Papers by Ilia Markov

6 papers
Reasoning about Ambiguous Definite Descriptions (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing resources to evaluate reasoning are not well suited to investigate the capability of resolving ambiguities by explicit reasoning.
Approach: They propose to use ambiguous definite descriptions to create a benchmark dataset which requires models to resolve ambiguity by explicit reasoning.
Outcome: The proposed model includes all information required to resolve the ambiguity in the prompt, which means a model does not require anything but reasoning to do well.
Punctuation as Native Language Interference (C18-1)

Copied to clipboard

Challenge: Numerous aspects of written language have been studied for native language identification (NLI) but its impact has not been studied.
Approach: They propose to use punctuation marks as indicators of native language . they propose to apply them to native language identification .
Outcome: The proposed methods support the hypothesis that punctuation marks are persistent and robust indicators of the native language of the author, even when a high proficiency level in a non-native language is achieved.
QUIK: Towards End-to-end 4-Bit Inference on Generative Large Language Models (2024.emnlp-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) are extremely popular, leading to a race towards reducing their inference costs.
Approach: They propose a method that quantizes weights and activations to 4 bits to achieve better accuracy.
Outcome: The proposed method reduces runtime costs in memory-bound models but does not address cost-bound scenarios.
Unknown Script: Impact of Script on Cross-Lingual Transfer (2024.naacl-srw)

Copied to clipboard

Challenge: Existing models for high-resource languages are not available for all languages, and the vast majority of the world's languages are excluded from these models.
Approach: They propose to use pre-trained models to analyze the effect of the target language and its script on cross-lingual transfer.
Outcome: The proposed model is based on six models pre-trained on NER and POS tasks in the original script and romanized version.
A Deep Generative Approach to Native Language Identification (2020.coling-main)

Copied to clipboard

Challenge: Native language identification (NLI) is a multi-class classification task involving multiple features that capture the systematic fingerprints of the first language in the second language writing.
Approach: They propose a deep generative language modelling approach to NLI that fine-tunes a GPT-2 model separately on texts written by the authors with the same L1 and assigns n-grams to an unseen text.
Outcome: The proposed method outperforms traditional machine learning approaches and currently achieves the best results on the benchmark NLI datasets.
Contextualized Graph Representations for Generating Counter-Narratives against Hate Speech (2024.findings-emnlp)

Copied to clipboard

Challenge: Hate speech (HS) is a widespread problem in society with severe repercussions at both personal and societal levels.
Approach: They propose to incorporate conversational history into CNs to confront biases and stereotypes driving hateful narratives.
Outcome: The proposed strategies outperform existing methods on comparing graphical and text representations with varying degrees of context.

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