Papers by Farhad Nooralahzadeh
Zero-Shot Cross-Lingual Transfer with Meta Learning (2020.emnlp-main)
Copied to clipboard
| Challenge: | There are more than 7,000 languages spoken in the world, over 90 of which have more than 10 million native speakers each. |
| Approach: | They propose to use meta-learning to train a model on multiple languages at the same time . they use standard supervised, zero-shot cross-lingual, and few-shot crosses-lingual settings for different natural language understanding tasks. |
| Outcome: | The proposed setup improves on the state-of-the-art for a total of 15 languages. |
Evaluation of Domain-specific Word Embeddings using Knowledge Resources (L18-1)
Copied to clipboard
| Challenge: | Existing word embeddings capture a range of semantic relations relevant to the interpretation of lexical items, but domain-specific terms are difficult to evaluate because of a lack of statistical clues in the underlying corpus. |
| Approach: | They conduct intrinsic and extrinsic evaluations of both general and domain-specific embeddings and adapt embeddment enhancement methods to provide vector representations for infrequent and unseen terms. |
| Outcome: | The proposed model improves both in the intrinsic evaluation and extrinsic evaluation of the embedding models and their representations of infrequent and unseen terms. |
Progressive Transformer-Based Generation of Radiology Reports (2021.findings-emnlp)
Copied to clipboard
Farhad Nooralahzadeh, Nicolas Perez Gonzalez, Thomas Frauenfelder, Koji Fujimoto, Michael Krauthammer
| Challenge: | Existing approaches to generate radiology reports are based on image-to-text generation. |
| Approach: | They propose a sequential (i.e., image-to-text-totext) generation framework that integrates high-level concepts into the generation process. |
| Outcome: | The proposed model outperforms existing models on two benchmark datasets. |
Reinforcement-based denoising of distantly supervised NER with partial annotation (D19-61)
Copied to clipboard
| Challenge: | Existing named entity recognition systems rely on large amounts of human-labeled data for supervision, but the result is noisy. |
| Approach: | They propose to use partial annotation to address false negative cases and implement a reinforcement learning strategy to identify false positive instances. |
| Outcome: | The proposed model reduces the amount of manually annotated data required to perform NER in a new domain. |
Disfluent Cues for Enhanced Speech Understanding in Large Language Models (2023.findings-emnlp)
Copied to clipboard
| Challenge: | a large number of language models struggle to handle disfluencies, authors say . when a speaker hesitates, interrupts themselves, repeats or corrects words, or abandons phrases, it can make their speech fragmented. |
| Approach: | They propose to use disfluent queries to “clean” spontaneous speech . they propose to apply disfluencies to models that use different types of speech repairs . |
| Outcome: | The proposed model improves on a reading comprehension task using disfluent queries . the results suggest that disfluencies can improve model performance, rather than their removal . |
StatBot.Swiss: Bilingual Open Data Exploration in Natural Language (2024.findings-acl)
Copied to clipboard
Farhad Nooralahzadeh, Yi Zhang, Ellery Smith, Sabine Maennel, Cyril Matthey-Doret, Raphaël De Fondeville, Kurt Stockinger
| Challenge: | StatBot.Swiss dataset is the first bilingual benchmark for evaluating Text-to-SQL systems based on real-world applications. |
| Approach: | They propose to use a bilingual dataset to evaluate LLMs in Text-to-SQL systems. |
| Outcome: | The proposed dataset contains 455 natural language/SQL-pairs over 35 big databases with varying level of complexity for English and German. |