Papers by Pascal Denis

12 papers
WordNet Is All You Need: A Surprisingly Effective Unsupervised Method for Graded Lexical Entailment (2023.findings-emnlp)

Copied to clipboard

Challenge: a simple unsupervised method for predicting graded lexical entailment in English relies on WordNet . despite its simplicity, our method outperforms all previous methods using WordNet as weak supervision.
Approach: They propose an unsupervised method which relies exclusively on WordNet for predicting graded lexical entailment in English.
Outcome: The proposed method outperforms existing methods on the largest GLE dataset using WordNet.
A Probabilistic Model for Joint Learning of Word Embeddings from Texts and Images (D18-1)

Copied to clipboard

Challenge: Existing approaches combine language and perception to infer word embeddings . however, the embeddables produced by such models do not reflect the actual word representations.
Approach: They propose a probabilistic model that integrates linguistic and perceptual inputs to explain observed word-context pairs in a text corpus.
Outcome: The proposed model achieves competitive or stronger results on tasks of assessing pairwise word similarity and image/caption retrieval compared to other state-of-the-art models.
Chop and Change: Anaphora Resolution in Instructional Cooking Videos (2022.findings-aacl)

Copied to clipboard

Challenge: temporally evolving entities present challenges for anaphora resolution tasks . recipes provide rich source for referring expressions of transformed entities .
Approach: They propose to use annotations to annotate recipes for anaphora resolution task . they propose to employ temporal features to improve anamorphic resolution .
Outcome: The proposed annotation scheme improves the performance of the anaphora resolution task.
MMAR: Multilingual and Multimodal Anaphora Resolution in Instructional Videos (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing approaches to multilingual anaphora resolution include images and video inputs.
Approach: They propose to include multimodal information in the form of images in anaphora resolution tasks.
Outcome: The proposed approach improves resolution by 10% for unseen languages.
Phylogenic Multi-Lingual Dependency Parsing (N19-1)

Copied to clipboard

Challenge: phylogenetic learning is beneficial for low resourced languages and well furnished languages families.
Approach: They propose to use the phylogenetic tree to guide the learning of multi-lingual dependency parsers . they use a phylogy tree to train models that leverage languages structural similarities .
Outcome: The proposed model outperforms independently learned models on zero-shot parsing of unseen languages.
To Word Senses and Beyond: Inducing Concepts with Contextualized Language Models (2024.emnlp-main)

Copied to clipboard

Challenge: Word Sense Disambiguiation and Word sense Induction are considered independent problems, but they are often neglected in practice.
Approach: They propose an unsupervised task of learning a soft clustering amongwords that defines a set of concepts directly from data.
Outcome: The proposed approach leverages both a local and global cross-lexicon view to induce concepts and also senses in the context of the proposed task.
Find-2-Find: Multitask Learning for Anaphora Resolution and Object Localization (2023.emnlp-main)

Copied to clipboard

Challenge: Existing systems require large number of accurate annotations, such as image-level labels and location-level labeling.
Approach: They propose a joint anaphora resolution and object localization dataset targeting visual-linguistic ambiguity.
Outcome: The proposed framework improves visual-linguistic alignment and object localization with one joint model compared to a strong single-task baseline.
A Framework for Understanding the Role of Morphology in Universal Dependency Parsing (D18-1)

Copied to clipboard

Challenge: a measure of morphological complexity is used to characterize syntactic information in word embeddings.
Approach: They propose a measure of morphological complexity in terms of governor-dependent preferential attachment that explains parsing performance.
Outcome: The proposed framework improves parsing performance on morphologically rich languages using morphology as a syntactic marker.
Exploring Category Structure with Contextual Language Models and Lexical Semantic Networks (2023.eacl-main)

Copied to clipboard

Challenge: Recent work on word embeddings reports low correlations with human ratings . contextual language models (CLMs) have been successful in acquiring semantic and world knowledge.
Approach: They propose to use BERT to probe contextual language models for predicting typicality scores.
Outcome: The proposed methods improve on previous studies on word embeddings and their ability to predict typicality scores.
Fair NLP Models with Differentially Private Text Encoders (2022.findings-emnlp)

Copied to clipboard

Challenge: Encoded text representations often capture sensitive attributes about individuals, raising privacy concerns and making models unfair to certain groups.
Approach: They propose an approach that combines privacy and adversarial training to learn private representations which induces fairer models.
Outcome: The proposed approach improves on four NLP datasets and shows that privacy and fairness can positively reinforce each other.
A Tale of Two Laws of Semantic Change: Predicting Synonym Changes with Distributional Semantic Models (2023.starsem-1)

Copied to clipboard

Challenge: Lexical Semantic Change is the study of how the meaning of words evolves through time.
Approach: They propose to use distributional models to detect whether LD or LPC operate for given word pairs.
Outcome: The proposed frameworks achieve a balanced accuracy above 0.6 on the dataset.
Fair Without Leveling Down: A New Intersectional Fairness Definition (2023.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to capture intersectional group fairness lack significant unfairness at intersection levels.
Approach: They propose a new definition of intersectional fairness that combines absolute and relative performance across sensitive groups.
Outcome: The proposed definition does not improve on a simple baseline.

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