arXiv subjects

Behrouz Minaei-Bidgoli

Publications and source records attributed to Behrouz Minaei-Bidgoli.

At least 19 recordsLinked to original sources

arXiv2026

XHotpotQA: A Benchmark for Cross-Lingual Knowledge Composition in Multi-Hop Question Answering

Knowledge-intensive multi-hop question answering requires systems to select evidence and compose dependent facts, yet multilingual benchmarks usually translate an entire example into one language. This hides failures at language boundaries inside the reasoning chain. We introduce XHotpotQA, a controlled benchmark for cross-lingual knowledge composition over mixed-language evidence. Each instance is modeled as an evidence-dependency graph whose question, bridge evidence, answer-bearing evidence, and distractors have explicit language assignments. The audited resource contains 15,661 training and 7,405 validation instances, with sentence-level support supervision and supplied distractors. In validation, 99.81% of items cross the question-to-gold-evidence language interface and 95.60% use gold paragraphs in different languages. Across three reader artifacts, full question-evidence mismatch is associated with 10.25 to 15.79 lower Unicode-aware answer F1 than partial alignment, and different-script evidence with deficits of 11.98 to 23.70 points; the corresponding adapted-selector contrasts are 1.71 and 1.78 points. Under this supplied-candidate design, the evaluated readers therefore show substantially larger condition-associated deficits than the selector. XHotpotQA provides role-aware diagnostics, modular evaluation, and an audited test bed for knowledge-based systems that must integrate evidence across languages.

cs.CL↗

arXiv2026

Bactrainus: Optimizing Large Language Models for Multi-hop Complex Question Answering Tasks

Multi-hop question answering requires a system to identify and integrate evidence distributed across documents, yet large language models remain vulnerable to irrelevant context. We investigate this evidence bottleneck in the English HotpotQA distractor setting and introduce Bactrainus, a modular selector-reader framework that separates paragraph selection, supporting-sentence identification, and answer generation. Optional question decomposition and teacher-generated rationale supervision make it possible to test where additional reasoning structure is useful. The evaluation combines foundation-model screening, controlled context and prompting ablations, parameter-efficient adaptation of Llama 3.1 8B Instruct and Llama 3.1 70B Instruct readers, and integrated selector-reader experiments. Supplying the full candidate context instead of gold supporting facts reduces answer token-overlap F1 by 17-21 points, showing that scale alone does not remove context sensitivity. The largest observed differences are associated with reader adaptation and sentence-level evidence control. The strongest reported configuration obtains 89.01 answer F1 and 79.70 joint F1, whereas decomposition and rationale-supervision variants yield smaller, recipe-dependent changes. These findings support auditable, explicitly supervised evidence interfaces for fixed-candidate multi-hop QA and motivate blind, matched, multi-seed evaluation of the remaining small differences.

cs.CL↗

arXiv2025

An $O(n^3)$ time algorithm for the maximum-weight limited-capacity many-to-many matching

Given an undirected bipartite graph $G=(A \cup B, E)$, a many-to-many matching (MM) in $G$ matches each vertex $v$ in $A$ (resp. $B$) to at least one vertex in $B$ (resp. $A$). In this paper, we consider the limited-capacity many-to-many matching (LCMM) in $G$, where each vertex $v\in A\cup B$ is matched to at least one and at most $Cap(v)$ vertices; the function $Cap : A\cup B \rightarrow \mathbb{Z}> 0$ denotes the capacity of $v$ (an upper bound on its degree in the LCMM). We give an $O(n^3)$ time algorithm for finding a maximum (respectively minimum) weight LCMM in $G$ with non-positive real (respectively non-negative real) edge weights, where $\lvert A \rvert+\lvert B \rvert=n$.

cs.DS↗

arXiv2025

Efficient Many-To-Many Matching of Points with Demands in One Dimension

Given two point sets $S$ and $T$, the minimum-cost many-to-many matching with demands (MMD) problem is the problem of finding a minimum-cost many-to-many matching between $S$ and $T$ such that each point of $S$ (respectively $T$) is matched to at least a given number of the points of $T$ (respectively $S$). We propose the first $O\left(n^2\right)$-time algorithm for computing a one dimensional MMD (OMMD) of minimum cost between $S$ and $T$, where $\left|S\right|+\left|T\right|=n$. In an OMMD problem, the input point sets $S$ and $T$ lie on the real line and the cost of matching a point to another point equals the Euclidean distance between the two points. We also study a generalized version of the MMD problem, the many-to-many matching with demands and capacities (MMDC) problem, that in which each point has a limited capacity in addition to a demand. We give the first $O(n^2)$-time algorithm for the minimum-cost one dimensional MMDC (OMMDC) problem.

cs.CG↗

arXiv2025

Rezwan: Leveraging Large Language Models for Comprehensive Hadith Text Processing: A 1.2M Corpus Development

This paper presents the development of Rezwan, a large-scale AI-assisted Hadith corpus comprising over 1.2M narrations, extracted and structured through a fully automated pipeline. Building on digital repositories such as Maktabat Ahl al-Bayt, the pipeline employs Large Language Models (LLMs) for segmentation, chain--text separation, validation, and multi-layer enrichment. Each narration is enhanced with machine translation into twelve languages, intelligent diacritization, abstractive summarization, thematic tagging, and cross-text semantic analysis. This multi-step process transforms raw text into a richly annotated research-ready infrastructure for digital humanities and Islamic studies. A rigorous evaluation was conducted on 1,213 randomly sampled narrations, assessed by six domain experts. Results show near-human accuracy in structured tasks such as chain--text separation (9.33/10) and summarization (9.33/10), while highlighting ongoing challenges in diacritization and semantic similarity detection. Comparative analysis against the manually curated Noor Corpus demonstrates the superiority of Najm in both scale and quality, with a mean overall score of 8.46/10 versus 3.66/10. Furthermore, cost analysis confirms the economic feasibility of the AI approach: tasks requiring over 229,000 hours of expert labor were completed within months at a fraction of the cost. The work introduces a new paradigm in religious text processing by showing how AI can augment human expertise, enabling large-scale, multilingual, and semantically enriched access to Islamic heritage.

cs.CL↗

arXiv2025

Noor-Ghateh: A Benchmark Dataset for Evaluating Arabic Word Segmenters in Hadith Domain

There are numerous complex and rich morphological features in the Arabic language, which are highly useful when analyzing traditional Arabic textbooks, especially in the literary and religious contexts, and help in understanding the meaning of the textbooks. Vocabulary separation means separating the word into different components, such as the root and affixes. In the morphological datasets, the variety of markers and the number of data samples help to evaluate the morphological techniques. In this paper, we present a standard dataset for analyzing the Arabic segmentation tools, which includes approximately 223,690 words from the "Shariat al-Islam" book, labeled by human experts. In terms of volume and word variety, this dataset is superior to the other Hadith Arabic datasets, to the best of our knowledge. To estimate the dataset, we applied different methods, including Farasa, Camel, and ALP, and reported the annotation quality and analyzed the benchmark specifications as well. This be

cs.CL↗

arXiv2024

Approximation Algorithms for the Freeze Tag Problem inside Polygons

The freeze tag problem (FTP) aims to awaken a swarm of robots with one or more initial awake robots as soon as possible. Each awake robot must touch a sleeping robot to wake it up. Once a robot is awakened, it can assist in awakening other sleeping robots. We study this problem inside a polygonal domain and present approximation algorithms for it.

cs.CG↗

arXiv2023

Borhan: A Novel System for Prioritized Default Logic

Prioritized Default Logic presents an optimal solution for addressing real-world problems characterized by incomplete information and the need to establish preferences among diverse scenarios. Although it has reached great success in the theoretical aspect, its practical implementation has received less attention. In this article, we introduce Borhan, a system designed and created for prioritized default logic reasoning. To create an effective system, we have refined existing default logic definitions, including the extension concept, and introduced novel concepts. In addition to its theoretical merits, Borhan proves its practical utility by efficiently addressing a range of prioritized default logic problems. In addition, one of the advantages of our system is its ability to both store and report the explanation path for any inferred triple, enhancing transparency and interpretability. Borhan is offered as an open-source system, implemented in Python, and even offers a simplified Java version as a plugin for the Protege ontology editor. Borhan thus represents a significant step forward in bridging the gap between the theoretical foundations of default logic and its real-world applications.

cs.LO↗

arXiv2023

Emulating the Human Mind: A Neural-symbolic Link Prediction Model with Fast and Slow Reasoning and Filtered Rules

Link prediction is an important task in addressing the incompleteness problem of knowledge graphs (KG). Previous link prediction models suffer from issues related to either performance or explanatory capability. Furthermore, models that are capable of generating explanations, often struggle with erroneous paths or reasoning leading to the correct answer. To address these challenges, we introduce a novel Neural-Symbolic model named FaSt-FLiP (stands for Fast and Slow Thinking with Filtered rules for Link Prediction task), inspired by two distinct aspects of human cognition: "commonsense reasoning" and "thinking, fast and slow." Our objective is to combine a logical and neural model for enhanced link prediction. To tackle the challenge of dealing with incorrect paths or rules generated by the logical model, we propose a semi-supervised method to convert rules into sentences. These sentences are then subjected to assessment and removal of incorrect rules using an NLI (Natural Language Inference) model. Our approach to combining logical and neural models involves first obtaining answers from both the logical and neural models. These answers are subsequently unified using an Inference Engine module, which has been realized through both algorithmic implementation and a novel neural model architecture. To validate the efficacy of our model, we conducted a series of experiments. The results demonstrate the superior performance of our model in both link prediction metrics and the generation of more reliable explanations.

cs.CL↗

arXiv2023

A faster algorithm for the limited-capacity many-to-many point matching in one dimension

Given two sets S and T, a limited-capacity many-to-many matching (LCMM) between S and T matches each element p in S (resp. T) to at least 1 and at most Cap(p) elements in T (resp. S), where the function Cap:S\cup T-> Z>0 denotes the capacity of p. In this paper, we present the first linear time algorithm for finding a minimum-cost one-dimensional LCMM (OLCMM) between S and T, where S and T are points lying on a line, and the cost of matching p in S to q in T equals the l_2 distance between p,q. Our algorithm improves the previous best-known quadratic time algorithm.

cs.CG↗

arXiv2023

Farspredict: A benchmark dataset for link prediction

Link prediction with knowledge graph embedding (KGE) is a popular method for knowledge graph completion. Furthermore, training KGEs on non-English knowledge graph promote knowledge extraction and knowledge graph reasoning in the context of these languages. However, many challenges in non-English KGEs pose to learning a low-dimensional representation of a knowledge graph's entities and relations. This paper proposes "Farspredict" a Persian knowledge graph based on Farsbase (the most comprehensive knowledge graph in Persian). It also explains how the knowledge graph structure affects link prediction accuracy in KGE. To evaluate Farspredict, we implemented the popular models of KGE on it and compared the results with Freebase. Given the analysis results, some optimizations on the knowledge graph are carried out to improve its functionality in the KGE. As a result, a new Persian knowledge graph is achieved. Implementation results in the KGE models on Farspredict outperforming Freebases in many cases. At last, we discuss what improvements could be effective in enhancing the quality of Farspredict and how much it improves.

cs.AI↗

arXiv2022

Evaluating Persian Tokenizers

Tokenization plays a significant role in the process of lexical analysis. Tokens become the input for other natural language processing tasks, like semantic parsing and language modeling. Natural Language Processing in Persian is challenging due to Persian's exceptional cases, such as half-spaces. Thus, it is crucial to have a precise tokenizer for Persian. This article provides a novel work by introducing the most widely used tokenizers for Persian and comparing and evaluating their performance on Persian texts using a simple algorithm with a pre-tagged Persian dependency dataset. After evaluating tokenizers with the F1-Score, the hybrid version of the Farsi Verb and Hazm with bounded morphemes fixing showed the best performance with an F1 score of 98.97%.

cs.CL↗

arXiv2021

KGRefiner: Knowledge Graph Refinement for Improving Accuracy of Translational Link Prediction Methods

The Link Prediction is the task of predicting missing relations between entities of the knowledge graph. Recent work in link prediction has attempted to provide a model for increasing link prediction accuracy by using more layers in neural network architecture. In this paper, we propose a novel method of refining the knowledge graph so that link prediction operation can be performed more accurately using relatively fast translational models. Translational link prediction models, such as TransE, TransH, TransD, have less complexity than deep learning approaches. Our method uses the hierarchy of relationships and entities in the knowledge graph to add the entity information as auxiliary nodes to the graph and connect them to the nodes which contain this information in their hierarchy. Our experiments show that our method can significantly increase the performance of translational link prediction methods in H@10, MR, MRR.

cs.CL↗

arXiv2021

A Sample-Based Training Method for Distantly Supervised Relation Extraction with Pre-Trained Transformers

Multiple instance learning (MIL) has become the standard learning paradigm for distantly supervised relation extraction (DSRE). However, due to relation extraction being performed at bag level, MIL has significant hardware requirements for training when coupled with large sentence encoders such as deep transformer neural networks. In this paper, we propose a novel sampling method for DSRE that relaxes these hardware requirements. In the proposed method, we limit the number of sentences in a batch by randomly sampling sentences from the bags in the batch. However, this comes at the cost of losing valid sentences from bags. To alleviate the issues caused by random sampling, we use an ensemble of trained models for prediction. We demonstrate the effectiveness of our approach by using our proposed learning setting to fine-tuning BERT on the widely NYT dataset. Our approach significantly outperforms previous state-of-the-art methods in terms of AUC and P@N metrics.

cs.CL↗

arXiv2021

Interval Probabilistic Fuzzy WordNet

WordNet lexical-database groups English words into sets of synonyms called "synsets." Synsets are utilized for several applications in the field of text-mining. However, they were also open to criticism because although, in reality, not all the members of a synset represent the meaning of that synset with the same degree, in practice, they are considered as members of the synset, identically. Thus, the fuzzy version of synsets, called fuzzy-synsets (or fuzzy word-sense classes) were proposed and studied. In this study, we discuss why (type-1) fuzzy synsets (T1 F-synsets) do not properly model the membership uncertainty, and propose an upgraded version of fuzzy synsets in which membership degrees of word-senses are represented by intervals, similar to what in Interval Type 2 Fuzzy Sets (IT2 FS) and discuss that IT2 FS theoretical framework is insufficient for analysis and design of such synsets, and propose a new concept, called Interval Probabilistic Fuzzy (IPF) sets. Then we present an algorithm for constructing the IPF synsets in any language, given a corpus and a word-sense-disambiguation system. Utilizing our algorithm and the open-American-online-corpus (OANC) and UKB word-sense-disambiguation, we constructed and published the IPF synsets of WordNet for English language.

cs.CL↗

arXiv2021

An Unsupervised Language-Independent Entity Disambiguation Method and its Evaluation on the English and Persian Languages

Entity Linking is one of the essential tasks of information extraction and natural language understanding. Entity linking mainly consists of two tasks: recognition and disambiguation of named entities. Most studies address these two tasks separately or focus only on one of them. Moreover, most of the state-of-the -art entity linking algorithms are either supervised, which have poor performance in the absence of annotated corpora or language-dependent, which are not appropriate for multi-lingual applications. In this paper, we introduce an Unsupervised Language-Independent Entity Disambiguation (ULIED), which utilizes a novel approach to disambiguate and link named entities. Evaluation of ULIED on different English entity linking datasets as well as the only available Persian dataset illustrates that ULIED in most of the cases outperforms the state-of-the-art unsupervised multi-lingual approaches.

cs.CL↗

arXiv2020

IUST at SemEval-2020 Task 9: Sentiment Analysis for Code-Mixed Social Media Text using Deep Neural Networks and Linear Baselines

Sentiment Analysis is a well-studied field of Natural Language Processing. However, the rapid growth of social media and noisy content within them poses significant challenges in addressing this problem with well-established methods and tools. One of these challenges is code-mixing, which means using different languages to convey thoughts in social media texts. Our group, with the name of IUST(username: TAHA), participated at the SemEval-2020 shared task 9 on Sentiment Analysis for Code-Mixed Social Media Text, and we have attempted to develop a system to predict the sentiment of a given code-mixed tweet. We used different preprocessing techniques and proposed to use different methods that vary from NBSVM to more complicated deep neural network models. Our best performing method obtains an F1 score of 0.751 for the Spanish-English sub-task and 0.706 over the Hindi-English sub-task.

cs.CL↗

arXiv2020

PERLEX: A Bilingual Persian-English Gold Dataset for Relation Extraction

Relation extraction is the task of extracting semantic relations between entities in a sentence. It is an essential part of some natural language processing tasks such as information extraction, knowledge extraction, and knowledge base population. The main motivations of this research stem from a lack of a dataset for relation extraction in the Persian language as well as the necessity of extracting knowledge from the growing big-data in the Persian language for different applications. In this paper, we present "PERLEX" as the first Persian dataset for relation extraction, which is an expert-translated version of the "Semeval-2010-Task-8" dataset. Moreover, this paper addresses Persian relation extraction utilizing state-of-the-art language-agnostic algorithms. We employ six different models for relation extraction on the proposed bilingual dataset, including a non-neural model (as the baseline), three neural models, and two deep learning models fed by multilingual-BERT contextual word representations. The experiments result in the maximum f-score 77.66% (provided by BERTEM-MTB method) as the state-of-the-art of relation extraction in the Persian language.

cs.CL↗