Papers by Parisa Kordjamshidi
Cross-Modality Relevance for Reasoning on Language and Vision (2020.acl-main)
Copied to clipboard
| Challenge: | Existing approaches to learn and reason over language and vision data for downstream tasks such as visual question answering (VQA) and natural language for visual reasoning (NLVR) |
| Approach: | They propose a cross-modality relevance module that is used in an end-to-end framework to learn the relevance representation between components of various input modalities under supervision of a target task. |
| Outcome: | The proposed approach shows competitive performance on two different language and vision tasks using public benchmarks and improves the state-of-the-art published results. |
LOViS: Learning Orientation and Visual Signals for Vision and Language Navigation (2022.coling-1)
Copied to clipboard
| Challenge: | Existing Transformer-based VLN agents entangle orientation and vision information, which limits the learning of each information source. |
| Approach: | They propose to design a navigation agent with explicit Orientation and Vision modules . they use a set of pre-training tasks to feed the modules into the model . |
| Outcome: | The proposed model improves on R2R and R4R datasets and achieves state-of-the-art results. |
Spatial and Temporal Language Understanding: Representation, Reasoning, and Grounding (2024.naacl-tutorials)
Copied to clipboard
| Challenge: | This tutorial provides an overview of cutting edge research on spatial and temporal language understanding. |
| Approach: | This tutorial provides an overview of cutting edge research on spatial and temporal language understanding. |
| Outcome: | This tutorial provides an overview of cutting edge research on spatial and temporal language understanding. |
Vision-and-Language Navigation with Analogical Textual Descriptions in LLMs (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing zero-shot LLM-based Vision-and-Language Navigation agents either encode images as textual scene descriptions, potentially oversimplifying visual details, or process raw image inputs, which can fail to capture abstract semantics required for high-level reasoning. |
| Approach: | They propose to integrate large language models into embodied AI models by incorporating textual descriptions that facilitate analogical reasoning across images from multiple perspectives. |
| Outcome: | The proposed approach improves the agent’s contextual understanding on the R2R dataset, showing that it can make better decisions based on the LLMs. |
Transfer Learning with Synthetic Corpora for Spatial Role Labeling and Reasoning (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing datasets on spatial language processing are either synthetic or at small scale. |
| Approach: | They propose a dataset for transfer learning on spatial question answering and spatial role labeling that includes a larger variety of spatial relation types and spatial expressions. |
| Outcome: | The proposed dataset can be used to evaluate spatial language processing models in real-world situations. |
Dynamic Relevance Graph Network for Knowledge-Aware Question Answering (2022.coling-1)
Copied to clipboard
| Challenge: | Existing approaches to solve commonsense question answering problems often miss some edges between entities, which breaks the reasoning chain. |
| Approach: | They propose a graph neural network architecture that uses relevance as graph edges to establish new edges dynamically for learning node representations in the graph network. |
| Outcome: | The proposed approach shows competitive performance on two QA benchmarks, CommonsenseQA and OpenbookQA, compared to the state-of-the-art published results. |
Representation, Learning and Reasoning on Spatial Language for Downstream NLP Tasks (2020.emnlp-tutorials)
Copied to clipboard
| Challenge: | In this tutorial, we discuss the cutting-edge research results and existing challenges related to spatial language understanding including semantic annotations, existing corpora, symbolic and sub-symbolic representations, qualitative spatial reasoning, spatial common sense, deep and structured learning models. |
| Approach: | This tutorial presents cutting-edge research results and current challenges related to spatial language understanding including semantic annotations, existing corpora, symbolic and sub-symbolic representations, qualitative spatial reasoning, spatial common sense, deep and structured learning models. |
| Outcome: | This paper reviews the cutting-edge research results and current challenges related to spatial language understanding including semantic annotations, existing corpora, symbolic and sub-symbolic representations, qualitative spatial reasoning, spatial common sense, deep and structured learning models. |
SRLGRN: Semantic Role Labeling Graph Reasoning Network (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing models that use context and type-matching heuristics do not provide realistic evaluation of reasoning capabilities. |
| Approach: | They propose a graph reasoning network based on the semantic structure of the sentences to learn cross paragraph reasoning paths and find supporting facts and the answer jointly. |
| Outcome: | The proposed network shows competitive performance on the HotpotQA distractor setting benchmark compared to the state-of-the-art models. |
From Spatial Relations to Spatial Configurations (2020.lrec-1)
Copied to clipboard
| Challenge: | Existing spatial representations are not sufficient for describing complex spatial configurations. |
| Approach: | They propose to integrate existing spatial representation languages with an annotation schema to extend the capabilities of existing ones. |
| Outcome: | The proposed language can represent a large set of spatial concepts crucial for reasoning . it integrates with the Abstract Meaning Representation (AMR) annotation schema and annotates text from diverse datasets . |
Learning vs Retrieval: The Role of In-Context Examples in Regression with Large Language Models (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing studies on in-context learning mechanisms are not consistent . current research identifies two main approaches to explain the ICL mechanism . |
| Approach: | They propose a framework for evaluating in-context learning mechanisms by focusing on regression tasks. |
| Outcome: | The proposed framework can solve regression problems and then measure the extent to which the LLM retrieves its internal knowledge versus learning from in-context examples. |
The Role of Semantic Parsing in Understanding Procedural Text (2023.findings-eacl)
Copied to clipboard
| Challenge: | Inferring actions and their impact on entities involved in a procedural text can be challenging in various aspects. |
| Approach: | They propose a symbolic parser and semantic role labeling as two sources of semantic parsing knowledge. |
| Outcome: | The proposed framework integrates semantic parsing knowledge into state-of-the-art neural models and shows that it improves procedural understanding. |
FoREST: Frame of Reference Evaluation in Spatial Reasoning Tasks (2025.emnlp-main)
Copied to clipboard
| Challenge: | Spatial reasoning is a fundamental aspect of human intelligence. |
| Approach: | They propose a framework to assess FoR comprehension in large language models (LLMs) by using the Frame of Reference Evaluation in Spatial Reasoning Tasks benchmark. |
| Outcome: | The proposed method improves overall performance across spatial reasoning tasks. |
Relevant CommonSense Subgraphs for “What if...” Procedural Reasoning (2022.findings-acl)
Copied to clipboard
| Challenge: | Existing knowledge graphs and commonsense are used to learn causal reasoning over procedural text. |
| Approach: | They propose a multi-hop graph reasoning model to efficiently extract a commonsense subgraph with the most relevant information from a large knowledge graph and predict the causal answer by reasoning over the representations obtained from the commonsen subgraph and contextual interactions between the questions and context. |
| Outcome: | The proposed model achieves state-of-the-art on WIQA benchmark and is comparable to previous models. |
Breaking Down and Building Up: Mixture of Skill-Based Vision-and-Language Navigation Agents (2026.acl-long)
Copied to clipboard
| Challenge: | Vision-and-Language Navigation (VLN) is a subfield of embodied AI that integrates natural language understanding, visual perception, and sequential decision-making to allow autonomous agents to navigate and interact within visual environments. |
| Approach: | They propose a modular framework that introduces structured, skill-based reasoning into Transformer-based VLN agents. |
| Outcome: | The proposed framework decomposes navigation into atomic skills handled by a specialized agent. |
Teaching Probabilistic Logical Reasoning to Transformers (2024.findings-eacl)
Copied to clipboard
| Challenge: | Existing approaches to reasoning using transformers are limiting, resulting in inconsistent results in arithmetic and QA benchmarks. |
| Approach: | They propose a novel approach that utilizes probabilistic logical rules as constraints in the fine-tuning phase without relying on them in the inference stage. |
| Outcome: | The proposed approach improves the transformer-based language model’s intrinsic reasoning and makes their probabilistic logical reasoning process more explicit and explainable. |
MetaReVision: Meta-Learning with Retrieval for Visually Grounded Compositional Concept Acquisition (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods to learn compositional concepts from previous experience are based on systematic generalization, productivity and substitutivity. |
| Approach: | They propose a retrieval-enhanced meta-learning model to solve the visually grounded compositional concept learning problem by meta-training retrieved primitive concepts from episodes constructed by the retriever. |
| Outcome: | The proposed model outperforms other baselines and the retrieval module plays an important role in this compositional learning process. |
SPARTQA: A Textual Question Answering Benchmark for Spatial Reasoning (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing studies have focused on the spatial reasoning capabilities of modern language models (LMs) however, there has been limited research into the spatial thinking capabilities of LMs. |
| Approach: | They propose a question-answering (QA) benchmark for spatial reasoning on natural language text which contains more realistic spatial phenomena not covered by prior work. |
| Outcome: | The proposed method significantly improves LMs' ability on spatial understanding, which in turn helps solve two external datasets, bAbI, and boolQ. |
Consistent Joint Decision-Making with Heterogeneous Learning Models (2024.findings-eacl)
Copied to clipboard
| Challenge: | Existing approaches to handle inconsistencies in correlated decisions are insufficient for tasks like hierarchical image classification and text summa-rization. |
| Approach: | They propose a decision-making framework that promotes consistency among decisions made by diverse models while utilizing external knowledge. |
| Outcome: | The proposed framework is superior to baselines on multiple datasets. |
Using Persuasive Writing Strategies to Explain and Detect Health Misinformation (2024.lrec-main)
Copied to clipboard
| Challenge: | Increasing misinformation has led to a decrease in trust in news organizations and a decline in the health and medical industry. |
| Approach: | They propose a novel annotation scheme that incorporates persuasive writing tactics in textual documents to aid the automatic identification of misinformation. |
| Outcome: | The proposed scheme improves accuracy and explainability of misinformation detection models. |
DomiKnowS: A Library for Integration of Symbolic Domain Knowledge in Deep Learning (2021.emnlp-demo)
Copied to clipboard
| Challenge: | Current deep learning architectures are data-hungry with issues mainly in generalizability and explainability. |
| Approach: | They propose a library for the integration of domain knowledge in deep learning architectures . structure of data is expressed symbolically via graph declarations and constraints can be added to deep models . |
| Outcome: | The proposed framework simplifies programming for integration of domain knowledge in deep learning architectures while separating the knowledge representation from learning algorithms. |
Disentangling Extraction and Reasoning in Multi-hop Spatial Reasoning (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Recent studies highlight the struggles even large language models encounter when it comes to performing spatial reasoning over text. |
| Approach: | They propose to disentangle spatial reasoning over text and compare them to state-of-the-art models with no explicit design for these parts. |
| Outcome: | The proposed models show that they can perform spatial reasoning over text and can generalize within real data domains. |
Neuro-symbolic Training for Reasoning over Spatial Language (2025.findings-naacl)
Copied to clipboard
| Challenge: | Spatial reasoning is essential for everyday human tasks and is crucial for robots to interact with their environment in a human-like manner. |
| Approach: | They propose to train language models to adhere to spatial reasoning rules as constraints . this allows them to capture the necessary level of abstraction for spatial reasoning . |
| Outcome: | The proposed technique improves language models in multi-hop spatial reasoning over text . it achieves higher accuracy than other competitive Spatial Question-answering benchmarks . |
Time-Stamped Language Model: Teaching Language Models to Understand The Flow of Events (2021.naacl-main)
Copied to clipboard
| Challenge: | Using transformer-based language models to track entities is challenging due to dynamic nature of the world described in the text. |
| Approach: | They propose to use transformer-based language models to track entities throughout a procedure . they propose to introduce timestamp encoding to encode event information in LMs . |
| Outcome: | The proposed model improves on the state-of-the-art model with a 3.1% increase in F1 score on the Propara dataset and better results on the location prediction task on the NPN-Cooking dataset. |
Visually Guided Spatial Relation Extraction from Text (N18-2)
Copied to clipboard
| Challenge: | Existing studies show that spatial relations can be extracted with a good accuracy, but spatial relation extraction is still challenging. |
| Approach: | They propose to use visual modality to fill the information gap in the text modality and resolve spatial semantic ambiguities. |
| Outcome: | The proposed model fills the information gap in the text modality and resolves spatial semantic ambiguities. |
Explicit Object Relation Alignment for Vision and Language Navigation (2022.acl-srw)
Copied to clipboard
| Challenge: | Existing work on vision and language navigation grounding the landmarks and spatial relations in textual instructions into visual modality is important. |
| Approach: | They propose a neural agent to explicitly align the spatial information in both instruction and visual environment, including landmarks and spatial relationships between the agent and landmarks. |
| Outcome: | The proposed method surpasses the baseline on the R2R dataset and shows that it can explain spatial reasoning and spatial relationships. |
NavHint: Vision and Language Navigation Agent with a Hint Generator (2024.findings-eacl)
Copied to clipboard
| Challenge: | Existing work on vision and language navigation relies on navigation-related losses to establish the connection between vision and modalities, neglecting aspects of helping the navigation agent build a deep understanding of the visual environment. |
| Approach: | They propose to provide indirect supervision to the navigation agent through a hint generator that generates visual descriptions during navigation. |
| Outcome: | The proposed method improves the navigation performance and interpretability of the R2R and R4R datasets. |
VLN-Trans: Translator for the Vision and Language Navigation Agent (2023.acl-long)
Copied to clipboard
| Challenge: | We observe two kinds of instructions that make the grounding in the vision-and-language navigation task quite challenging. |
| Approach: | They propose to use a translator module to convert instructions into easy-to-follow sub-instruction representations at each step. |
| Outcome: | The proposed model is based on a Room2Room (R2R), Room4room (R4R), and Room2room Last (R1R-Last) datasets and achieves state-of-the-art results on multiple benchmarks. |
Learning Language through Grounding (2025.naacl-tutorial)
Copied to clipboard
| Challenge: | This tutorial provides a historical overview of grounding and discusses its use in computational linguistics and in computational language processing. |
| Approach: | They introduce the concept of grounding and discuss future directions and open challenges . they will delve into recent progress in learning lexical semantics, syntax, and complex meanings through various forms of ground. |
| Outcome: | This course will provide an overview of the field of grounding and discuss future directions and challenges related to large language models and scaling. |