Related papers: Domain Knowledge Empowered Structured Neural Net f…
Extracting relations is critical for knowledge base completion and construction in which distant supervised methods are widely used to extract relational facts automatically with the existing knowledge bases. However, the automatically…
Structured information resulting from temporal information processing is crucial for a variety of natural language processing tasks, for instance to generate timeline summarization of events from news documents, or to answer…
The meaning of a word often varies depending on its usage in different domains. The standard word embedding models struggle to represent this variation, as they learn a single global representation for a word. We propose a method to learn…
Event Extraction bridges the gap between text and event signals. Based on the assumption of trigger-argument dependency, existing approaches have achieved state-of-the-art performance with expert-designed templates or complicated decoding…
Topic discovery has witnessed a significant growth as a field of data mining at large. In particular, time-evolving topic discovery, where the evolution of a topic is taken into account has been instrumental in understanding the historical…
In document-level relation extraction, entities may appear multiple times in a document, and their relationships can shift from one context to another. Accurate prediction of the relationship between two entities across an entire document…
Prior work on cross-lingual dependency parsing often focuses on capturing the commonalities between source and target languages and overlooks the potential of leveraging linguistic properties of the languages to facilitate the transfer. In…
Named entity recognition (NER) for identifying proper nouns in unstructured text is one of the most important and fundamental tasks in natural language processing. However, despite the widespread use of NER models, they still require a…
There is significant need for principled uncertainty reasoning in machine learning systems as they are increasingly deployed in safety-critical domains. A new approach with uncertainty-aware neural networks (NNs), based on learning…
Structured prediction energy networks (SPENs; Belanger & McCallum 2016) use neural network architectures to define energy functions that can capture arbitrary dependencies among parts of structured outputs. Prior work used gradient descent…
Recent neural network-driven semantic role labeling (SRL) systems have shown impressive improvements in F1 scores. These improvements are due to expressive input representations, which, at least at the surface, are orthogonal to…
Mappings to structured output spaces (strings, trees, partitions, etc.) are typically learned using extensions of classification algorithms to simple graphical structures (eg., linear chains) in which search and parameter estimation can be…
The probing classifiers framework has been employed for interpreting deep neural network models for a variety of natural language processing (NLP) applications. Studies, however, have largely focused on sentencelevel NLP tasks. This work is…
Event argument extraction (EAE) aims to identify the arguments of an event and classify the roles that those arguments play. Despite great efforts made in prior work, there remain many challenges: (1) Data scarcity. (2) Capturing the…
Although the spike-trains in neural networks are mainly constrained by the neural dynamics itself, global temporal constraints (refractoriness, time precision, propagation delays, ..) are also to be taken into account. These constraints are…
Deep learning-based methods deliver state-of-the-art performance for solving inverse problems that arise in computational imaging. These methods can be broadly divided into two groups: (1) learn a network to map measurements to the signal…
Recent developments in predictive modeling using marked temporal point processes (MTPP) have enabled an accurate characterization of several real-world applications involving continuous-time event sequences (CTESs). However, the retrieval…
We employ constraints to control the parameter space of deep neural networks throughout training. The use of customized, appropriately designed constraints can reduce the vanishing/exploding gradients problem, improve smoothness of…
Transfer learning has fundamentally changed the landscape of natural language processing (NLP) research. Many existing state-of-the-art models are first pre-trained on a large text corpus and then fine-tuned on downstream tasks. However,…
Recently established equivalences between differential equations and the structure of neural networks enabled some interpretation of training of a neural network as partial-differential-equation (PDE) constrained optimization. We add to the…