Papers by Gertjan van Noord

7 papers
A Taxonomy for In-depth Evaluation of Normalization for User Generated Content (L18-1)

Copied to clipboard

Challenge: Existing taxonomies for lexical normalization are not suitable for the task of normalization since the categories are substantially different.
Approach: They propose a taxonomy of error categories for lexical normalization . they annotate a recent normalization dataset and read a near-perfect agreement .
Outcome: The proposed taxonomy is based on a recent normalization dataset and it performs well.
Hyper-X: A Unified Hypernetwork for Multi-Task Multilingual Transfer (2022.emnlp-main)

Copied to clipboard

Challenge: Existing multilingual models cannot fully leverage training data when it is available in different task-language combinations.
Approach: They propose a single hypernetwork that unifies multi-task and multilingual learning with efficient adaptation.
Outcome: The proposed model achieves the best or competitive gain when a mixture of multiple resources is available while being significantly more efficient than existing models.
Evaluating Pre-training Objectives for Low-Resource Translation into Morphologically Rich Languages (2022.lrec-1)

Copied to clipboard

Challenge: a lack of parallel data is a major limitation for Neural Machine Translation systems, especially for morphologically rich languages.
Approach: They propose to leverage target monolingual data to overcome the lack of parallel data . they introduce a new technique called PT-Inflect to train NMT systems .
Outcome: The proposed techniques outperform NMT systems trained on parallel data on four typologically diverse target languages.
Modeling Input Uncertainty in Neural Network Dependency Parsing (D18-1)

Copied to clipboard

Challenge: Recent advances in neural network parsers address data sparsity issues by modeling character level information and exploiting raw data in semi-supervised settings.
Approach: They investigate whether lexical normalization provides similar functionality to lexiconal normalization . they show that a separate normalization component improves performance of a neural network parser .
Outcome: The proposed approaches improve performance even with access to character level information and word embeddings.
Subword-Delimited Downsampling for Better Character-Level Translation (2022.findings-emnlp)

Copied to clipboard

Challenge: Subword-level models are expensive in terms of time and computation, but character-level model with downsampling component can be used for machine translation.
Approach: They propose a character-level downsampling method which is informed by subwords to improve model performance.
Outcome: The proposed method outperforms existing methods and shows that it can be done without sacrificing quality.
Endowing Neural Language Learners with Human-like Biases: A Case Study on Dependency Length Minimization (2024.lrec-main)

Copied to clipboard

Challenge: Comparing the behavior of models with that of human learners can reveal which aspects affect the emergence of this preference.
Approach: They propose to add three factors to the standard neural-agent language learning and communication framework to make the simulation more realistic.
Outcome: The proposed conditions can contribute to a small but significant learning advantage for listeners of verb-initial languages.
UDapter: Language Adaptation for Truly Universal Dependency Parsing (2020.emnlp-main)

Copied to clipboard

Challenge: Cross-language interference and restrained model capacity remain major obstacles in multilingual dependency parsing.
Approach: They propose a multilingual task adaptation approach based on contextual parameter generation and adapter modules that learn adapters via language embeddings while sharing model parameters across languages.
Outcome: The proposed approach outperforms strong monolingual and multilingual baselines on most languages on high-resource and low-resourced (zero-shot) languages.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations