Search Results for author:
Found 23 papers, 12 papers with code
CaPE: Contrastive Parameter Ensembling for Reducing Hallucination in Abstractive Summarization
Then, we fine-tune a base summarization model, which is trained on all training samples, on the clean (noisy) subset to obtain an \textit{expert} (\textit{anti-expert}) model.
HydraSum: Disentangling Stylistic Features in Text Summarization using Multi-Decoder Models
Summarization systems make numerous "decisions" about summary properties during inference, e. g. degree of copying, specificity and length of outputs, etc.
Goodwill Hunting: Analyzing and Repurposing Off-the-Shelf Named Entity Linking Systems
If not, how easily can such a system be repurposed for their use case?
SummVis: Interactive Visual Analysis of Models, Data, and Evaluation for Text Summarization
Novel neural architectures, training strategies, and the availability of large-scale corpora haven been the driving force behind recent progress in abstractive text summarization.
FastIF: Scalable Influence Functions for Efficient Model Interpretation and Debugging
With the availability of the fast influence functions, we demonstrate their usefulness in four applications.
Profile Prediction: An Alignment-Based Pre-Training Task for Protein Sequence Models
Recent deep-learning approaches to protein prediction have shown that pre-training on unlabeled data can yield useful representations for downstream tasks.
Explaining and Improving Model Behavior with k Nearest Neighbor Representations
Interpretability techniques in NLP have mainly focused on understanding individual predictions using attention visualization or gradient-based saliency maps over tokens.
Explaining Creative Artifacts
Human creativity is often described as the mental process of combining associative elements into a new form, but emerging computational creativity algorithms may not operate in this manner.
ReviewRobot: Explainable Paper Review Generation based on Knowledge Synthesis
To assist human review process, we build a novel ReviewRobot to automatically assign a review score and write comments for multiple categories such as novelty and meaningful comparison.
Universal Natural Language Processing with Limited Annotations: Try Few-shot Textual Entailment as a Start
We demonstrate that this framework enables a pretrained entailment model to work well on new entailment domains in a few-shot setting, and show its effectiveness as a unified solver for several downstream NLP tasks such as question answering and coreference resolution when the end-task annotations are limited.
GeDi: Generative Discriminator Guided Sequence Generation
While large-scale language models (LMs) are able to imitate the distribution of natural language well enough to generate realistic text, it is difficult to control which regions of the distribution they generate.
DART: Open-Domain Structured Data Record to Text Generation
Data-to-Text annotations can be a costly process, especially when dealing with tables which are the major source of structured data and contain nontrivial structures.
BERTology Meets Biology: Interpreting Attention in Protein Language Models
Transformer architectures have proven to learn useful representations for protein classification and generation tasks.
Double-Hard Debias: Tailoring Word Embeddings for Gender Bias Mitigation
Word embeddings derived from human-generated corpora inherit strong gender bias which can be further amplified by downstream models.
ESPRIT: Explaining Solutions to Physical Reasoning Tasks
Our framework learns to generate explanations of how the physical simulation will causally evolve so that an agent or a human can easily reason about a solution using those interpretable descriptions.
ERASER: A Benchmark to Evaluate Rationalized NLP Models
We propose several metrics that aim to capture how well the rationales provided by models align with human rationales, and also how faithful these rationales are (i. e., the degree to which provided rationales influenced the corresponding predictions).
Explain Yourself! Leveraging Language Models for Commonsense Reasoning
Deep learning models perform poorly on tasks that require commonsense reasoning, which often necessitates some form of world-knowledge or reasoning over information not immediately present in the input.
Ranked #22 on
Common Sense Reasoning
on CommonsenseQA
Stacking with Auxiliary Features for Visual Question Answering
We propose four categories of auxiliary features for ensembling for VQA.
Stacking With Auxiliary Features for Entity Linking in the Medical Domain
In the medical domain, it is common to link text spans to medical concepts in large, curated knowledge repositories such as the Unified Medical Language System.
Stacking With Auxiliary Features
Ensembling methods are well known for improving prediction accuracy.
Supervised and Unsupervised Ensembling for Knowledge Base Population
We present results on combining supervised and unsupervised methods to ensemble multiple systems for two popular Knowledge Base Population (KBP) tasks, Cold Start Slot Filling (CSSF) and Tri-lingual Entity Discovery and Linking (TEDL).
