Search Results for author:
Found 17 papers, 14 papers with code
Character-Level Models versus Morphology in Semantic Role Labeling
Character-level models have become a popular approach specially for their accessibility and ability to handle unseen data.
LINSPECTOR: Multilingual Probing Tasks for Word Representations
We present a reusable methodology for creation and evaluation of such tests in a multilingual setting.
Data Augmentation via Dependency Tree Morphing for Low-Resource Languages
Neural NLP systems achieve high scores in the presence of sizable training dataset.
Text Processing Like Humans Do: Visually Attacking and Shielding NLP Systems
Visual modifications to text are often used to obfuscate offensive comments in social media (e. g., "! d10t") or as a writing style ("1337" in "leet speak"), among other scenarios.
LINSPECTOR WEB: A Multilingual Probing Suite for Word Representations
We present LINSPECTOR WEB, an open source multilingual inspector to analyze word representations.
Two Birds with One Stone: Investigating Invertible Neural Networks for Inverse Problems in Morphology
We show that they are able to recover the morphological input parameters, i. e., predicting the lemma (e. g., cat) or the morphological tags (e. g., Plural) when run in the reverse direction, without any significant performance drop in the forward direction, i. e., predicting the surface form (e. g., cats).
PuzzLing Machines: A Challenge on Learning From Small Data
To expose this problem in a new light, we introduce a challenge on learning from small data, PuzzLing Machines, which consists of Rosetta Stone puzzles from Linguistic Olympiads for high school students.
To Augment or Not to Augment? A Comparative Study on Text Augmentation Techniques for Low-Resource NLP
Although NLP has recently witnessed a load of textual augmentation techniques, the field still lacks a systematic performance analysis on a diverse set of languages and sequence tagging tasks.
MetaQA: Combining Expert Agents for Multi-Skill Question Answering
The recent explosion of question answering (QA) datasets and models has increased the interest in the generalization of models across multiple domains and formats by either training on multiple datasets or by combining multiple models.
UKP-SQUARE: An Online Platform for Question Answering Research
Recent advances in NLP and information retrieval have given rise to a diverse set of question answering tasks that are of different formats (e. g., extractive, abstractive), require different model architectures (e. g., generative, discriminative), and setups (e. g., with or without retrieval).
Transformers on Multilingual Clause-Level Morphology
While transformer architectures with data augmentation achieved the most promising results for inflection and reinflection tasks, prefix-tuning on mGPT received the highest results for the analysis task.
Lessons Learned from a Citizen Science Project for Natural Language Processing
Citizen Science is an alternative to crowdsourcing that is relatively unexplored in the context of NLP.
Metric-Based In-context Learning: A Case Study in Text Simplification
However, determining the best method to select examples for ICL is nontrivial as the results can vary greatly depending on the quality, quantity, and order of examples used.
Ranked #1 on
Text Simplification
on ASSET
Benchmarking Procedural Language Understanding for Low-Resource Languages: A Case Study on Turkish
To tackle these tasks, we implement strong baseline models via fine-tuning large language-specific models such as TR-BART and BERTurk, as well as multilingual models such as mBART, mT5, and XLM.
GECTurk: Grammatical Error Correction and Detection Dataset for Turkish
To encourage further research on Turkish GEC, we release our datasets, baseline models, and the synthetic data generation pipeline at https://github. com/GGLAB-KU/gecturk.
Quantifying Divergence for Human-AI Collaboration and Cognitive Trust
The users are then shown the similarities/differences to their most similar model and are surveyed for their likelihood of collaboration and cognitive trust to the selected system.
PARADISE: Evaluating Implicit Planning Skills of Language Models with Procedural Warnings and Tips Dataset
Recently, there has been growing interest within the community regarding whether large language models are capable of planning or executing plans.
