Papers by Filip Ilievski

13 papers
Contextualizing Argument Quality Assessment with Relevant Knowledge (2024.naacl-short)

Copied to clipboard

Challenge: Existing methods for assessing argument quality in isolation analyze their quality in the absence of context, which affects their accuracy and generalizability.
Approach: They propose a method for scoring argument quality based on contextualization via relevant knowledge that leverages large language models to provide feedback, infer hidden assumptions, supply a similar-quality argument, or give a counter-argument.
Outcome: The proposed method outperforms existing methods across multiple metrics in both in-domain and zero-shot setups.
Connecting the Dots: A Knowledgeable Path Generator for Commonsense Question Answering (2020.findings-emnlp)

Copied to clipboard

Challenge: Existing QA systems do not have commonsense knowledge or cannot reason with it.
Approach: They propose to augment a general commonsense QA framework with a knowledgeable path generator by extrapolating existing paths from a KG with 'state-of-the-art' language model.
Outcome: The generated paths are interpretable, novel, and relevant to the task.
BRAINTEASER: Lateral Thinking Puzzles for Large Language Models (2023.emnlp-main)

Copied to clipboard

Challenge: lateral thinking tasks require implicit and complex reasoning, relying on human-like commonsense mechanisms.
Approach: They propose a lateral thinking benchmark to test models' ability to exhibit lateral reasoning and defy default commonsense associations.
Outcome: The proposed model exhibits lateral thinking and defies default commonsense associations.
Robust Text Classification: Analyzing Prototype-Based Networks (2024.findings-emnlp)

Copied to clipboard

Challenge: Language models exhibit a drop in performance on noisy data, which can cause classifiers to incorrectly change their predictions.
Approach: They propose to use Prototype-Based Networks to classify examples based on their similarity to prototypical examples of a class (prototypes) they show that PBNs offer more robustness under both targeted and static adversarial attacks.
Outcome: The proposed model is robust to noise and targets both targeted and static attacks.
Coalescing Global and Local Information for Procedural Text Understanding (2022.coling-1)

Copied to clipboard

Challenge: Existing models for procedural text understanding have low precision or low recall . et al., 2012, pp. 106-106.
Approach: They propose a model that builds entity- and timestep-aware input representations . they extend the model with additional output layers and integrate it into a story reasoning framework .
Outcome: The proposed model achieves state-of-the-art on a popular procedural text understanding dataset and on 'story reasoning benchmark' it integrates the model with additional output layers and improves on the previous models.
Systematic Study of Long Tail Phenomena in Entity Linking (C18-1)

Copied to clipboard

Challenge: Existing systems for entity linking are based on frequent 'head' cases, while performance drops when moving towards rare 'long tail' entities.
Approach: They propose to use a long tail to investigate the properties of entity linking datasets.
Outcome: The proposed systems overfit to popular/frequent and non-ambiguous cases and find the most difficult cases among the infrequent candidates of ambiguous forms.
Exploring Strategies for Generalizable Commonsense Reasoning with Pre-trained Models (2021.emnlp-main)

Copied to clipboard

Challenge: Recent work proposes lightweight updates to improve commonsense reasoning models . fine-tuning can cause models to overfit to task-specific data and forget knowledge gained during training .
Approach: They propose to use lightweight models to update pre-trained language models to learn commonsense background knowledge.
Outcome: The proposed models learn from commonsense reasoning datasets, but they are overfitted and limited generalized.
Representing Numbers in NLP: a Survey and a Vision (2021.naacl-main)

Copied to clipboard

Challenge: Numeracy is an essential skill for language understanding since numbers are often interspersed in text.
Approach: They propose a comprehensive taxonomy of tasks and methods to represent numbers in text . they synthesize best practices for representing numbers in texts and articulate a vision for holistic numeracy .
Outcome: The proposed model synthesizes best practices for representing numbers in text . it argues that the model is more effective than other approaches .
Do Language Models Perform Generalizable Commonsense Inference? (2021.findings-acl)

Copied to clipboard

Challenge: Recent work has applied pretrained language models to populate commonsense knowledge graphs (CKGs) but there is a lack of understanding on their generalization to multiple CKGs, unseen relations, and novel entities.
Approach: They analyze the ability of pretrained language models to perform generalizable commonsense inference in terms of knowledge capacity, transferability and induction.
Outcome: The proposed models can adapt to different schemas defined by multiple CKGs but fail to generalize to new relations.
Don’t Annotate, but Validate: a Data-to-Text Method for Capturing Event Data (L18-1)

Copied to clipboard

Challenge: Existing methods to create event data are limited by ambiguity and variation in the data.
Approach: They propose a method to obtain large volumes of text corpora with event data . they use a tool to annotate texts and enrich the reference texts with event coreference annotations.
Outcome: The proposed method obtains large volumes of high-quality text corpora with event data . the data obtained with this method have high precision and at a large scale .
PaCo: Preconditions Attributed to Commonsense Knowledge (2022.findings-emnlp)

Copied to clipboard

Challenge: Existing language models can reason with circumstantial preconditions of commonsense knowledge, but they do not understand the circumstancial precondition.
Approach: They propose to use a dataset to examine the ability of existing language models to understand circumstantial preconditions to improve their reasoning with commonsense knowledge.
Outcome: The proposed task shows that human reasoning with preconditions is an open challenge.
Numeracy enhances the Literacy of Language Models (2021.emnlp-main)

Copied to clipboard

Challenge: Specialized number representations have shown improvements on numerical reasoning tasks like arithmetic word problems and masked number prediction.
Approach: They propose to use six different number encoders to improve masked word prediction by avoiding conflating nominal and ordinal number occurrences.
Outcome: The proposed representations improve masked word prediction accuracy and generalize to contexts without annotated numbers.
Large-scale Cross-lingual Language Resources for Referencing and Framing (2020.lrec-1)

Copied to clipboard

Challenge: Existing corpora that capture language but do not represent actual situations hinder development of systems to resolve cross-document coreference.
Approach: They introduce the concept of cross-lingual referential corpora and propose a framework to analyze framing . they expect to capture larger variation in framation compared to traditional approaches .
Outcome: The proposed project will analyze the framing of incidents in different languages and texts . it expects to capture larger variation in framation compared to traditional approaches .

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