Farhad Nooralahzadeh


2020

pdf bib
Zero-Shot Cross-Lingual Transfer with Meta Learning
Farhad Nooralahzadeh | Giannis Bekoulis | Johannes Bjerva | Isabelle Augenstein
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Learning what to share between tasks has become a topic of great importance, as strategic sharing of knowledge has been shown to improve downstream task performance. This is particularly important for multilingual applications, as most languages in the world are under-resourced. Here, we consider the setting of training models on multiple different languages at the same time, when little or no data is available for languages other than English. We show that this challenging setup can be approached using meta-learning: in addition to training a source language model, another model learns to select which training instances are the most beneficial to the first. We experiment using standard supervised, zero-shot cross-lingual, as well as few-shot cross-lingual settings for different natural language understanding tasks (natural language inference, question answering). Our extensive experimental setup demonstrates the consistent effectiveness of meta-learning for a total of 15 languages. We improve upon the state-of-the-art for zero-shot and few-shot NLI (on MultiNLI and XNLI) and QA (on the MLQA dataset). A comprehensive error analysis indicates that the correlation of typological features between languages can partly explain when parameter sharing learned via meta-learning is beneficial.

2019

pdf bib
Reinforcement-based denoising of distantly supervised NER with partial annotation
Farhad Nooralahzadeh | Jan Tore Lønning | Lilja Øvrelid
Proceedings of the 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019)

Existing named entity recognition (NER) systems rely on large amounts of human-labeled data for supervision. However, obtaining large-scale annotated data is challenging particularly in specific domains like health-care, e-commerce and so on. Given the availability of domain specific knowledge resources, (e.g., ontologies, dictionaries), distant supervision is a solution to generate automatically labeled training data to reduce human effort. The outcome of distant supervision for NER, however, is often noisy. False positive and false negative instances are the main issues that reduce performance on this kind of auto-generated data. In this paper, we explore distant supervision in a supervised setup. We adopt a technique of partial annotation to address false negative cases and implement a reinforcement learning strategy with a neural network policy to identify false positive instances. Our results establish a new state-of-the-art on four benchmark datasets taken from different domains and different languages. We then go on to show that our model reduces the amount of manually annotated data required to perform NER in a new domain.

2018

pdf bib
SIRIUS-LTG-UiO at SemEval-2018 Task 7: Convolutional Neural Networks with Shortest Dependency Paths for Semantic Relation Extraction and Classification in Scientific Papers
Farhad Nooralahzadeh | Lilja Øvrelid | Jan Tore Lønning
Proceedings of The 12th International Workshop on Semantic Evaluation

This article presents the SIRIUS-LTG-UiO system for the SemEval 2018 Task 7 on Semantic Relation Extraction and Classification in Scientific Papers. First we extract the shortest dependency path (sdp) between two entities, then we introduce a convolutional neural network (CNN) which takes the shortest dependency path embeddings as input and performs relation classification with differing objectives for each subtask of the shared task. This approach achieved overall F1 scores of 76.7 and 83.2 for relation classification on clean and noisy data, respectively. Furthermore, for combined relation extraction and classification on clean data, it obtained F1 scores of 37.4 and 33.6 for each phase. Our system ranks 3rd in all three sub-tasks of the shared task.

pdf bib
Evaluation of Domain-specific Word Embeddings using Knowledge Resources
Farhad Nooralahzadeh | Lilja Øvrelid | Jan Tore Lønning
Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)

pdf bib
Syntactic Dependency Representations in Neural Relation Classification
Farhad Nooralahzadeh | Lilja Øvrelid
Proceedings of the Workshop on the Relevance of Linguistic Structure in Neural Architectures for NLP

We investigate the use of different syntactic dependency representations in a neural relation classification task and compare the CoNLL, Stanford Basic and Universal Dependencies schemes. We further compare with a syntax-agnostic approach and perform an error analysis in order to gain a better understanding of the results.

pdf bib
SIRIUS-LTG: An Entity Linking Approach to Fact Extraction and Verification
Farhad Nooralahzadeh | Lilja Øvrelid
Proceedings of the First Workshop on Fact Extraction and VERification (FEVER)

This article presents the SIRIUS-LTG system for the Fact Extraction and VERification (FEVER) Shared Task. It consists of three components: 1) Wikipedia Page Retrieval: First we extract the entities in the claim, then we find potential Wikipedia URI candidates for each of the entities using a SPARQL query over DBpedia 2) Sentence selection: We investigate various techniques i.e. Smooth Inverse Frequency (SIF), Word Mover’s Distance (WMD), Soft-Cosine Similarity, Cosine similarity with unigram Term Frequency Inverse Document Frequency (TF-IDF) to rank sentences by their similarity to the claim. 3) Textual Entailment: We compare three models for the task of claim classification. We apply a Decomposable Attention (DA) model (Parikh et al., 2016), a Decomposed Graph Entailment (DGE) model (Khot et al., 2018) and a Gradient-Boosted Decision Trees (TalosTree) model (Sean et al., 2017) for this task. The experiments show that the pipeline with simple Cosine Similarity using TFIDF in sentence selection along with DA model as labelling model achieves the best results on the development set (F1 evidence: 32.17, label accuracy: 59.61 and FEVER score: 0.3778). Furthermore, it obtains 30.19, 48.87 and 36.55 in terms of F1 evidence, label accuracy and FEVER score, respectively, on the test set. Our system ranks 15th among 23 participants in the shared task prior to any human-evaluation of the evidence.

2014

pdf bib
Part of Speech Tagging for French Social Media Data
Farhad Nooralahzadeh | Caroline Brun | Claude Roux
Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: Technical Papers