Related papers: Improving Autoregressive Training with Dynamic Ora…
We describe a gradient-based method to discover local error maximizers of a deep neural network (DNN) used for regression, assuming the availability of an "oracle" capable of providing real-valued supervision (a regression target) for…
Distantly Supervised Named Entity Recognition (DS-NER) has attracted attention due to its scalability and ability to automatically generate labeled data. However, distant annotation introduces many mislabeled instances, limiting its…
Learning from demonstration (LfD) techniques seek to enable novice users to teach robots novel tasks in the real world. However, prior work has shown that robot-centric LfD approaches, such as Dataset Aggregation (DAgger), do not perform…
Previous studies have shown that linguistic features of a word such as possession, genitive or other grammatical cases can be employed in word representations of a named entity recognition (NER) tagger to improve the performance for…
Recent advances in deep neural models allow us to build reliable named entity recognition (NER) systems without handcrafting features. However, such methods require large amounts of manually-labeled training data. There have been efforts on…
Natural language generation (NLG) is an essential component of task-oriented dialog systems. Despite the recent success of neural approaches for NLG, they are typically developed in an offline manner for particular domains. To better fit…
Most multi-agent reinforcement learning (MARL) methods are limited in the scale of problems they can handle. With increasing numbers of agents, the number of training iterations required to find the optimal behaviors increases exponentially…
To create models that are robust across a wide range of test inputs, training datasets should include diverse examples that span numerous phenomena. Dynamic adversarial data collection (DADC), where annotators craft examples that challenge…
Interactive Imitation Learning deals with training a novice policy from expert demonstrations in an online fashion. The established DAgger algorithm trains a robust novice policy by alternating between interacting with the environment and…
Existing deep active learning algorithms achieve impressive sampling efficiency on natural language processing tasks. However, they exhibit several weaknesses in practice, including (a) inability to use uncertainty sampling with black-box…
Neural ordinary differential equations (NODEs) -- parametrizations of differential equations using neural networks -- have shown tremendous promise in learning models of unknown continuous-time dynamical systems from data. However, every…
Previous multimodal sentence representation learning methods have achieved impressive performance. However, most approaches focus on aligning images and text at a coarse level, facing two critical challenges:cross-modal misalignment bias…
Deep neural networks trained on demonstrations of human actions give robot the ability to perform self-driving on the road. However, navigation in a pedestrian-rich environment, such as a campus setup, is still challenging---one needs to…
We introduce novel dynamic oracles for training two of the most accurate known shift-reduce algorithms for constituent parsing: the top-down and in-order transition-based parsers. In both cases, the dynamic oracles manage to notably…
Recent advancements in tabular deep learning (DL) have led to substantial performance improvements, surpassing the capabilities of traditional models. With the adoption of techniques from natural language processing (NLP), such as language…
Large language models (LLMs) have shown remarkable reasoning capabilities, yet aligning such abilities to small language models (SLMs) remains a challenge due to distributional mismatches and limited model capacity. Existing reasoning…
Document digitization is essential for the digital transformation of our societies, yet a crucial step in the process, Optical Character Recognition (OCR), is still not perfect. Even commercial OCR systems can produce questionable output…
Model-based offline reinforcement learning (RL) has emerged as a promising approach for recommender systems, enabling effective policy learning by interacting with frozen world models. However, the reward functions in these world models,…
We propose an efficient dynamic oracle for training the 2-Planar transition-based parser, a linear-time parser with over 99% coverage on non-projective syntactic corpora. This novel approach outperforms the static training strategy in the…
With the rise of large language models, neural text summarization has advanced significantly in recent years. However, even state-of-the-art models continue to rely heavily on high-quality human-annotated data for training and evaluation.…