Education

  • Ph.D. 2019-2023

    Computer Science and Engineering (NLP)

    Michigan State University (USA)

    GPA: 4

    Research Assistant: Spatial Language Understanding and extraction, Spatial Reasoning, Symbolic Reasoning, Question Answering, Pretrained Language Models, Transfer Learning, Large Language Models.

    Teacher Assistant: Data structure and Algorithm, Introduction to Python

  • M.Sc. 2016-2018

    Computer Engineering, Algorithms & Computation

    Tehran University (Iran)

    GPA: 4

    A Case-based Reasoning Approach for recommender system of interior design: Improve CBR by compositional adaptation and fuzzy ontology on semantics relationships of objects to recommend interior design sets.

  • B.Sc.2012-2016

    Computer Science

    Amirkabir University Of Technology (Iran)

    GPA: 3.7

Work and Internship Experience

(click for details)
  • 2019-2023
    Research Assistant/Teaching Assistant
    Michigan State University

    Research Assistant: Spatial Language Understanding and extraction, Spatial Reasoning, Symbolic Reasoning, Question Answering, Pretrained Language Models, Transfer Learning, Large Language Models.

    Teacher Assistant: Data structure and Algorithm, Introduction to Python


    East Lanisng, MI
  • Summer 2022
    Applied scientist Intern
    Qualtrics-XM

    Improve the generalizability of models considering the result of interpretation

    Method and Metrics for Models Interpretation: Define a saliency score to check the influence of highlighted keywords extracted by saliency map methods (Using AllenAI packages for interpretation .)


    Seattle, WA
  • Summer 2021
    Applied scientist Intern
    Robert Bosch LLC - CR/RS1-NA

    Augmenting Language Models with Spatial CommonSense Through Synthetic Question Answering


    Pittsburgh, PA
  • 2016 - 2019
    Project Manager - Teacher (Web Design)
    Vestaak

    Developing Front-end of web-pages.

    Teaching web development in Vestacamp.


    Tehran , Iran

Contact Information and Links

Disentangling Extraction and Reasoning in Multi-hop Spatial Reasoning

Authors: Roshanak Mirzaee, Parisa Kordjamshidi
2023EMNLP-Findings

Abstract

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 relations. Recent studies highlight the struggles even large-scale language models encounter when it comes to performing spatial reasoning over text. In this paper, we explore the potential benefits of disentangling the processes of information extraction and reasoning to address this challenge. We design various models that disentangle extraction and reasoning~(either symbolic or neural) and compare them with pretrained language model baselines which have state-of-the-art results. Our experimental results consistently demonstrate the efficacy of disentangling, showcasing its ability to enhance models' generalizability within realistic data domains.

Dual-Phase Models for Extracting Information and Symbolic Reasoning: A Case-Study in Spatial Reasoning

Authors: Roshanak Mirzaee, Parisa Kordjamshidi
2023IJCAI-STRL, ICML-KLR workshops

Abstract

Spatial reasoning over text is challenging as the models need to extract the direct spatial information from the text, reason over those, and infer implicit spatial relations. Recent studies highlight the struggles even large-scale language models encounter when it comes to performing spatial reasoning over text. In this paper, we explore the potential benefits of disentangling the processes of information extraction and reasoning in models to address this challenge. To explore this, we devise various models that disentangle extraction and reasoning (either symbolic or neural) and compare them with SOTA baselines with no explicit design for these parts. Our experimental results consistently demonstrate the efficacy of disentangling, showcasing its ability to enhance models’ generalizability within realistic data domains.

Gluecons: A generic benchmark for learning under constraints

Authors: Hossein Rajaby Faghihi, Aliakbar Nafar, Chen Zheng, Roshanak Mirzaee, Yue Zhang, Andrzej Uszok, Alexander Wan, Tanawan Premsri, Dan Roth, Parisa Kordjamshidi
2023AAAI

Abstract

Recent research has shown that integrating domain knowledge into deep learning architectures is effective -- it helps reduce the amount of required data, improves the accuracy of the models' decisions, and improves the interpretability of models. However, the research community is missing a convened benchmark for systematically evaluating knowledge integration methods. In this work, we create a benchmark that is a collection of nine tasks in the domains of natural language processing and computer vision. In all cases, we model external knowledge as constraints, specify the sources of the constraints for each task, and implement various models that use these constraints. We report the results of these models using a new set of extended evaluation criteria in addition to the task performances for a more in-depth analysis. This effort provides a framework for a more comprehensive and systematic comparison of constraint integration techniques and for identifying related research challenges. It will facilitate further research for alleviating some problems of state-of-the-art neural models.

Transfer Learning with Synthetic Corpora for Spatial Role Labeling and Reasoning

Authors: Roshanak Mirzaee, Parisa Kordjamshidi
2022EMNLP

Abstract

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 explored for spatial language. We provide two new data resources on multiple spatial language processing tasks. The first dataset is synthesized for transfer learning on spatial question answering (SQA) and spatial role labeling (SpRL). Compared to previous SQA datasets, we include a larger variety of spatial relation types and spatial expressions. Our data generation process is easily extendable with new spatial expression lexicons. The second one is a real-world SQA dataset with human-generated questions built on an existing corpus with SPRL annotations. This dataset can be used to evaluate spatial language processing models in realistic situations. We show pretraining with automatically generated data significantly improves the SOTA results on several SQA and SPRL benchmarks, particularly when the training data in the target domain is small.

Generalizable Neuro-Symbolic Systems for Commonsense Question Answering

Authors: Alessandro Oltramari, Jonathan Francis, Filip Ilievski, Kaixin Ma, Roshanak Mirzaee
2021IOS Press

Abstract

In this chapter, we provide a retrospective analysis of our recent work, wherein we develop methods for integrating neural language models and knowledge graphs. We characterize the situations in which this combination is most appropriate, and we offer quantitative and qualitative evaluation of these neuro-symbolic modeling strategies on a variety of commonsense question answering benchmark datasets. Our overarching goal is to illustrate how suitable combinations of learning mechanisms and knowledge can enable domain generalizability and robustness in downstream tasks. The chapter is structured as follows: section 13.2 describes some limitations observed when state-of-the-art language models are used in commonsense question answering tasks; in section 13.3 we discuss the main findings of our empirical investigations in discriminative tasks, focused on knowledge-injection and pre-training/fine-tuning methods (13.3. 3-13.3. 4), and we present novel ideas about improving reasoning capabilities of neuro-symbolic systems, laying down the path towards generalizability (13.3. 5).

SpartQA: A Textual Question Answering Benchmark for Spatial Reasoning

Authors: Roshanak Mirzaee, Hossein Rajaby Faghihi, Qiang Ning, Parisa Kordjmashidi
2020SpLU-EMNLP Workshop(non-archival)
2021NAACL

Abstract

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 is challenging for state-of-the-art language models (LM). We propose a distant supervision method to improve on this task. Specifically, we design grammar and reasoning rules to automatically generate a spatial description of visual scenes and corresponding QA pairs. Experiments show that further pretraining LMs on these automatically generated data significantly improves LMs' capability on spatial understanding, which in turn helps to better solve two external datasets, bAbI, and boolQ. We hope that this work can foster investigations into more sophisticated models for spatial reasoning over text.

The Best Poster of Michigan AI Symposium 2020. Best poster award Grad symposium MSU 2022

Latent Alignment of Procedural Concepts in Multimodal Recipes

Authors: Hossein Rajaby Faghihi, Roshanak Mirzaee, Sudarshan Paliwal, Parisa Kordjamshidi
2020ACL-ALVR Workshop

Abstract

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 which is a reading comprehension on a recipe containing images and instructions. We exploit the power of attention networks, cross-modal representations, and a latent alignment space between instructions and candidate answers to solve the problem. We introduce constrained max-pooling which refines the max-pooling operation on the alignment matrix to impose disjoint constraints among the outputs of the model. Our evaluation result indicates a 19\% improvement over the baselines.

Academic Projects

Filter by type:

Sort by year:

Probablistic Reasoning With Large Language Models

2023
Large Language Models Logical Programming probabilistic Programming Infromation Extraction Transfer Learning NLP Transformers
Pytorch HuggingFace OpenAI

Using probabilistic logical programming to solve the spatial logical reasoning and spatial commonsense reasoning in Large Language Models.

Spatial Reasoning in Large Language Models and Evaluation Methods

2023 Part of: Disentangling Extraction and Reasoning in Multi-hop Spatial Reasoning (EMNLP-Findings)
Large Language Models Logical Programming Infromation Extraction Transfer Learning NLP Transformers
Pytorch HuggingFace OpenAI

Evaluate LLMs such as GPT3.5, GPT4 and PaLM2 on Spatial reasoning. Providing A disentangled approach to use LLMs as the extraction modules and use symbolic reasoning to do the reasoning steps.

Spatial relation extraction

2023 Part of : Disentangling Extraction and Reasoning in Multi-hop Spatial Reasoning (EMNLP-Findings)
Logical Programming Infromation Extraction Coreference resolution Transfer Learning NLP Language Models Transformers Pytorch HuggingFace

Propose a model to extract implicit and explicit spatial relations between entities.

Pipeline model to do multi-hop spatial reasoning

2022 Part of: Disentangling Extraction and Reasoning in Multi-hop Spatial Reasoning (EMNLP-Findings)
Logical Programming Infromation Extraction Coreference resolution Transfer Learning NLP Language Models Transformers Pytorch HuggingFace

Propose a model including spatial information extraction and spatial reasoner modules for spatial question answering.

Implement coreference resolution model including plural antecedents.

Method and Metrics for Models Interpretation

2022 Internship
Automatically Data Generation LMs interpretability NLP Transfer Learning Language Models Transformers Pytorch HuggingFace AllenNLP

Define a saliency score to check the influence of highlighted keywords extracted by saliency map methods (Use AllenAI packages for interpretation .)

Transfer Learning on Spatial Tasks

2022 Part of: Transfer Learning with Synthetic Corpora for Spatial Role Labeling and Reasoning (EMNLP)
Automatically Data Generation Logical Programming Transfer Learning NLP Language Models Transformers Pytorch HuggingFace

Propose a method to generate data with broad coverage of expressions and relations to enhance the generalizability of transfer learning method.

Symbolic Spatial Reasoner

2022 Part of: Transfer Learning with Synthetic Corpora for Spatial Role Labeling and Reasoning (EMNLP)
Logic Programming First order Logic Pyton Prolog

A prolog model for complex spatial reasoning using the combination between spatial rules relations.

Spatial Information Extraction

2021 Part of: Transfer Learning with Synthetic Corpora for Spatial Role Labeling and Reasoning (EMNLP)
Automatically Data Generation Transfer Learning Information Extraction NLP Language Models Transformers Pytorch HuggingFace

Probe language models on spatial information extraction by manipulating and tagging the input text.

Spatial Commonsense Reasoning

Internship 2021 Part of: Chapter: Generalizable Neuro-Symbolic Systems for Commonsense Question Answering (IOS Press)
Automatically Data Generation Transfer Learning NLP Language Models Transformers Pytorch HuggingFace

Augmenting Language Models with Spatial CommonSense Through Synthetic Question Answering

Evaluate and Enhance language models’ spatial reasoning capability

2021 Part of: Paper: SpartQA: A Textual Question Answering Benchmark for Spatial Reasoning (NAACL)
Automatically Dataset Generation Transfer Learning Consistency EValuation of LMs NLP Language Models Transformers
Pytorch HuggingFace

Use Context-free grammar, context-sensitive rules, and spatial rules to generate automatic text and questions. Propose different experiments to evaluate Language models’ spatial reasoning capability using the generated distant supervision in transfer learning.

Find incoherent images in Multi-modal Recipes

2020 Part of: Paper: Latent Alignment of Procedural Concepts in Multimodal Recipes (ACL-VLR Workshop)
Computer Vision NLP Language Models Transformers Pytorch HuggingFace

Use BERT, Bi-LSTM, and attention model to find the image with no related text description.

A Case-based Reasoning Approach for recommender system of interior design in Augmented Reality Platform

2018 - M.Sc. Thesis
Machine Learning Semantic Relations and Similarity Recommender Systems
HTML CSS/Bootstrap JavaScript JQuery PHP

Abstract

We have employed case-based reasoning in a recommender system, which proposes optimal interior design solutions for a scanned environment. Specifically, semantic relations were utilized for superior case (information) retrieval, and compositional adaptation was employed to generate the most appropriate recommendations. When an issue arises, the system identifies analogous cases based on the semantic similarity between previously utilized objects and recommends objects that fulfill user requirements. Additionally, machine learning techniques were integrated to enhance the overall process, which facilitate the system's learning and improvement subsequent to each problem-solving instance.

Classification of recognized patterns in Neural Networks

2017 - ML Course Project
Python Deep Learning Neural Network

Description

The project involved digitizing alphabet patterns using a 7x7 matrix and training the system using diverse deep learning techniques. Subsequently, the system's noise tolerance was quantified.

A Framework for Learning and Teaching Mathematics to high school students

2016 - B.Sc. Final Graduation Project
HTML CSS/Bootstrap JavaScript JQuery PHP

Description

The objective was to develop an E-Learning platform that facilitates collaboration between students and teachers in the context of courses and classes. The platform utilizes a crowdsourcing approach for both the generation of teacher questions and the assignment of points among students. Moreover, students are encouraged to persist in problem-solving through continuous feedback.

  • image

    Conference Reviewer (2021-present)

    Reviewing different workshops and conferences

    EMNLP ACL SpLU-RoboNLP (ACL workshop)
  • image

    Internship Projects (2016-2019)

    Describe different projects, which help interns to achieve experience

    Co-worker: Vestaak Corporation

    Having acquired foundational knowledge through courses and seminars, it is imperative to gain practical experience to excel in any field. To this end, we have enhanced our interns' proficiency through hands-on internship projects, providing exposure to real-world challenges and applications.

    Android developer Web developer Digital marketing UI/UX designer Python learning system
  • image

    Seminars in introducing different programming languages (2015)

    Advantage and disadvantages of them and how to start learn them.

    The seminars were organized as part of our CS-Plus Organization. The primary objective was to gather insights from expert programmers in various programming languages, with the intention of providing valuable tips and guidance to freshmen students.


    PHP Android Java Python Matlab Ruby Django Laravel
  • image

    Classes in Programming languages and applications (2015-2019)

    Workshop

    Every programming languages involved in this courses and classes was primarily discussed in syntax and then applications. we aimed to help students learn how to develop their ideas with the presented tools.

    PHP Android Java Python Matlab Ruby Django Laravel
  • image

    Seminar of introducing various occupations in IT Field (2015)

    Short Introduction about each occupation and how to start to be that

    To progress in your learning journey, it's crucial to have a well-defined understanding of the path you've embarked upon. These seminars aimed to introduce each significant job title and provide guidance on how to adequately prepare for those roles.

    Game developer Android developer Web developer Digital marketing Graphist
  • image

    Startup accelator Camp (2015)

    Introduction to DIMOND accelerator and how to start your own startup

    We arranged this camp in order to make students familiar with the concept and life style of startup.