer deficiencies such as…

Zero-shot Learners are models capable of predicting unseen classes. In this work, we propose a Zero-shot Learning approach for text categorization. Our method involves training model on a large corpus of sentences to learn the relationship…

We propose a framework for parsing video and text jointly for understanding events and answering user queries. Our framework produces a parse graph that represents the compositional structures of spatial information (objects and scenes),…

In this paper we study the problem of learning multi-step dynamics prediction models (jumpy models) from unlabeled experience and their utility for fast inference of (high-level) plans in downstream tasks. In particular we propose to learn…

Speaker intent detection and semantic slot filling are two critical tasks in spoken language understanding (SLU) for dialogue systems. In this paper, we describe a recurrent neural network (RNN) model that jointly performs intent detection,…

Multimodal foundation models can process several modalities. However, since the space of possible modalities is large and evolving over time, training a model from scratch to encompass all modalities is unfeasible. Moreover, integrating a…

The extraction of modular object-centric representations for downstream tasks is an emerging area of research. Learning grounded representations of objects that are guaranteed to be stable and invariant promises robust performance across…

Long-running, high-impact events such as the Boston Marathon bombing often develop through many stages and involve a large number of entities in their unfolding. Timeline summarization of an event by key sentences eases story digestion, but…