Mehrnoush Shamsfard

Mozhgan Pourkeshavarz, Shahabedin Nabavi, Mohsen Ebrahimi Moghaddam et al.

Recently, the attention-enriched encoder-decoder framework has aroused great interest in image captioning due to its overwhelming progress. Many visual attention models directly leverage meaningful regions to generate image descriptions. However, seeking a direct transition from visual space to text is not enough to generate fine-grained captions. This paper exploits a feature-compounding approach to bring together high-level semantic concepts and visual information regarding the contextual environment fully end-to-end. Thus, we propose a stacked cross-modal feature consolidation (SCFC) attention network for image captioning in which we simultaneously consolidate cross-modal features through a novel compounding function in a multi-step reasoning fashion. Besides, we jointly employ spatial information and context-aware attributes (CAA) as the principal components in our proposed compounding function, where our CAA provides a concise context-sensitive semantic representation. To make better use of consolidated features potential, we further propose an SCFC-LSTM as the caption generator, which can leverage discriminative semantic information through the caption generation process. The experimental results indicate that our proposed SCFC can outperform various state-of-the-art image captioning benchmarks in terms of popular metrics on the MSCOCO and Flickr30K datasets.

Dilara Torunoğlu-Selamet, Dogukan Arslan, Rodrigo Wilkens et al.

Potentially idiomatic expressions (PIEs) construe meanings inherently tied to the everyday experience of a given language community. As such, they constitute an interesting challenge for assessing the linguistic (and to some extent cultural) capabilities of NLP systems. In this paper, we present XMPIE, a parallel multilingual and multimodal dataset of potentially idiomatic expressions. The dataset, containing 34 languages and over ten thousand items, allows comparative analyses of idiomatic patterns among language-specific realisations and preferences in order to gather insights about shared cultural aspects. This parallel dataset allows to evaluate model performance for a given PIE in different languages and whether idiomatic understanding in one language can be transferred to another. Moreover, the dataset supports the study of PIEs across textual and visual modalities, to measure to what extent PIE understanding in one modality transfers or implies in understanding in another modality (text vs. image). The data was created by language experts, with both textual and visual components crafted under multilingual guidelines, and each PIE is accompanied by five images representing a spectrum from idiomatic to literal meanings, including semantically related and random distractors. The result is a high-quality benchmark for evaluating multilingual and multimodal idiomatic language understanding.

Vahide Tajalli, Fateme Kalantari, Mehrnoush Shamsfard

Informal language is a style of spoken or written language frequently used in casual conversations, social media, weblogs, emails and text messages. In informal writing, the language faces some lexical and/or syntactic changes varying among different languages. Persian is one of the languages with many differences between its formal and informal styles of writing, thus developing informal language processing tools for this language seems necessary. Such a converter needs a large aligned parallel corpus of colloquial-formal sentences which can be useful for linguists to extract a regulated grammar and orthography for colloquial Persian as is done for the formal language. In this paper we explain our methodology in building a parallel corpus of 50,000 sentence pairs with alignments in the word/phrase level. The sentences were attempted to cover almost all kinds of lexical and syntactic changes between informal and formal Persian, therefore both methods of exploring and collecting from the different resources of informal scripts and following the phonological and morphological patterns of changes were applied to find as much instances as possible. The resulting corpus has about 530,000 alignments and a dictionary containing 49,397 word and phrase pairs.

Moein Salimi Sartakhti, Romina Etezadi, Mehrnoush Shamsfard

Relation extraction that is the task of predicting semantic relation type between entities in a sentence or document is an important task in natural language processing. Although there are many researches and datasets for English, Persian suffers from sufficient researches and comprehensive datasets. The only available Persian dataset for this task is PERLEX, which is a Persian expert-translated version of the SemEval-2010-Task-8 dataset. In this paper, we present our augmented dataset and the results and findings of our system, participated in the Persian relation Extraction shared task of NSURL 2021 workshop. We use PERLEX as the base dataset and enhance it by applying some text preprocessing steps and by increasing its size via data augmentation techniques to improve the generalization and robustness of applied models. We then employ two different models including ParsBERT and multilingual BERT for relation extraction on the augmented PERLEX dataset. Our best model obtained 64.67% of Macro-F1 on the test phase of the contest and it achieved 83.68% of Macro-F1 on the test set of PERLEX.

Mostafa Masumi, Seyed Soroush Majd, Mehrnoush Shamsfard et al.

We introduce FaBERT, a Persian BERT-base model pre-trained on the HmBlogs corpus, encompassing both informal and formal Persian texts. FaBERT is designed to excel in traditional Natural Language Understanding (NLU) tasks, addressing the intricacies of diverse sentence structures and linguistic styles prevalent in the Persian language. In our comprehensive evaluation of FaBERT on 12 datasets in various downstream tasks, encompassing Sentiment Analysis (SA), Named Entity Recognition (NER), Natural Language Inference (NLI), Question Answering (QA), and Question Paraphrasing (QP), it consistently demonstrated improved performance, all achieved within a compact model size. The findings highlight the importance of utilizing diverse and cleaned corpora, such as HmBlogs, to enhance the performance of language models like BERT in Persian Natural Language Processing (NLP) applications. FaBERT is openly accessible at https://huggingface.co/sbunlp/fabert

Hossein Rouhizadeh, Mehrnoush Shamsfard, Vahideh Tajalli et al.

Word Sense Disambiguation (WSD) is a long-standing task in Natural Language Processing(NLP) that aims to automatically identify the most relevant meaning of the words in a given context. Developing standard WSD test collections can be mentioned as an important prerequisite for developing and evaluating different WSD systems in the language of interest. Although many WSD test collections have been developed for a variety of languages, no standard All-words WSD benchmark is available for Persian. In this paper, we address this shortage for the Persian language by introducing SBU-WSD-Corpus, as the first standard test set for the Persian All-words WSD task. SBU-WSD-Corpus is manually annotated with senses from the Persian WordNet (FarsNet) sense inventory. To this end, three annotators used SAMP (a tool for sense annotation based on FarsNet lexical graph) to perform the annotation task. SBU-WSD-Corpus consists of 19 Persian documents in different domains such as Sports, Science, Arts, etc. It includes 5892 content words of Persian running text and 3371 manually sense annotated words (2073 nouns, 566 verbs, 610 adjectives, and 122 adverbs). Providing baselines for future studies on the Persian All-words WSD task, we evaluate several WSD models on SBU-WSD-Corpus. The corpus is publicly available at https://github.com/hrouhizadeh/SBU-WSD-Corpus.

Mohammad Heydari Rad, Farhan Farsi, Shayan Bali et al.

Nowadays, the usage of Large Language Models (LLMs) has increased, and LLMs have been used to generate texts in different languages and for different tasks. Additionally, due to the participation of remarkable companies such as Google and OpenAI, LLMs are now more accessible, and people can easily use them. However, an important issue is how we can detect AI-generated texts from human-written ones. In this article, we have investigated the problem of AI-generated text detection from two different aspects: semantics and syntax. Finally, we presented an AI model that can distinguish AI-generated texts from human-written ones with high accuracy on both multilingual and monolingual tasks using the M4 dataset. According to our results, using a semantic approach would be more helpful for detection. However, there is a lot of room for improvement in the syntactic approach, and it would be a good approach for future work.

Mehrnoush Shamsfard, Zahra Saaberi, Mostafa Karimi manesh et al.

Research on evaluating and analyzing large language models (LLMs) has been extensive for resource-rich languages such as English, yet their performance in languages such as Persian has received considerably less attention. This paper introduces FarsEval-PKBETS benchmark, a subset of FarsEval project for evaluating large language models in Persian. This benchmark consists of 4000 questions and answers in various formats, including multiple choice, short answer and descriptive responses. It covers a wide range of domains and tasks,including medicine, law, religion, Persian language, encyclopedic knowledge, human preferences, social knowledge, ethics and bias, text generation, and respecting others' rights. This bechmark incorporates linguistics, cultural, and local considerations relevant to the Persian language and Iran. To ensure the questions are challenging for current LLMs, three models -- Llama3-70B, PersianMind, and Dorna -- were evaluated using this benchmark. Their average accuracy was below 50%, meaning they provided fully correct answers to fewer than half of the questions. These results indicate that current language models are still far from being able to solve this benchmark

Parastoo Falakaflaki, Mehrnoush Shamsfard

This study explores the formality style transfer in Persian, particularly relevant in the face of the increasing prevalence of informal language on digital platforms, which poses challenges for existing Natural Language Processing (NLP) tools. The aim is to transform informal text into formal while retaining the original meaning, addressing both lexical and syntactic differences. We introduce a novel model, Fa-BERT2BERT, based on the Fa-BERT architecture, incorporating consistency learning and gradient-based dynamic weighting. This approach improves the model's understanding of syntactic variations, balancing loss components effectively during training. Our evaluation of Fa-BERT2BERT against existing methods employs new metrics designed to accurately measure syntactic and stylistic changes. Results demonstrate our model's superior performance over traditional techniques across various metrics, including BLEU, BERT score, Rouge-l, and proposed metrics underscoring its ability to adeptly navigate the complexities of Persian language style transfer. This study significantly contributes to Persian language processing by enhancing the accuracy and functionality of NLP models and thereby supports the development of more efficient and reliable NLP applications, capable of handling language style transformation effectively, thereby streamlining content moderation, enhancing data mining results, and facilitating cross-cultural communication.

Hamzeh Motahari Khansari, Mehrnoush Shamsfard

This paper introduces the hmBlogs corpus for Persian, as a low resource language. This corpus has been prepared based on a collection of nearly 20 million blog posts over a period of about 15 years from a space of Persian blogs and includes more than 6.8 billion tokens. It can be claimed that this corpus is currently the largest Persian corpus that has been prepared independently for the Persian language. This corpus is presented in both raw and preprocessed forms, and based on the preprocessed corpus some word embedding models are produced. By the provided models, the hmBlogs is compared with some of the most important corpora available in Persian, and the results show the superiority of the hmBlogs corpus over the others. These evaluations also present the importance and effects of corpora, evaluation datasets, model production methods, different hyperparameters and even the evaluation methods. In addition to evaluating the corpus and its produced language models, this research also presents a semantic analogy dataset.

Peyman Alavi, Pouria Nikvand, Mehrnoush Shamsfard

This paper describes a novel study on using `Attention Mask' input in transformers and using this approach for detecting offensive content in both English and Persian languages. The paper's principal focus is to suggest a methodology to enhance the performance of the BERT-based models on the `Offensive Language Detection' task. Therefore, we customize attention probabilities by changing the `Attention Mask' input to create more efficacious word embeddings. To do this, we firstly tokenize the training set of the exploited datasets (by BERT tokenizer). Then, we apply Multinomial Naive Bayes to map these tokens to two probabilities. These probabilities indicate the likelihood of making a text non-offensive or offensive, provided that it contains that token. Afterwards, we use these probabilities to define a new term, namely Offensive Score. Next, we create two separate (because of the differences in the types of the employed datasets) equations based on Offensive Scores for each language to re-distribute the `Attention Mask' input for paying more attention to more offensive phrases. Eventually, we put the F1-macro score as our evaluation metric and fine-tune several combinations of BERT with ANNs, CNNs and RNNs to examine the effect of using this methodology on various combinations. The results indicate that all models will enhance with this methodology. The most improvement was 2% and 10% for English and Persian languages, respectively.

Romina Etezadi, Mehrnoush Shamsfard

Research on open-domain question answering (QA) has a long tradition. A challenge in this domain is answering complex questions (CQA) that require complex inference methods and large amounts of knowledge. In low resource languages, such as Persian, there are not many datasets for open-domain complex questions and also the language processing toolkits are not very accurate. In this paper, we propose a knowledge-based approach for answering Persian complex questions using Farsbase; the Persian knowledge graph, exploiting PeCoQ; the newly created complex Persian question dataset. In this work, we handle multi-constraint and multi-hop questions by building their set of possible corresponding logical forms. Then Multilingual-BERT is used to select the logical form that best describes the input complex question syntactically and semantically. The answer to the question is built from the answer to the logical form, extracted from the knowledge graph. Experiments show that our approach outperforms other approaches in Persian CQA.

Zeinab Rahimi, Mehrnoush ShamsFard

Detection of semantic contradictory sentences is one of the most challenging and fundamental issues for NLP applications such as recognition of textual entailments. Contradiction in this study includes different types of semantic confrontation, such as conflict and antonymy. Due to lack of sufficient data to apply precise machine learning and specifically deep learning methods to Persian and other low resource languages, rule-based approaches that can function similarly to these systems will be of a great interest. Also recently, emergence of new methods such as transfer learning, has opened up the possibility of deep learning for low-resource languages. Considering two above points, in this study, along with a simple rule-base baseline, a novel rule-base system for identifying semantic contradiction along with a Bert base deep contradiction detection system for Persian texts have been introduced. The rule base system has used frequent rule mining method to extract appropriate contradiction rules using a development set. Extracted rules are tested for different categories of contradictory sentences. In this system the maximum f-measure among contradiction categories is obtained for negation about 90% and the average F-measure of system for all classes is about 76% which outperforms other algorithms on Persian texts. On the other hand, because of medium performance of rule base system for some categories of contradiction, we use a Bert base deep learning system using our translated dataset; with average F-measure of 73. Our hybrid system has f-measure of about 80.

Seyyed Ehsan Mahmoudi, Mehrnoush Shamsfard

In recent years there has been a special interest in word embeddings as a new approach to convert words to vectors. It has been a focal point to understand how much of the semantics of the the words has been transferred into embedding vectors. This is important as the embedding is going to be used as the basis for downstream NLP applications and it will be costly to evaluate the application end-to-end in order to identify quality of the used embedding model. Generally the word embeddings are evaluated through a number of tests, including analogy test. In this paper we propose a test framework for Persian embedding models. Persian is a low resource language and there is no rich semantic benchmark to evaluate word embedding models for this language. In this paper we introduce an evaluation framework including a hand crafted Persian SAT based analogy dataset, a colliquial test set (specific to Persian) and a benchmark to study the impact of various parameters on the semantic evaluation task.

Romina Etezadi, Mehrnoush Shamsfard

Question answering systems may find the answers to users' questions from either unstructured texts or structured data such as knowledge graphs. Answering questions using supervised learning approaches including deep learning models need large training datasets. In recent years, some datasets have been presented for the task of Question answering over knowledge graphs, which is the focus of this paper. Although many datasets in English were proposed, there have been a few question-answering datasets in Persian. This paper introduces \textit{PeCoQ}, a dataset for Persian question answering. This dataset contains 10,000 complex questions and answers extracted from the Persian knowledge graph, FarsBase. For each question, the SPARQL query and two paraphrases that were written by linguists are provided as well. There are different types of complexities in the dataset, such as multi-relation, multi-entity, ordinal, and temporal constraints. In this paper, we discuss the dataset's characteristics and describe our methodology for building it.

Zeinab Rahimi, Mehrnoush ShamsFard

Recognizing causal elements and causal relations in text is one of the challenging issues in natural language processing; specifically, in low resource languages such as Persian. In this research we prepare a causality human annotated corpus for the Persian language which consists of 4446 sentences and 5128 causal relations and three labels of cause, effect and causal mark -- if possibl -- are specified for each relation. We have used this corpus to train a system for detecting causal elements boundaries. Also, we present a causality detection benchmark for three machine learning methods and two deep learning systems based on this corpus. Performance evaluations indicate that our best total result is obtained through CRF classifier which has F-measure of 0.76 and the best accuracy obtained through Bi-LSTM-CRF deep learning method with Accuracy equal to %91.4.

Ehsan Taher, Seyed Abbas Hoseini, Mehrnoush Shamsfard

Named entity recognition is a natural language processing task to recognize and extract spans of text associated with named entities and classify them in semantic Categories. Google BERT is a deep bidirectional language model, pre-trained on large corpora that can be fine-tuned to solve many NLP tasks such as question answering, named entity recognition, part of speech tagging and etc. In this paper, we use the pre-trained deep bidirectional network, BERT, to make a model for named entity recognition in Persian. We also compare the results of our model with the previous state of the art results achieved on Persian NER. Our evaluation metric is CONLL 2003 score in two levels of word and phrase. This model achieved second place in NSURL-2019 task 7 competition which associated with NER for the Persian language. our results in this competition are 83.5 and 88.4 f1 CONLL score respectively in phrase and word level evaluation.

Arezoo Hatefi Ghahfarrokhi, Mehrnoush Shamsfard

In this paper, we investigate the impact of the social media data in predicting the Tehran Stock Exchange (TSE) variables for the first time. We consider the closing price and daily return of three different stocks for this investigation. We collected our social media data from Sahamyab.com/stocktwits for about three months. To extract information from online comments, we propose a hybrid sentiment analysis approach that combines lexicon-based and learning-based methods. Since lexicons that are available for the Persian language are not practical for sentiment analysis in the stock market domain, we built a particular sentiment lexicon for this domain. After designing and calculating daily sentiment indices using the sentiment of the comments, we examine their impact on the baseline models that only use historical market data and propose new predictor models using multi regression analysis. In addition to the sentiments, we also examine the comments volume and the users' reliabilities. We conclude that the predictability of various stocks in TSE is different depending on their attributes. Moreover, we indicate that for predicting the closing price only comments volume and for predicting the daily return both the volume and the sentiment of the comments could be useful. We demonstrate that Users' Trust coefficients have different behaviors toward the three stocks.

Hassan Maleki Galandouz, Mohsen Ebrahimi Moghaddam, Mehrnoush Shamsfard

Image captioning aims at automatically generating descriptions of an image in natural language. This is a challenging problem in the field of artificial intelligence that has recently received significant attention in the computer vision and natural language processing. Among the existing approaches, visual retrieval based methods have been proven to be highly effective. These approaches search for similar images, then build a caption for the query image based on the captions of the retrieved images. In this study, we present a method for visual retrieval based image captioning, in which we use a multi criteria decision making algorithm to effectively combine several criteria with proportional impact weights to retrieve the most relevant caption for the query image. The main idea of the proposed approach is to design a mechanism to retrieve more semantically relevant captions with the query image and then selecting the most appropriate caption by imitation of the human act based on a weighted multi-criteria decision making algorithm. Experiments conducted on MS COCO benchmark dataset have shown that proposed method provides much more effective results in compare to the state-of-the-art models by using criteria with proportional impact weights .

Zahra Riahi Samani, Mehrnoush Shamsfard

Conceptual formalism supported by typical ontologies may not be sufficient to represent uncertainty information which is caused due to the lack of clear cut boundaries between concepts of a domain. Fuzzy ontologies are proposed to offer a way to deal with this uncertainty. This paper describes the state of the art in developing fuzzy ontologies. The survey is produced by studying about 35 works on developing fuzzy ontologies from a batch of 100 articles in the field of fuzzy ontologies.

Rana Forsati, Mehrdad Mahdavi, Mehrnoush Shamsfard et al.

With the advent of online social networks, recommender systems have became crucial for the success of many online applications/services due to their significance role in tailoring these applications to user-specific needs or preferences. Despite their increasing popularity, in general recommender systems suffer from the data sparsity and the cold-start problems. To alleviate these issues, in recent years there has been an upsurge of interest in exploiting social information such as trust relations among users along with the rating data to improve the performance of recommender systems. The main motivation for exploiting trust information in recommendation process stems from the observation that the ideas we are exposed to and the choices we make are significantly influenced by our social context. However, in large user communities, in addition to trust relations, the distrust relations also exist between users. For instance, in Epinions the concepts of personal "web of trust" and personal "block list" allow users to categorize their friends based on the quality of reviews into trusted and distrusted friends, respectively. In this paper, we propose a matrix factorization based model for recommendation in social rating networks that properly incorporates both trust and distrust relationships aiming to improve the quality of recommendations and mitigate the data sparsity and the cold-start users issues. Through experiments on the Epinions data set, we show that our new algorithm outperforms its standard trust-enhanced or distrust-enhanced counterparts with respect to accuracy, thereby demonstrating the positive effect that incorporation of explicit distrust information can have on recommender systems.