Papers by Alexis Nasr
Typological Features for Multilingual Delexicalised Dependency Parsing (N19-1)
Copied to clipboard
| Challenge: | Existing universal models to describe the syntax of languages are debated for decades . a new study examines the plausibility of universal grammars in dependency parsing . |
| Approach: | They propose to use typological features to describe the syntax of languages to train a multilingual dependency parser. |
| Outcome: | The proposed model can be trained on 40 languages with the help of typological features. |
Factual Knowledge Assessment of Language Models Using Distractors (2025.coling-main)
Copied to clipboard
Hichem Ammar Khodja, Abderrahmane Ait gueni ssaid, Frederic Bechet, Quentin Brabant, Alexis Nasr, Gwénolé Lecorvé
| Challenge: | Language models encode extensive factual knowledge within their parameters. |
| Approach: | They propose a new interpretable knowledge assessment method that leverages distractors to provide incorrect alternatives to the correct answer. |
| Outcome: | The proposed method shows that it is aligned with human judgment and stronger robustness to verbalization artifacts. |
Dependency Parsing with Backtracking using Deep Reinforcement Learning (2022.tacl-1)
Copied to clipboard
| Challenge: | Greedy algorithms for NLP such as transition-based parsing are prone to error propagation. |
| Approach: | They propose to allow transition-based parsing to backtrack in cases where evidence contradicts the current solution. |
| Outcome: | The proposed behavior can be implemented on POS tagging and dependency parsing . it shows that backtracking is an effective means to fight error propagation . |
SLICE: Supersense-based Lightweight Interpretable Contextual Embeddings (2020.coling-main)
Copied to clipboard
| Challenge: | Contextualised embeddings are a key component of human languages but their opaqueness makes it difficult to interpret their behaviour. |
| Approach: | They propose a weakly supervised method to learn interpretable embeddings from raw corpora and seed words. |
| Outcome: | The proposed model can represent both a word and its context as embeddings into the same compact space, whose dimensions correspond to interpretable supersenses. |
WikiFactDiff: A Large, Realistic, and Temporally Adaptable Dataset for Atomic Factual Knowledge Update in Causal Language Models (2024.lrec-main)
Copied to clipboard
| Challenge: | Factual update is a task of inserting, replacing, or removing facts in large language models. |
| Approach: | They present a dataset that describes the evolution of factual knowledge between two dates as a collection of simple facts divided into three categories: new, obsolete, and static. |
| Outcome: | The proposed dataset compares the state of the Wikidata knowledge base at 4 January 2021 and 27 February 2023. |
Investigating the Effect of Relative Positional Embeddings on AMR-to-Text Generation with Structural Adapters (2023.eacl-main)
Copied to clipboard
| Challenge: | Recent approaches to text generation from Abstract Meaning Representation (AMR) have been based on neural-centered encoderdecoder architectures. |
| Approach: | They propose a structure-aware adapter which injects the input graph connectivity within PLMs using Graph Neural Networks. |
| Outcome: | The proposed adapter is robust to a variety of approaches and can be used to generate Graph-to-Text representations. |
Adding Syntactic Annotations to Flickr30k Entities Corpus for Multimodal Ambiguous Prepositional-Phrase Attachment Resolution (L18-1)
Copied to clipboard
| Challenge: | Using visual features extracted from an image, we propose to study the joint processing of image and language features for the Preposition-Phrase attachment disambiguation task. |
| Approach: | They propose to add syntactic annotations to the captions of the Flickr30k Entities corpus to study the joint processing of image and language features for the Preposition-Phrase attachment disambiguation task. |
| Outcome: | The proposed framework is based on the captions of the Flickr30k Entities corpus and is automatically projected on their French and German translations. |
Evaluating Pretrained Causal Language Models for Synonymy (2025.findings-acl)
Copied to clipboard
| Challenge: | Despite the scaling of causal language models, the underlying basis of complex skills remains unclear. |
| Approach: | They propose that subjacent skills such as synonymy might be explained using linguistic concepts. |
| Outcome: | The proposed model recognizes synonymy but struggles to generate synonyms when prompted with relevant context. |
CALOR-QUEST : generating a training corpus for Machine Reading Comprehension models from shallow semantic annotations (D19-58)
Copied to clipboard
Frederic Bechet, Cindy Aloui, Delphine Charlet, Geraldine Damnati, Johannes Heinecke, Alexis Nasr, Frederic Herledan
| Challenge: | Recent large corpora of triplets have opened the door to supervised machine learning approaches for Question-Answering. |
| Approach: | They propose to generate questions from the semantic Frame analysis of large corpora using a CALOR-QUEST resource in French and use it to improve machine reading comprehension. |
| Outcome: | The proposed method generates questions from the semantic Frame analysis of large corpora and then tests them on the CALOR-QUEST resource in French. |
Handling Normalization Issues for Part-of-Speech Tagging of Online Conversational Text (L18-1)
Copied to clipboard
Géraldine Damnati, Jeremy Auguste, Alexis Nasr, Delphine Charlet, Johannes Heinecke, Frédéric Béchet
| Challenge: | a new approach to POS tagging noisy user generated text is proposed . word embeddings are trained on a noisy corpus to address both normalization and POS. |
| Approach: | They propose to use word embeddings to normalize text before tagging it, while a gated neural network based tagger handles the remaining errors. |
| Outcome: | The proposed approach normalizes some errors before tagging, while a gated neural network handles the remaining errors. |
Semantic Frame Parsing for Information Extraction : the CALOR corpus (L18-1)
Copied to clipboard
| Challenge: | a recent study compares the semantic parsing of encyclopedic history texts with the Berkeley FrameNet project. |
| Approach: | They propose to use Berkeley FrameNet to parse encyclopedic history texts . they use a sequence labeling model which optimizes frame identification and role segmentation . |
| Outcome: | The proposed approach leverages the manual annotation of larger corpora than full text parsing. |