Universal transformers
Recurrent neural networks (RNNs) sequentially process data by updating their state with
each new data point, and have long been the de facto choice for sequence modeling tasks …
each new data point, and have long been the de facto choice for sequence modeling tasks …
Reasoning with latent structure refinement for document-level relation extraction
Document-level relation extraction requires integrating information within and across
multiple sentences of a document and capturing complex interactions between inter …
multiple sentences of a document and capturing complex interactions between inter …
What artificial neural networks can tell us about human language acquisition
A Warstadt, SR Bowman - Algebraic structures in natural …, 2022 - taylorfrancis.com
Rapid progress in machine learning for natural language processing has the potential to
transform debates about how humans learn language. However, the learning environments …
transform debates about how humans learn language. However, the learning environments …
Entity structure within and throughout: Modeling mention dependencies for document-level relation extraction
Abstract Entities, as the essential elements in relation extraction tasks, exhibit certain
structure. In this work, we formulate such entity structure as distinctive dependencies …
structure. In this work, we formulate such entity structure as distinctive dependencies …
Hierarchical graph network for multi-hop question answering
In this paper, we present Hierarchical Graph Network (HGN) for multi-hop question
answering. To aggregate clues from scattered texts across multiple paragraphs, a …
answering. To aggregate clues from scattered texts across multiple paragraphs, a …
Question answering by reasoning across documents with graph convolutional networks
Most research in reading comprehension has focused on answering questions based on
individual documents or even single paragraphs. We introduce a neural model which …
individual documents or even single paragraphs. We introduce a neural model which …
Multi-hop reading comprehension through question decomposition and rescoring
Multi-hop Reading Comprehension (RC) requires reasoning and aggregation across
several paragraphs. We propose a system for multi-hop RC that decomposes a …
several paragraphs. We propose a system for multi-hop RC that decomposes a …
Dynamically fused graph network for multi-hop reasoning
Text-based question answering (TBQA) has been studied extensively in recent years. Most
existing approaches focus on finding the answer to a question within a single paragraph …
existing approaches focus on finding the answer to a question within a single paragraph …
A hierarchical multi-task approach for learning embeddings from semantic tasks
Much effort has been devoted to evaluate whether multi-task learning can be leveraged to
learn rich representations that can be used in various Natural Language Processing (NLP) …
learn rich representations that can be used in various Natural Language Processing (NLP) …
Learning which features matter: RoBERTa acquires a preference for linguistic generalizations (eventually)
One reason pretraining on self-supervised linguistic tasks is effective is that it teaches
models features that are helpful for language understanding. However, we want pretrained …
models features that are helpful for language understanding. However, we want pretrained …