Papers by Timothy Miller

9 papers
Depth-bounding is effective: Improvements and evaluation of unsupervised PCFG induction (D18-1)

Copied to clipboard

Challenge: Recent attempts to improve grammar induction systems by bounding complexity of the model have not been compared against unbounded induction models.
Approach: They propose to use a Bayesian induction inducer to limit the search space of the model and then sample trees with or without bounding.
Outcome: The proposed model produces trees more accurately than or competitively with state-of-the-art constituency grammar induction models.
Cross-document coreference: An approach to capturing coreference without context (D19-62)

Copied to clipboard

Challenge: a cross-document coreference annotation schema was developed to extract timelines in the clinical domain.
Approach: They propose a cross-document coreference annotation schema that is governed by schematic rules to create meaningful and consistent cross- document relations.
Outcome: The proposed approach produces an agreement score of 93.77% for identical relations between the two sets of notes.
Hierarchical Annotation for Building A Suite of Clinical Natural Language Processing Tasks: Progress Note Understanding (2022.lrec-1)

Copied to clipboard

Challenge: Existing corpus and annotations focus on textual features and relation prediction, but there are no structured corpus models for clinical diagnostic thinking.
Approach: They propose a hierarchical annotation schema with three stages to address clinical diagnostic thinking.
Outcome: The proposed model is based on a large collection of publicly available daily progress notes.
Summarizing Patients’ Problems from Hospital Progress Notes Using Pre-trained Sequence-to-Sequence Models (2022.coling-1)

Copied to clipboard

Challenge: Problem list summarization requires a model to understand, abstract, and generate clinical documentation.
Approach: They propose a task that summarises patients' main problems from daily progress notes using input from the provider's progress notes during hospitalization.
Outcome: The proposed model outperforms two state-of-the-art seq2seq transformer architectures in summarizing patients' main problems from daily progress notes in the medical information mart for Intensive Care (MIMIC)-III.
When Raw Data Prevails: Are Large Language Model Embeddings Effective in Numerical Data Representation for Medical Machine Learning Applications? (2024.findings-emnlp)

Copied to clipboard

Challenge: Numerical data is pivotal for medical questions and answers, but tabular data is not fully integrated into LLMs.
Approach: They examine the effectiveness of vector representations from last hidden states of LLMs for medical diagnostics and prognostics using electronic health record data.
Outcome: The proposed representations outperform those using raw numerical EHR data in medical diagnostics and prognostics.
Simplified Neural Unsupervised Domain Adaptation (N19-1)

Copied to clipboard

Challenge: Existing unsupervised domain adaptation methods use neural networks to learn representations that are trained to predict the values of subset of important features called “pivot features.”
Approach: They propose to combine the representation learner and task learner to improve on existing neural domain adaptation algorithms by removing heuristically-selected "pivot features" they show competitive performance with a simpler model.
Outcome: The proposed model outperforms existing models by removing heuristically-selected pivot features.
Two-Stage Fine-Tuning for Improved Bias and Variance for Large Pretrained Language Models (2023.acl-long)

Copied to clipboard

Challenge: Recent work challenges the bias-variance trade-off . large pretrained models can have large variance and overfit domain-specific data .
Approach: They propose a bias-variance trade-off that implies learning methods need to balance complexity with data size to minimize under-fitting and over-fit.
Outcome: The proposed method achieves strong results on SuperGLUE and clinical information extraction tasks.
Spotting Spurious Data with Neural Networks (N18-1)

Copied to clipboard

Challenge: Existing methods to identify spurious instances require either annotations generated by each individual annotator or both task-specific and instance-type annotations.
Approach: They propose an approach that discriminates instances based on their "difficulty to learn" they use queueing theory and psychology of learning to improve annotations .
Outcome: The proposed methods outperform state-of-the-art baselines and have a MAP of 0.85 and 0.22 in identifying spurious instances in synthetic and carefully-crowdsourced real-world datasets respectively.
Unsupervised Learning of PCFGs with Normalizing Flow (P19-1)

Copied to clipboard

Challenge: Existing induction models unable to incorporate semantics and morphology into induction . current models lack a robust model for generating morphologically rich sentences .
Approach: They propose a PCFG inducer which uses context embeddings to generalize over rare, morphologically rich forms.
Outcome: The proposed model produces grammars with state-of-the-art accuracy on a variety of languages.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations