Search Results for author:
Found 16 papers, 5 papers with code
Simultaneously Self-Attending to Text and Entities for Knowledge-Informed Text Representations
In this work, we aim at directly learning text representations which leverage structured knowledge about entities mentioned in the text.
Meta-Adapters: Parameter Efficient Few-shot Fine-tuning through Meta-Learning
Meta-Adapters perform competitively with state-of-the-art few-shot learning methods that require full fine-tuning, while only fine-tuning 0. 6% of the parameters.
A Moment in the Sun: Solar Nowcasting from Multispectral Satellite Data using Self-Supervised Learning
Solar energy is now the cheapest form of electricity in history.
Diverse Distributions of Self-Supervised Tasks for Meta-Learning in NLP
Meta-learning considers the problem of learning an efficient learning process that can leverage its past experience to accurately solve new tasks.
Unsupervised Pre-training for Biomedical Question Answering
We explore the suitability of unsupervised representation learning methods on biomedical text -- BioBERT, SciBERT, and BioSentVec -- for biomedical question answering.
Self-Supervised Meta-Learning for Few-Shot Natural Language Classification Tasks
We meta-train a transformer model on this distribution of tasks using a recent meta-learning framework.
Simultaneously Linking Entities and Extracting Relations from Biomedical Text Without Mention-level Supervision
Understanding the meaning of text often involves reasoning about entities and their relationships.
Learning to Few-Shot Learn Across Diverse Natural Language Classification Tasks
LEOPARD is trained with the state-of-the-art transformer architecture and shows better generalization to tasks not seen at all during training, with as few as 4 examples per label.
A2N: Attending to Neighbors for Knowledge Graph Inference
State-of-the-art models for knowledge graph completion aim at learning a fixed embedding representation of entities in a multi-relational graph which can generalize to infer unseen entity relationships at test time.
Marginal Likelihood Training of BiLSTM-CRF for Biomedical Named Entity Recognition from Disjoint Label Sets
This paper presents a method for training a single CRF extractor from multiple datasets with disjoint or partially overlapping sets of entity types.
Emergent Complexity via Multi-Agent Competition
In this paper, we point out that a competitive multi-agent environment trained with self-play can produce behaviors that are far more complex than the environment itself.
Continuous Adaptation via Meta-Learning in Nonstationary and Competitive Environments
Ability to continuously learn and adapt from limited experience in nonstationary environments is an important milestone on the path towards general intelligence.
Low-Rank Hidden State Embeddings for Viterbi Sequence Labeling
In textual information extraction and other sequence labeling tasks it is now common to use recurrent neural networks (such as LSTM) to form rich embedded representations of long-term input co-occurrence patterns.
RelNet: End-to-End Modeling of Entities & Relations
We introduce RelNet: a new model for relational reasoning.
Ask the GRU: Multi-Task Learning for Deep Text Recommendations
In a variety of application domains the content to be recommended to users is associated with text.
A provable SVD-based algorithm for learning topics in dominant admixture corpus
Our aim is to develop a model which makes intuitive and empirically supported assumptions and to design an algorithm with natural, simple components such as SVD, which provably solves the inference problem for the model with bounded $l_1$ error.
