Ana Marasović

Publications
Influence

Don't Stop Pretraining: Adapt Language Models to Domains and Tasks

Suchin Gururangan, Ana Marasović, +4 authors Noah A. Smith
Computer Science
ACL
23 April 2020

We present a study across four domains (biomedical and computer science publications, news, and reviews) and eight classification tasks, showing that a second phase of pretraining in-domain (domain-adaptive pretraining) leads to performance gains, under both high- and low-resource settings. Expand

Quoref: A Reading Comprehension Dataset with Questions Requiring Coreferential Reasoning

Pradeep Dasigi, Nelson F. Liu, Ana Marasović, Noah A. Smith, Matt Gardner
Computer Science
EMNLP/IJCNLP
2019

We present 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. Expand

A Mention-Ranking Model for Abstract Anaphora Resolution

Ana Marasović, Leo Born, J. Opitz, A. Frank
Computer Science, Mathematics
EMNLP
7 June 2017

We propose a mention-ranking model that learns how abstract anaphors relate to their antecedents with an LSTM-Siamese Net. Expand

SRL4ORL: Improving Opinion Role Labelling using Multi-task Learning with Semantic Role Labeling

Ana Marasović, A. Frank
Computer Science
NAACL-HLT
2 November 2017

We investigate the limitations of neural models in solving the fine-grained opinion analysis on MPQA and address this issue using different multi-task learning techniques. Expand

Explaining NLP Models via Minimal Contrastive Editing (MiCE)

Alexis Ross, Ana Marasović, Matthew E. Peters
Computer Science
ArXiv
27 December 2020

We present MINIMAL CONTRASTIVE EDITING (MICE), a method for generating contrastive explanations of model predictions in the form of edits to inputs that change model outputs to the contrast case. Expand

Multilingual Modal Sense Classification using a Convolutional Neural Network

Ana Marasović, A. Frank
Computer Science
Rep4NLP@ACL
1 August 2016

We explore a CNN architecture for classifying modal sense in English and German. Expand

Modal Sense Classification At Large: Paraphrase-Driven Sense Projection, Semantically Enriched Classification Models and Cross-Genre Evaluations

Ana Marasović, Mengfei Zou, Alexis Palmer, A. Frank
Computer Science
LILT
2 September 2016

We build a semantically enriched model for modal sense classification by designing novel features related to lexical, proposition-level and discourse-level semantic factors. Expand

Measuring Association Between Labels and Free-Text Rationales

Sarah Wiegreffe, Ana Marasović, Noah A. Smith
Computer Science
ArXiv
24 October 2020

We propose measurements of label-rationale association, a necessary property of faithful rationales, for self-rationalizing models that provide free-text natural language rationales. Expand

Natural Language Rationales with Full-Stack Visual Reasoning: From Pixels to Semantic Frames to Commonsense Graphs

Ana Marasović, Chandra Bhagavatula, J. Park, Ronan Le Bras, N. A. Smith, Yejin Choi
Computer Science
EMNLP
15 October 2020

We present Rationale^VT 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. Expand

Easy, Reproducible and Quality-Controlled Data Collection with Crowdaq

Qiang Ning, Hao Wu, +5 authors Z. Nie
Computer Science
EMNLP
1 October 2020

We introduce CROWDAQ, an open-source platform that standardizes the data collection pipeline with customizable user-interface components, automated annotator qualification, and saved pipelines in a re-usable format. Expand

Recommended Authors