Papers by Philippe Langlais

18 papers
Extracting Parallel Sentences with Bidirectional Recurrent Neural Networks to Improve Machine Translation (C18-1)

Copied to clipboard

Challenge: Parallel sentence extraction is a task addressing the data sparsity problem found in multilingual natural language processing applications.
Approach: They propose a bidirectional recurrent neural network based approach to extract parallel sentences from multilingual corpora.
Outcome: The proposed approach outperforms existing approaches on noisy parallel corpora and shows significant improvements in translation performance.
Context-aware Adversarial Training for Name Regularity Bias in Named Entity Recognition (2021.tacl-1)

Copied to clipboard

Challenge: Name Regularity Bias is a problem in NER models that use contextual information to predict the type of an ambiguous entity.
Approach: They propose a model-agnostic training method that adds learnable adversarial noise to some entity mentions to improve their accuracy.
Outcome: The proposed method outperforms feature-based models on name regularity bias . it adds learnable adversarial noise to some entity mentions, leading to gains .
Effective Data Augmentation for Sentence Classification Using One VAE per Class (2022.coling-1)

Copied to clipboard

Challenge: Variational auto-encoders and its conditional variant the Conditional-VAE (CVAE) are often used to generate new textual data, but they require more complex manipulations to ensure that the generated examples are useful.
Approach: They propose a simple way to use Variational Auto-Encoders (VAE) for data augmentation by training one VAE per class.
Outcome: The proposed method outperforms generative models on binary classification tasks and several dataset sizes on four different tasks.
RW-KD: Sample-wise Loss Terms Re-Weighting for Knowledge Distillation (2021.findings-emnlp)

Copied to clipboard

Challenge: Knowledge Distillation (KD) is used to compress the pre-training and task-specific fine-tuning phases of large neural language models.
Approach: They propose a sample-wise loss weighting method that re-weights the two losses for each sample.
Outcome: The proposed method outperforms existing methods on 7 datasets of the GLUE benchmark.
CHARP: Conversation History AwaReness Probing for Knowledge-grounded Dialogue Systems (2024.findings-acl)

Copied to clipboard

Challenge: CHARP is a testbed for knowledge-grounded dialogue evaluation of models trained on FaithDial data.
Approach: They propose a testbed for evaluating models trained on FaithDial with annotation artifacts that may bias models towards completely ignoring the conversation history.
Outcome: The proposed model fails to accurately evaluate the conversational history and lacks hallucination detection.
SC-LSTM: Learning Task-Specific Representations in Multi-Task Learning for Sequence Labeling (N19-1)

Copied to clipboard

Challenge: Multi-task learning (MTL) has been studied for sequence labeling tasks . auxiliary tasks are selected specifically to improve performance of a target task .
Approach: They propose a shared-cell long-short-term memory cell which contains shared parameters that can learn from all tasks and task-specific parameters that could learn task-related information.
Outcome: The proposed model can learn from all tasks and task-specific parameters.
EUROPA: A Legal Multilingual Keyphrase Generation Dataset (2024.acl-long)

Copied to clipboard

Challenge: Keyphrases are short phrases that describe a text and have been used for many applications.
Approach: They present a dataset for multilingual keyphrase generation in the legal domain . it is derived from legal judgments from the Court of Justice of the European Union . they run multilingual models on the corpus and analyze the results .
Outcome: The proposed dataset shows that it is better than existing models and can capture larger input context.
A Methodology for Building a Diachronic Dataset of Semantic Shifts and its Application to QC-FR-Diac-V1.0, a Free Reference for French (2022.lrec-1)

Copied to clipboard

Challenge: Existing algorithms to detect semantic shifts have been criticized for their difficulty in evaluating them.
Approach: They propose a method for building a reference dataset for semantic shift detection . they use a word-sense disambiguation model to associate a date of first appearance to all senses of a term .
Outcome: The proposed method is based on a word-sense disambiguation model . significant changes in sense distributions and stability are detected . the resulting words are inspected by experts using a dedicated interface .
Revisiting the Task of Scoring Open IE Relations (L18-1)

Copied to clipboard

Challenge: Recent Open Information Extraction systems allow us to extract ever larger (yet incomplete) open-domain Knowledge Bases from text.
Approach: They propose a baseline model which gives competitive results in a previously defined protocol and provides an independent source of signal to judge arbitrary fact plausibility.
Outcome: The proposed model gives competitive results in the previously defined protocol and provides an independent source of signal to judge arbitrary fact plausibility.
Unsupervised multiple-choice question generation for out-of-domain Q&A fine-tuning (2022.acl-short)

Copied to clipboard

Challenge: Pre-trained models have shown very good performances on a number of question answering benchmarks especially when fine-tuned on multiple question answering datasets at once.
Approach: They propose an approach to fine-tune a question-answering dataset using a rule-based algorithm that generates questions and answers from unannotated sentences.
Outcome: The proposed model can generate questions and answers from unannotated sentences on a multiple-choice physics, biology and chemistry benchmark.
ReGLA: Refining Gated Linear Attention (2025.naacl-long)

Copied to clipboard

Challenge: Recent advances in Large Language Models (LLMs) are known for their computational and storage requirements due to the quadratic computation complexity of softmax attention.
Approach: They propose to reduce the quadratic computation complexity of softmax attention by using feature maps, normalization and the gating mechanism to improve performance.
Outcome: The proposed model outperforms existing gated linear attention models in extensive tasks including training from scratch and post-linearization with continual pre-training.
Transforming Wikipedia into a Large-Scale Fine-Grained Entity Type Corpus (L18-1)

Copied to clipboard

Challenge: et al. (2017): WiFiNE annotated with fine-grained entity types . lack of a well-established training corpus makes it difficult to manually annotate the amount of data needed for training.
Approach: They propose an English corpus annotated with fine-grained entity types based on Wikipedia . they use heuristics to build a large, high quality, annotating corpus using 2 manually annotized benchmarks .
Outcome: The proposed system outperforms the existing systems with two datasets and gains a 2.8 macro F1 score.
Is ChatGPT the ultimate Data Augmentation Algorithm? (2023.findings-emnlp)

Copied to clipboard

Challenge: Recent research has examined the use of ChatGPT for data augmentation, but only in limited contexts.
Approach: They use ChatGPT to create new data with paraphrasing and zero-shot generation to compare it to seven other algorithms.
Outcome: The proposed model performs exceptionally well on some simpler data, but it does not perform better than the other algorithms.
RAIL-KD: RAndom Intermediate Layer Mapping for Knowledge Distillation (2022.findings-naacl)

Copied to clipboard

Challenge: Existing methods for intermediate layer knowledge distillation suffer from computational burdens and engineering efforts for setting up a proper layer mapping.
Approach: They propose a method where intermediate layers from teacher and student models are randomly selected to be distilled into intermediate layers of student models.
Outcome: The proposed method outperforms state-of-the-art intermediate layer knowledge distillation methods on GLUE tasks and out-of domain test sets.
On Evaluation Protocols for Data Augmentation in a Limited Data Scenario (2025.coling-main)

Copied to clipboard

Challenge: Textual data augmentation (DA) is a prolific field of study where novel techniques to create artificial data are regularly proposed.
Approach: They propose to use textual data augmentation (DA) to generate new sentences for text classification in a limited data setting.
Outcome: The proposed methods perform better on small data settings and on large datasets, but they are not as effective on large data sets.
A linguistically-motivated evaluation methodology for unraveling model’s abilities in reading comprehension tasks (2024.emnlp-main)

Copied to clipboard

Challenge: Existing models fail for linguistic characteristics of input examples, despite the impressive quantity of scientific studies dedicated to them, the capabilities, limitations, and risks of these models remain largely unknown.
Approach: They propose to use semantic frame annotation to characterize examples by a small number of complexity factors to account for model’s difficulty.
Outcome: The proposed evaluation methodology is based on the intuition that certain examples consistently yield lower scores regardless of model size or architecture.
BenchIE^FL: A Manually Re-Annotated Fact-Based Open Information Extraction Benchmark (2024.findings-acl)

Copied to clipboard

Challenge: Numerous OIE systems claim ever-increasing performance, limiting their effectiveness.
Approach: They propose a benchmark which fully enforces the principles of BenchIE while containing fewer errors, omissions and shortcomings when candidate facts are matched towards reference ones.
Outcome: The proposed benchmark aims to improve the performance of OIE extractors while avoiding errors and omissions.
CHARPEVAL: Benchmarking Large Language Models’ Contextual Reasoning in Knowledge-Grounded Dialogue (2025.findings-acl)

Copied to clipboard

Challenge: Existing benchmarks that evaluate the ability of Large Language Models (LLMs) to perform contextualized reasoning in knowledge-grounded dialogue scenarios are lacking.
Approach: They propose a benchmark to evaluate the ability of Large Language Models to perform contextualized reasoning in knowledge-grounded dialogue scenarios.
Outcome: The proposed benchmark shows that open-weight LLMs are ineffective at reasoning over discontinuous chunks of text across the input.

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