1 code implementation • 3 Apr 2023 • Alireza Salemi, Amirhossein Abaskohi, Sara Tavakoli, Yadollah Yaghoobzadeh, Azadeh Shakery
Multilingual pre-training on monolingual data ignores the availability of parallel data in many language pairs.
no code implementations • 2 Nov 2022 • Sajad Movahedi, Azadeh Shakery
While deep learning in the form of recurrent neural networks (RNNs) has caused a significant improvement in neural language modeling, the fact that they are extremely prone to overfitting is still a mainly unresolved issue.
1 code implementation • 14 Oct 2022 • Sajad Movahedi, Melika Adabinejad, Ayyoob Imani, Arezou Keshavarz, Mostafa Dehghani, Azadeh Shakery, Babak N. Araabi
The main shortcoming of DARTS is performance collapse, where the discovered architecture suffers from a pattern of declining quality during search.
1 code implementation • EMNLP 2021 • Alireza Salemi, Emad Kebriaei, Ghazal Neisi Minaei, Azadeh Shakery
Current pre-training works in abstractive summarization give more points to the summaries with more words in common with the main text and pay less attention to the semantic similarity between generated sentences and the original document.
no code implementations • SEMEVAL 2021 • Hossein Basafa, Sajad Movahedi, Ali Ebrahimi, Azadeh Shakery, Heshaam Faili
This paper presents a technical report of our submission to the 4th task of SemEval-2021, titled: Reading Comprehension of Abstract Meaning.
1 code implementation • SEMEVAL 2021 • Alireza Salemi, Nazanin Sabri, Emad Kebriaei, Behnam Bahrak, Azadeh Shakery
Detecting which parts of a sentence contribute to that sentence's toxicity -- rather than providing a sentence-level verdict of hatefulness -- would increase the interpretability of models and allow human moderators to better understand the outputs of the system.
no code implementations • 23 Apr 2020 • Amir Vakili Tahami, Kamyar Ghajar, Azadeh Shakery
Response retrieval is a subset of neural ranking in which a model selects a suitable response from a set of candidates given a conversation history.
no code implementations • 6 Nov 2019 • Amir Vakili Tahami, Azadeh Shakery
Recent work has shown that these language models can be used in text-matching scenarios to create Bi-encoders that perform almost as well as Cross-encoders while having a much faster inference speed.
no code implementations • 28 Oct 2019 • Samaneh Karimi, Azadeh Shakery, Rakesh Verma
The use of user-generated content in this framework, as a partly-unbiased, real-time and low cost content on the web distinguishes the proposed news website ranking framework from the literature.
no code implementations • 25 Jun 2019 • Rakesh Verma, Samaneh Karimi, Daniel Lee, Omprakash Gnawali, Azadeh Shakery
In a disaster situation, first responders need to quickly acquire situational awareness and prioritize response based on the need, resources available and impact.
no code implementations • WS 2019 • Ida Amini, Samane Karimi, Azadeh Shakery
Wide and universal changes in the web content due to the growth of web 2 applications increase the importance of user-generated content on the web.
no code implementations • SEMEVAL 2019 • Emad Kebriaei, Samaneh Karimi, Nazanin Sabri, Azadeh Shakery
In this paper, the used methods and the results obtained by our team, entitled Emad, on the OffensEval 2019 shared task organized at SemEval 2019 are presented.
no code implementations • ECIR 2019 • Erfan Ghadery, Sajad Movahedi, Masoud Jalili Sabet, Heshaam Faili, Azadeh Shakery
For a given sentence, our proposed method performs ACD based on two hypotheses: First, a category should be assigned to a sentence if there is a high semantic similarity between the sentence and a set of representative words of that category.
Aspect-Based Sentiment Analysis Aspect-Based Sentiment Analysis (ABSA) +6
no code implementations • 4 Jan 2019 • Sajad Movahedi, Erfan Ghadery, Heshaam Faili, Azadeh Shakery
In this paper, we propose a deep neural network method based on attention mechanism to identify different aspect categories of a given review sentence.
Aspect-Based Sentiment Analysis Aspect-Based Sentiment Analysis (ABSA) +2
2 code implementations • 8 Dec 2018 • Erfan Ghadery, Sajad Movahedi, Heshaam Faili, Azadeh Shakery
Besides, most of these supervised methods require feature engineering to perform well.
Aspect-Based Sentiment Analysis Aspect-Based Sentiment Analysis (ABSA) +3
no code implementations • 8 Nov 2018 • Ayyoob Imani, Amir Vakili, Ali Montazer, Azadeh Shakery
In this paper, we show that this is also true for more recently proposed embedding-based query expansion methods.
1 code implementation • 30 Jan 2018 • Mahsa Sadat Shahshahani, Mahdi Mohseni, Azadeh Shakery, Heshaam Faili
The goal in the NER task is to classify proper nouns of a text into classes such as person, location, and organization.
no code implementations • COLING 2016 • Javid Dadashkarimi, Masoud Jalili Sabet, Azadeh Shakery
To this end, first we build a query-generated training data using pseudo-relevant documents to the query and all translation candidates.
no code implementations • 25 May 2016 • Javid Dadashkarimi, Hossein Nasr Esfahani, Heshaam Faili, Azadeh Shakery
Stemming is a common approach to this end.
no code implementations • 25 May 2016 • Javid Dadashkarimi, Mahsa S. Shahshahani, Amirhossein Tebbifakhr, Heshaam Faili, Azadeh Shakery
Using top-ranked documents in response to a query has been shown to be an effective approach to improve the quality of query translation in dictionary-based cross-language information retrieval.
no code implementations • 29 Jan 2015 • Hamed Zamani, Azadeh Shakery, Pooya Moradi
In this paper, we consider a tweet containing a rating for a movie as an instance and focus on ranking the instances of each user based on their engagement, i. e., the total number of retweets and favorites it will gain.
no code implementations • 4 Nov 2014 • Javid Dadashkarimi, Azadeh Shakery, Heshaam Faili
Translation ambiguity, out of vocabulary words and missing some translations in bilingual dictionaries make dictionary-based Cross-language Information Retrieval (CLIR) a challenging task.
no code implementations • 20 May 2014 • Hosein Azarbonyad, Azadeh Shakery, Heshaam Faili
To evaluate the proposed method we do English-Persian CLIR, in which we employ the translation ranking model to find translations of English queries and employ the translations to retrieve Persian documents.