Papers by Byron C. Wallace
Learning to Faithfully Rationalize by Construction (2020.acl-main)
Copied to clipboard
| Challenge: | Neural models dominate NLP but it remains difficult to know why they make specific predictions for sequential text inputs. |
| Approach: | They propose a model to produce faithful rationales for neural text classification by defining independent snippet extraction and prediction modules. |
| Outcome: | The proposed model produces faithful explanations even when the model is complex and complex. |
Explaining Black Box Predictions and Unveiling Data Artifacts through Influence Functions (2020.acl-main)
Copied to clipboard
| Challenge: | Modern deep learning models for NLP are notoriously opaque, and this has motivated efforts to design example-specific approaches to interpret such models. |
| Approach: | They propose to use influence functions to explain models by highlighting important words in input text to provide models with an explanation. |
| Outcome: | The proposed approach is particularly useful for natural language inference, a task in which ‘saliency maps’ may not have clear interpretation. |
Predicting Annotation Difficulty to Improve Task Routing and Model Performance for Biomedical Information Extraction (N19-1)
Copied to clipboard
| Challenge: | Modern NLP systems require high-quality annotations, but experts are expensive and lay annotators may not have the knowledge to provide high- quality annotations. |
| Approach: | They propose to directly model instance difficulty to improve model performance and to route instances to appropriate annotators. |
| Outcome: | The proposed model improves performance on a biomedical information extraction task using expert and lay annotations. |
Learning Disentangled Representations of Texts with Application to Biomedical Abstracts (D18-1)
Copied to clipboard
| Challenge: | a method for learning disentangled representations of texts that encode distinct and complementary aspects is proposed . a classic problem in distributed representation learning is that it is difficult to determine what information individual dimensions encode. |
| Approach: | They propose a method for learning disentangled representations of texts that encode distinct and complementary aspects by a adversarial objective based on the (dis)similarity between triplets of documents with respect to specific aspects. |
| Outcome: | The proposed method can be used to perform aspect-specific retrieval on biomedical abstracts. |
Attention is not Explanation (N19-1)
Copied to clipboard
| Challenge: | Attention mechanisms have seen wide adoption in neural NLP models. |
| Approach: | They perform extensive experiments to assess the degree to which attention weights provide meaningful "explanations" they find that attention weighted inputs are often uncorrelated with gradient-based measures of feature importance . |
| Outcome: | The proposed model is based on a distribution over attended-to input units . the findings show that attention weights are often uncorrelated with features . |
Inferring Which Medical Treatments Work from Reports of Clinical Trials (N19-1)
Copied to clipboard
| Challenge: | Ideally, one would consult all available evidence from relevant clinical trials. however, these results are primarily disseminated in natural language scientific articles. |
| Approach: | They propose a task that involves inferring results from a full-text article describing randomized controlled trials with respect to a given intervention, comparator, and outcome of interest. |
| Outcome: | The proposed task consists of 10,000+ prompts coupled with full-text articles describing randomized controlled trials. |
ERASER: A Benchmark to Evaluate Rationalized NLP Models (2020.acl-main)
Copied to clipboard
Jay DeYoung, Sarthak Jain, Nazneen Fatema Rajani, Eric Lehman, Caiming Xiong, Richard Socher, Byron C. Wallace
| Challenge: | State-of-the-art models in NLP are opaque in terms of how they come to make predictions. |
| Approach: | They propose to release a benchmark to measure the quality of rationales extracted by models and how faithful these rationale are to human annotators. |
| Outcome: | The proposed benchmark will enable researchers to compare models and track progress on interpretable models for NLP. |
Trialstreamer: Mapping and Browsing Medical Evidence in Real-Time (2020.acl-demos)
Copied to clipboard
| Challenge: | Trialstreamer extracts key pieces of information that clinicians need when appraising the literature . the highest-quality evidence to inform healthcare practice comes from randomized controlled trials . |
| Approach: | They propose a system that extracts key pieces of information from biomedical abstracts and combines them into a database of clinical trial reports. |
| Outcome: | The proposed system extracts descriptions of trial participants, treatments compared in each arm, and which outcomes were measured. |
How Many and Which Training Points Would Need to be Removed to Flip this Prediction? (2023.eacl-main)
Copied to clipboard
| Challenge: | Existing methods to find St using brute-force are intractable. |
| Approach: | They propose a fast approximation method to find St based on influence functions . they propose to identify a minimum subset of training data that one would need to remove . |
| Outcome: | The proposed method can find St based on influence functions for simple classification models. |
Structured Multi-Label Biomedical Text Tagging via Attentive Neural Tree Decoding (D18-1)
Copied to clipboard
| Challenge: | Existing methods for tagging unstructured texts with arbitrary number of terms drawn from an ontology are lacking. |
| Approach: | They propose a model for tagging unstructured texts with an arbitrary number of terms drawn from an ontology. |
| Outcome: | The proposed model yields state-of-the-art results on the important task of assigning MeSH terms to biomedical abstracts. |
Practical Obstacles to Deploying Active Learning (D19-1)
Copied to clipboard
| Challenge: | Active learning (AL) is a widely-used training strategy for maximizing predictive performance subject to a fixed annotation budget. |
| Approach: | They propose to use active learning to optimize predictive performance . they find that current approaches do not generalize reliably across models and tasks . |
| Outcome: | The proposed approach outperforms training on i.i.d. datasets on supervised learning tasks. |