Don’t Stop Pretraining: Adapt Language Models to Domains and Tasks
- Suchin Gururangan, Ana Marasović, Noah A. Smith
- Computer ScienceAnnual Meeting of the Association for…
- 23 April 2020
It is consistently found that multi-phase adaptive pretraining offers large gains in task performance, and it is shown that adapting to a task corpus augmented using simple data selection strategies is an effective alternative, especially when resources for domain-adaptive pretraining might be unavailable.
Quoref: A Reading Comprehension Dataset with Questions Requiring Coreferential Reasoning
- Pradeep Dasigi, Nelson F. Liu, Ana Marasović, Noah A. Smith, Matt Gardner
- Computer ScienceConference on Empirical Methods in Natural…
- 2019
This work presents a new crowdsourced dataset containing more than 24K span-selection questions that require resolving coreference among entities in over 4.7K English paragraphs from Wikipedia, and shows that state-of-the-art reading comprehension models perform significantly worse than humans on this benchmark.
Measuring Association Between Labels and Free-Text Rationales
- Sarah Wiegreffe, Ana Marasović, Noah A. Smith
- Computer ScienceConference on Empirical Methods in Natural…
- 24 October 2020
It is demonstrated that *pipelines*, models for faithful rationalization on information-extraction style tasks, do not work as well on “reasoning” tasks requiring free-text rationales, and state-of-the-art T5-based joint models exhibit desirable properties for explaining commonsense question-answering and natural language inference.
Explaining NLP Models via Minimal Contrastive Editing (MiCE)
- Alexis Ross, Ana Marasović, Matthew E. Peters
- Biology, Computer ScienceFindings
- 27 December 2020
It is demonstrated how MICE edits can be used for two use cases in NLP system development—debugging incorrect model outputs and uncovering dataset artifacts—and thereby illustrate that producing contrastive explanations is a promising research direction for model interpretability.
Formalizing Trust in Artificial Intelligence: Prerequisites, Causes and Goals of Human Trust in AI
- Alon Jacovi, Ana Marasović, Tim Miller, Yoav Goldberg
- Computer ScienceConference on Fairness, Accountability and…
- 15 October 2020
This work discusses a model of trust inspired by, but not identical to, interpersonal trust as defined by sociologists, and incorporates a formalization of 'contractual trust', such that trust between a user and an AI model is trust that some implicit or explicit contract will hold.
Natural Language Rationales with Full-Stack Visual Reasoning: From Pixels to Semantic Frames to Commonsense Graphs
- Ana Marasović, Chandra Bhagavatula, J. S. Park, Ronan Le Bras, Noah A. Smith, Yejin Choi
- Computer ScienceFindings
- 15 October 2020
This study presents RationaleˆVT Transformer, an integrated model that learns to generate free-text rationales by combining pretrained language models with object recognition, grounded visual semantic frames, and visual commonsense graphs, and finds that integration of richer semantic and pragmatic visual features improves visual fidelity of rationales.
SRL4ORL: Improving Opinion Role Labeling Using Multi-Task Learning with Semantic Role Labeling
- Ana Marasović, A. Frank
- Computer ScienceNorth American Chapter of the Association for…
- 2 November 2017
It is found that the vanilla MTL model, which makes predictions using only shared ORL and SRL features, performs the best, and two MTL models improve significantly over the single-task model for labeling of both holders and targets, on the development and the test sets.
A Mention-Ranking Model for Abstract Anaphora Resolution
- Ana Marasović, Leo Born, J. Opitz, A. Frank
- Linguistics, Computer ScienceConference on Empirical Methods in Natural…
- 7 June 2017
A mention-ranking model that learns how abstract anaphors relate to their antecedents with an LSTM-Siamese Net is proposed and its model outperforms state-of-the-art results on shell noun resolution and reports first benchmark results on an abstractAnaphora subset of the ARRAU corpus.
Teach Me to Explain: A Review of Datasets for Explainable NLP
- Sarah Wiegreffe, Ana Marasović
- Computer ScienceArXiv
- 2021
This review identifies three predominant classes of explanations (highlights, free-text, and structured), organize the literature on annotating each type, point to what has been learned to date, and give recommendations for collecting EXNLP datasets in the future.
Documenting the English Colossal Clean Crawled Corpus
- Jesse Dodge, Maarten Sap, Matt Gardner
- Computer ScienceArXiv
- 2021
This work provides some of the first documentation of the English Colossal Clean Crawled Corpus (C4), one of the largest corpora of text available, and hosts an indexed version of C4 at https://c4-search.allenai.org/, allowing anyone to search it.
...
...