Papers by Ana Marasović

10 papers
Effective Attention Sheds Light On Interpretability (2021.findings-acl)

Copied to clipboard

Challenge: Using a subset of the GLUE tasks and BERT, we compare the two attention matrices and show that their interpretations differ.
Approach: They propose to use visualizing effective attention to interpret a transformer's behavior since it is more pertinent to the model output by design.
Outcome: The proposed method is more relevant to the model output by design than visualizing attention weights.
Documenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled Corpus (2021.emnlp-main)

Copied to clipboard

Challenge: Large text corpora are often introduced with minimal documentation . documenting collection process, composition, intended uses, and other are key for structured, task-specific datasets.
Approach: They propose to document a dataset created by applying filters to a single snapshot of Common Crawl.
Outcome: The proposed dataset shows that blocklist filtering removes text from minority individuals and patents.
Natural Language Rationales with Full-Stack Visual Reasoning: From Pixels to Semantic Frames to Commonsense Graphs (2020.findings-emnlp)

Copied to clipboard

Challenge: Existing models that use natural language rationales provide intuitive, higher-level explanations that are easily understandable by humans.
Approach: They propose a model that generates free-text rationales by combining pretrained language models with object recognition, grounded visual semantic frames, and visual commonsense graphs.
Outcome: The proposed model generates free-text rationales by combining pretrained language models with object recognition, grounded visual semantic frames, and visual commonsense graphs.
Easy, Reproducible and Quality-Controlled Data Collection with CROWDAQ (2020.emnlp-demos)

Copied to clipboard

Challenge: Efficient data collection is important for advancing research and building time-sensitive applications.
Approach: They propose an open-source platform that standardizes the data collection pipeline . it includes customizable user interface components, automated annotator qualification, and saved pipelines .
Outcome: The proposed platform simplifies data annotation significantly on diverse datasets . it can be used by researchers and engineers to improve reproducibility and minimize overhead .
Quoref: A Reading Comprehension Dataset with Questions Requiring Coreferential Reasoning (D19-1)

Copied to clipboard

Challenge: Existing reading comprehension benchmarks do not contain complex coreferential phenomena . obtaining questions focused on such phenomena is difficult because of lexical cues .
Approach: They propose to use a crowdsourced dataset to examine the ability of models to resolve coreference among entities in Wikipedia paragraphs.
Outcome: The proposed model performs significantly worse than humans on the reading comprehension benchmark . paragraphs and other longer texts typically make multiple references to the same entities .
Don’t Stop Pretraining: Adapt Language Models to Domains and Tasks (2020.acl-main)

Copied to clipboard

Challenge: Language models prerained on text from a wide variety of sources form the foundation of today’s NLP.
Approach: They propose to tailor a pretrained model to the domain of a target task by using domain-adaptive pretraining in-domain.
Outcome: The proposed model can be tailored to the domain of a target task and perform well under both high- and low-resource settings.
Promoting Graph Awareness in Linearized Graph-to-Text Generation (2021.findings-acl)

Copied to clipboard

Challenge: Recent applications of pretrained transformers to linearizations of graph inputs yield stateof-the-art results on graph-to-text tasks.
Approach: They propose to use pretrained transformers to encode local graph structures . they find they can improve the quality of models' implicit graph encodings .
Outcome: The proposed models can encode local graph structures and reconstruct corrupted inputs.
Explaining NLP Models via Minimal Contrastive Editing (MiCE) (2021.findings-acl)

Copied to clipboard

Challenge: Cognitive science and philosophy research has shown that human explanations are contrastive . a contrast case plays a key role in modulating what explanations can be given .
Approach: They propose a method for producing contrastive explanations of model predictions . they edit models' outputs to change model outputs, and then edit them to the contrast case .
Outcome: a new method produces contrastive explanations of model predictions in the form of edits . the edits are minimal and fluent, consistent with human contrastive edits.
Measuring Association Between Labels and Free-Text Rationales (2021.emnlp-main)

Copied to clipboard

Challenge: Existing models for extractive rationales do not work as well on reasoning tasks requiring free-text rationale.
Approach: They propose to use pipelines to extract rationales from input words and to use them to explain reasoning tasks.
Outcome: The proposed models exhibit desirable properties for explaining commonsense question-answering and natural language inference, indicating their potential for producing faithful free-text rationales.
SRL4ORL: Improving Opinion Role Labeling Using Multi-Task Learning with Semantic Role Labeling (N18-1)

Copied to clipboard

Challenge: Recent neural approaches do not outperform the state-of-the-art feature-based models for Opinion Role Labeling (ORL).
Approach: They propose to use multi-task learning to improve Opinion Role Labeling by using a related task which has substantially more data.
Outcome: The proposed model outperforms the state-of-the-art model for Opinion Role Labeling (ORL) with more data.

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