Text-to-SQL parsers map natural language questions to programs that are executable over tables to generate answers, and are typically evaluated on large-scale datasets like Spider (Yu et al., 2018).
Standard conversational semantic parsing maps a complete user utterance into an executable program, after which the program is executed to respond to the user.
Collecting data for conversational semantic parsing is a time-consuming and demanding process.
Conversational semantic parsers map user utterances to executable programs given dialogue histories composed of previous utterances, programs, and system responses.
However, in machine learning, models are most often trained to solve the target tasks directly. Inspired by human learning, we propose a novel curriculum learning approach which decomposes challenging tasks into sequences of easier intermediate goals that are used to pre-train a model before tackling the target task.
We describe a span-level supervised attention loss that improves compositional generalization in semantic parsers.
We explore the use of large pretrained language models as few-shot semantic parsers.
Finally, aside from our analysis we also release Re-TACRED, a new completely re-annotated version of the TACRED dataset that can be used to perform reliable evaluation of relation extraction models.
We propose HyperDynamics, a dynamics meta-learning framework that conditions on an agent's interactions with the environment and optionally its visual observations, and generates the parameters of neural dynamics models based on inferred properties of the dynamical system.
We propose HyperDynamics, a framework that conditions on an agent’s interactions with the environment and optionally its visual observations, and generates the parameters of neural dynamics models based on inferred properties of the dynamical system.
Relation extraction (RE) aims to predict a relation between a subject and an object in a sentence, while knowledge graph link prediction (KGLP) aims to predict a set of objects, O, given a subject and a relation from a knowledge graph.
Never-ending learning is a machine learning paradigm that aims to bridge this gap, with the goal of encouraging researchers to design machine learning systems that can learn to perform a wider variety of inter-related tasks in more complex environments.
In this paper, we propose a curriculum learning framework for NMT that reduces training time, reduces the need for specialized heuristics or large batch sizes, and results in overall better performance.
We propose a simple modification to existing neural machine translation (NMT) models that enables using a single universal model to translate between multiple languages while allowing for language specific parameterization, and that can also be used for domain adaptation.
Structured prediction is ubiquitous in applications of machine learning such as knowledge extraction and natural language processing.