activity
20212023
most citedGeneralizable Neuro-symbolic Systems for Commonsense Question Answering

6 citations · 10 across the 6 of their papers we have counts for

collaborators
Showing cs.CLShow all

5 papers · 1 filter

cs.CL2023

Disentangling Extraction and Reasoning in Multi-hop Spatial Reasoning

Roshanak Mirzaee, Parisa Kordjamshidi

Spatial reasoning over text is challenging as the models not only need to extract the direct spatial information from the text but also reason over those and infer implicit spatial…

cs.CL2022

Transfer Learning with Synthetic Corpora for Spatial Role Labeling and Reasoning

Roshanak Mirzaee, Parisa Kordjamshidi

Recent research shows synthetic data as a source of supervision helps pretrained language models (PLM) transfer learning to new target tasks/domains. However, this idea is less exp…

cs.CL2022★ 6 cited

Generalizable Neuro-symbolic Systems for Commonsense Question Answering

Alessandro Oltramari, Jonathan Francis, Filip Ilievski +2

This chapter illustrates how suitable neuro-symbolic models for language understanding can enable domain generalizability and robustness in downstream tasks. Different methods for…

cs.CL2021★ 1 cited

SpartQA: : A Textual Question Answering Benchmark for Spatial Reasoning

Roshanak Mirzaee, Hossein Rajaby Faghihi, Qiang Ning +1

This paper proposes a question-answering (QA) benchmark for spatial reasoning on natural language text which contains more realistic spatial phenomena not covered by prior work and…

cs.CL2021★ 2 cited

Latent Alignment of Procedural Concepts in Multimodal Recipes

Hossein Rajaby Faghihi, Roshanak Mirzaee, Sudarshan Paliwal +1

We propose a novel alignment mechanism to deal with procedural reasoning on a newly released multimodal QA dataset, named RecipeQA. Our model is solving the textual cloze task whic…