Hossein Rajaby Faghihi


CrisisLTLSum: A Benchmark for Local Crisis Event Timeline Extraction and Summarization
Hossein Rajaby Faghihi | Bashar Alhafni | Ke Zhang | Shihao Ran | Joel Tetreault | Alejandro Jaimes
Findings of the Association for Computational Linguistics: EMNLP 2022

Social media has increasingly played a key role in emergency response: first responders can use public posts to better react to ongoing crisis events and deploy the necessary resources where they are most needed. Timeline extraction and abstractive summarization are critical technical tasks to leverage large numbers of social media posts about events. Unfortunately, there are few datasets for benchmarking technical approaches for those tasks. This paper presents , the largest dataset of local crisis event timelines available to date. contains 1,000 crisis event timelines across four domains: wildfires, local fires, traffic, and storms. We built using a semi-automated cluster-then-refine approach to collect data from the public Twitter stream. Our initial experiments indicate a significant gap between the performance of strong baselines compared to the human performance on both tasks.Our dataset, code, and models are publicly available (https://github.com/CrisisLTLSum/CrisisTimelines).


DomiKnowS: A Library for Integration of Symbolic Domain Knowledge in Deep Learning
Hossein Rajaby Faghihi | Quan Guo | Andrzej Uszok | Aliakbar Nafar | Parisa Kordjamshidi
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing: System Demonstrations

We demonstrate a library for the integration of domain knowledge in deep learning architectures. Using this library, the structure of the data is expressed symbolically via graph declarations and the logical constraints over outputs or latent variables can be seamlessly added to the deep models. The domain knowledge can be defined explicitly, which improves the explainability of the models in addition to their performance and generalizability in the low-data regime. Several approaches for such integration of symbolic and sub-symbolic models have been introduced; however, there is no library to facilitate the programming for such integration in a generic way while various underlying algorithms can be used. Our library aims to simplify programming for such integration in both training and inference phases while separating the knowledge representation from learning algorithms. We showcase various NLP benchmark tasks and beyond. The framework is publicly available at Github(https://github.com/HLR/DomiKnowS).

Time-Stamped Language Model: Teaching Language Models to Understand The Flow of Events
Hossein Rajaby Faghihi | Parisa Kordjamshidi
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Tracking entities throughout a procedure described in a text is challenging due to the dynamic nature of the world described in the process. Firstly, we propose to formulate this task as a question answering problem. This enables us to use pre-trained transformer-based language models on other QA benchmarks by adapting those to the procedural text understanding. Secondly, since the transformer-based language models cannot encode the flow of events by themselves, we propose a Time-Stamped Language Model (TSLM) to encode event information in LMs architecture by introducing the timestamp encoding. Our model evaluated on the Propara dataset shows improvements on the published state-of-the-art results with a 3.1% increase in F1 score. Moreover, our model yields better results on the location prediction task on the NPN-Cooking dataset. This result indicates that our approach is effective for procedural text understanding in general.

SPARTQA: A Textual Question Answering Benchmark for Spatial Reasoning
Roshanak Mirzaee | Hossein Rajaby Faghihi | Qiang Ning | Parisa Kordjamshidi
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

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.


Latent Alignment of Procedural Concepts in Multimodal Recipes
Hossein Rajaby Faghihi | Roshanak Mirzaee | Sudarshan Paliwal | Parisa Kordjamshidi
Proceedings of the First Workshop on Advances in Language and Vision Research

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.