Search Results for author: Mohammad Sadegh Rasooli

Found 25 papers, 8 papers with code

Multitask Learning for Cross-Lingual Transfer of Broad-coverage Semantic Dependencies

no code implementations EMNLP 2020 Maryam Aminian, Mohammad Sadegh Rasooli, Mona Diab

We describe a method for developing broad-coverage semantic dependency parsers for languages for which no semantically annotated resource is available.

Cross-Lingual Transfer

Bidirectional Language Models Are Also Few-shot Learners

no code implementations29 Sep 2022 Ajay Patel, Bryan Li, Mohammad Sadegh Rasooli, Noah Constant, Colin Raffel, Chris Callison-Burch

An arbitrary task can be reformulated as a natural language prompt, and a language model can be asked to generate the completion, indirectly performing the task in a paradigm known as prompt-based learning.

Denoising Language Modelling +4

Cultural and Geographical Influences on Image Translatability of Words across Languages

1 code implementation NAACL 2021 Nikzad Khani, Isidora Tourni, Mohammad Sadegh Rasooli, Chris Callison-Burch, Derry Tanti Wijaya

We find that images of words are not always invariant across languages, and that language pairs with shared culture, meaning having either a common language family, ethnicity or religion, have improved image translatability (i. e., have more similar images for similar words) compared to its converse, regardless of their geographic proximity.

Cultural Vocal Bursts Intensity Prediction Multilingual NLP +3

Automatic Standardization of Colloquial Persian

1 code implementation10 Dec 2020 Mohammad Sadegh Rasooli, Farzane Bakhtyari, Fatemeh Shafiei, Mahsa Ravanbakhsh, Chris Callison-Burch

We also show that our model improves English-to-Persian machine translation in scenarios for which the training data is from colloquial Persian with 1. 4 absolute BLEU score difference in the development data, and 0. 8 in the test data.

Machine Translation Translation

The Persian Dependency Treebank Made Universal

1 code implementation LREC 2022 Mohammad Sadegh Rasooli, Pegah Safari, Amirsaeid Moloodi, Alireza Nourian

Our delexicalized Persian-to-English parser transfer experiments show that a parsing model trained on our data is ~2% absolutely more accurate than that of Seraji et al. (2016) in terms of labeled attachment score.

Mutlitask Learning for Cross-Lingual Transfer of Semantic Dependencies

no code implementations30 Apr 2020 Maryam Aminian, Mohammad Sadegh Rasooli, Mona Diab

We make use of supervised syntactic parsing as an auxiliary task in a multitask learning framework, and show that with different multitask learning settings, we consistently improve over the single-task baseline.

Cross-Lingual Transfer

Cross-Lingual Transfer of Semantic Roles: From Raw Text to Semantic Roles

no code implementations WS 2019 Maryam Aminian, Mohammad Sadegh Rasooli, Mona Diab

We describe a transfer method based on annotation projection to develop a dependency-based semantic role labeling system for languages for which no supervised linguistic information other than parallel data is available.

Cross-Lingual Transfer Semantic Role Labeling

Low-Resource Syntactic Transfer with Unsupervised Source Reordering

no code implementations NAACL 2019 Mohammad Sadegh Rasooli, Michael Collins

We describe a cross-lingual transfer method for dependency parsing that takes into account the problem of word order differences between source and target languages.

Cross-Lingual Transfer Dependency Parsing

Entity-Aware Language Model as an Unsupervised Reranker

no code implementations12 Mar 2018 Mohammad Sadegh Rasooli, Sarangarajan Parthasarathy

One solution is to use a reranker trained with global features, in which global features are derived from n-best lists.

Language Modelling

Transferring Semantic Roles Using Translation and Syntactic Information

no code implementations IJCNLP 2017 Maryam Aminian, Mohammad Sadegh Rasooli, Mona Diab

Our paper addresses the problem of annotation projection for semantic role labeling for resource-poor languages using supervised annotations from a resource-rich language through parallel data.

Semantic Role Labeling Translation +1

Cross-Lingual Syntactic Transfer with Limited Resources

1 code implementation TACL 2017 Mohammad Sadegh Rasooli, Michael Collins

We describe a simple but effective method for cross-lingual syntactic transfer of dependency parsers, in the scenario where a large amount of translation data is not available.


Yara Parser: A Fast and Accurate Dependency Parser

2 code implementations23 Mar 2015 Mohammad Sadegh Rasooli, Joel Tetreault

At its fastest, Yara can parse about 4000 sentences per second when in greedy mode (1 beam).

Dependency Parsing Information Retrieval +3

Cannot find the paper you are looking for? You can Submit a new open access paper.