Papers by Izhak Shafran

8 papers
MUX-PLMs: Data Multiplexing for High-throughput Language Models (2023.findings-emnlp)

Copied to clipboard

Challenge: MUX-PLMs are high-throughput pre-trained language models that can be fine-tuned for any downstream task to yield high-performance.
Approach: They propose to train language models with data multiplexing to achieve 2x/5x inference speedup . they use multiplexers to entangle and disentangle inputs to achieve the same performance .
Outcome: MUX-PLMs achieve 2x/5x inference speedup with 1-4 % drop on broad suite of tasks.
Audio De-identification - a New Entity Recognition Task (N19-2)

Copied to clipboard

Challenge: Named Entity Recognition (NER) is an important step in de-identification (de-ID) of medical records, many of which are recorded conversations between a patient and a doctor.
Approach: They propose to use Named Entity Recognition (NER) to detect audio spans with entity mentions in medical records and then use it to evaluate the results.
Outcome: The proposed pipeline is based on a large labeled segment of the Switchboard and Fisher audio datasets and compares it with a benchmark.
Extracting Symptoms and their Status from Clinical Conversations (P19-1)

Copied to clipboard

Challenge: Existing models for extracting symptoms from clinical conversations are inherently difficult.
Approach: They propose two new deep learning models tailored for a new application . they propose a hierarchical span-attribute tagging model and a sequence-to-sequence model .
Outcome: The proposed models perform well under different conditions and are compared to existing models.
Unsupervised Slot Schema Induction for Task-oriented Dialog (2022.naacl-main)

Copied to clipboard

Challenge: Defining task-specific schemas is the first step of building a task-oriented dialog system.
Approach: They propose an unsupervised approach for slot schema induction from unlabeled dialog corpora using in-domain language models and unsupervised parsing structures.
Outcome: The proposed method shows significant performance improvement on multi-domain and SGD datasets.
Knowledge-grounded Dialog State Tracking (2022.findings-emnlp)

Copied to clipboard

Challenge: Structured knowledge is encoded implicitly into model parameters for downstream tasks, making training inefficient.
Approach: They propose to perform dialog state tracking grounded on knowledge encoded externally.
Outcome: The proposed method outperforms baseline models in the few-shot learning setting.
Learning to Infer Entities, Properties and their Relations from Clinical Conversations (D19-1)

Copied to clipboard

Challenge: Existing relation extraction models restrict inferring relations between tokens within a few neighboring sentences to avoid high computational complexity.
Approach: They propose a Span Attribute Tagging (SAT) model to infer clinical entities and their properties using a hierarchical two-stage approach.
Outcome: The proposed model outperforms baseline models in identifying relations between symptoms and properties by about 32% and 50% on medications and their properties.
The Medical Scribe: Corpus Development and Model Performance Analyses (2020.lrec-1)

Copied to clipboard

Challenge: Existing tools to assist in clinical note generation using audio of provider-patient encounters are lacking.
Approach: They develop an annotation scheme to extract relevant clinical concepts from audio of provider-patient encounters and train a state-of-the-art tagging model.
Outcome: The proposed model is more useful than the F-scores reflect and can be used in clinical notes.
AnyTOD: A Programmable Task-Oriented Dialog System (2023.emnlp-main)

Copied to clipboard

Challenge: a neuro-symbolic approach allows zero-shot adaptation to unseen tasks and domains . a neural LM keeps track of events that occur during a conversation and a symbolic program implements dialog policy is executed to recommend actions.
Approach: They propose an end-to-end, zero-shot task-oriented dialog system . it is designed to adapt to unseen tasks or domains without prior training .
Outcome: The proposed system can be programmed to adapt to unseen tasks without training . it reduces data collection and training requirements for enabling new TOD 1 16189 tasks .

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