A Sensitivity Analysis of (and Practitioners’ Guide to) Convolutional Neural Networks for Sentence Classification
- Ye Zhang, Byron C. Wallace
- Computer ScienceInternational Joint Conference on Natural…
- 13 October 2015
A sensitivity analysis of one-layer CNNs is conducted to explore the effect of architecture components on model performance; the aim is to distinguish between important and comparatively inconsequential design decisions for sentence classification.
ERASER: A Benchmark to Evaluate Rationalized NLP Models
- Jay DeYoung, Sarthak Jain, Byron C. Wallace
- Computer ScienceAnnual Meeting of the Association for…
- 8 November 2019
This work proposes the Evaluating Rationales And Simple English Reasoning (ERASER) a benchmark to advance research on interpretable models in NLP, and proposes several metrics that aim to capture how well the rationales provided by models align with human rationales, and also how faithful these rationales are.
Closing the Gap between Methodologists and End-Users: R as a Computational Back-End
- Byron C. Wallace, I. Dahabreh, T. Trikalinos, J. Lau, Paul Trow, C. Schmid
- Computer Science
- 30 June 2012
This paper presents open-source meta-analysis software that uses R as the underlying statistical engine, and Python for the GUI, and a framework that allows methodologists to implement new methods in R that are then automatically integrated into the GUI for use by end-users, so long as the programmer conforms to the interface.
Attention is not Explanation
- Sarthak Jain, Byron C. Wallace
- Computer ScienceNorth American Chapter of the Association for…
- 26 February 2019
This work performs extensive experiments across a variety of NLP tasks to assess the degree to which attention weights provide meaningful “explanations” for predictions, and finds that they largely do not.
Modelling Context with User Embeddings for Sarcasm Detection in Social Media
- Silvio Amir, Byron C. Wallace, Hao Lyu, Paula Carvalho, Mário J. Silva
- Computer ScienceConference on Computational Natural Language…
- 4 July 2016
This work proposes to automatically learn and then exploit user embeddings, to be used in concert with lexical signals to recognize sarcasm, and shows that the model outperforms a state-of-the-art approach leveraging an extensive set of carefully crafted features.
Semi-automated screening of biomedical citations for systematic reviews
- Byron C. Wallace, T. Trikalinos, J. Lau, C. Brodley, C. Schmid
- Computer ScienceBMC Bioinformatics
- 26 January 2010
A semi-automated citation screening algorithm for systematic reviews has the potential to substantially reduce the number of citations reviewers have to manually screen, without compromising the quality and comprehensiveness of the review.
Learning to Faithfully Rationalize by Construction
- Sarthak Jain, Sarah Wiegreffe, Yuval Pinter, Byron C. Wallace
- Computer ScienceAnnual Meeting of the Association for…
- 30 April 2020
Variations of this simple framework yield predictive performance superior to ‘end-to-end’ approaches, while being more general and easier to train.
A Corpus with Multi-Level Annotations of Patients, Interventions and Outcomes to Support Language Processing for Medical Literature
- Benjamin E. Nye, Junyi Jessy Li, Byron C. Wallace
- Computer ScienceAnnual Meeting of the Association for…
- 11 June 2018
A corpus of 5,000 richly annotated abstracts of medical articles describing clinical randomized controlled trials is presented and a set of challenging NLP tasks that would aid searching of the medical literature and the practice of evidence-based medicine are outlined.
Meta-Analyst: software for meta-analysis of binary, continuous and diagnostic data
- Byron C. Wallace, C. Schmid, J. Lau, T. Trikalinos
- Computer ScienceBMC Medical Research Methodology
- 4 December 2009
A new program for conducting meta-analyses that combines the advantages of existing software for this task is developed and validated, and its numerical precision is verified by comparing its output with that from standard meta-analysis routines in Stata over a large database.
Deploying an interactive machine learning system in an evidence-based practice center: abstrackr
- Byron C. Wallace, Kevin Small, C. Brodley, J. Lau, T. Trikalinos
- Computer ScienceInternational Health Informatics Symposium
- 28 January 2012
The ongoing development of an end-to-end interactive machine learning system at the Tufts Evidence-based Practice Center is described and abstrackr, an online tool for the task of citation screening for systematic reviews is developed, which provides an interface to the machine learning methods.
...
...