Papers by Timothée Bernard

9 papers
The Emergence of High-Level Semantics in a Signaling Game (2024.starsem-1)

Copied to clipboard

Challenge: a symbol grounding problem has been raised in recent years in AI . we show that neural agents can communicate high-level semantic concepts .
Approach: They propose to use an adversarial agent to train neural agents in a signaling game . they show that the agents can communicate high-level semantic concepts rather than low-level features .
Outcome: The proposed method can learn to communicate high-level semantic concepts . it also produces an appropriate training signal when no other method is available .
So many design choices: Improving and interpreting neural agent communication in signaling games (2023.findings-acl)

Copied to clipboard

Challenge: Emergent language games are experimental protocols designed to model how communication may arise among a group of agents.
Approach: They propose to adopt a signaling game in which a sender is exposed to an image and generates a sequence of symbols that is transmitted to a receiver.
Outcome: The proposed language improves when the sender is exposed to an image and generates a sequence of symbols that is transmitted to a receiver.
On the Relation Between Fine-Tuning, Topological Properties, and Task Performance in Sense-Enhanced Embeddings (2025.acl-long)

Copied to clipboard

Challenge: Enhanced word embeddings do not align well with word senses, resulting in poor performance on word sense identification tasks.
Approach: They propose to use two methods to fine-tune embeddings to identify the topological properties that contribute to sense-enhanced embeddables.
Outcome: The proposed methods improve the embeddings’ ability to capture nuanced semantic distinctions while reducing their expressiveness.
NuNER: Entity Recognition Encoder Pre-training via LLM-Annotated Data (2024.emnlp-main)

Copied to clipboard

Challenge: Named Entity Recognition (NER) is a core component of natural language processing, present in a variety of applications such as medical coding, financial news analysis, or legal documents parsing.
Approach: They propose to use Large Language Models (LLMs) to create NuNER, a compact language representation model specialized in the Named Entity Recognition task.
Outcome: The proposed model outperforms similar-sized foundation models in the few-shot regime and is based on a human-annotated dataset.
Improving Word Sense Induction through Adversarial Forgetting of Morphosyntactic Information (2024.starsem-1)

Copied to clipboard

Challenge: Contextualized word representations from pre-trained language models encode more information than is necessary for the identification of word senses and some of this information affect performance negatively in unsupervised settings.
Approach: They propose to use a framework to erase specific information from pre-trained word models and create feature-invariant representations that are invariant to these ‘nuisance features’.
Outcome: The proposed framework erases information from the representations of pre-trained language models, thereby creating feature-invariant representations.
Mandarinograd: A Chinese Collection of Winograd Schemas (2020.lrec-1)

Copied to clipboard

Challenge: Mandarinograd is a corpus of Winograd Schemas in Mandarin Chinese . WS are hard to collect and few datasets are publicly available .
Approach: They introduce a corpus of Winograd Schemas in Mandarin Chinese . they describe the difficulties faced when building the corpus and explain how they overcome the anomalies.
Outcome: The proposed corpus of Winograd Schemas in Mandarin Chinese is hard to build and resistant to statistical methods.
Tabouid: a Wikipedia-based word guessing game (2020.acl-demos)

Copied to clipboard

Challenge: Using Wikipedia articles, we generate word-guessing games using a set of NLP and machine-learning techniques.
Approach: They propose a system which uses Wikipedia to generate word-guessing games.
Outcome: The proposed game is based on Tabouid, a word-guessing board game originally published by Parker Brothers in 1989.
What Meaning-Form Correlation Has to Compose With: A Study of MFC on Artificial and Natural Language (2020.coling-main)

Copied to clipboard

Challenge: Compositionality is a widely discussed property of natural languages, although its exact definition has been elusive.
Approach: They propose that compositionality can be measured by measuring meaning-form correlation . they analyze three sets of languages: artificial toy languages tailored to be compositional .
Outcome: The proposed method can assess compositionality on three sets of languages . linguistic phenomena such as synonymy and ungrounded stop-words weigh on the results .
Multiple Tasks Integration: Tagging, Syntactic and Semantic Parsing as a Single Task (2021.eacl-main)

Copied to clipboard

Challenge: Existing systems that bypass intermediate levels of analysis are prone to error propagation and are therefore free from interference.
Approach: They propose a multitask paradigm orthogonal to weight sharing that uses multiple tasks to process input iteratively but concurrently at multiple levels of analysis.
Outcome: The proposed model uses reinforcement learning and release from sequential constraints to improve the quality of the syntactic and semantic parses.

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