Papers by Cecile Paris

13 papers
Lifelong Explainer for Lifelong Learners (2021.emnlp-main)

Copied to clipboard

Challenge: Existing explanation methods are inefficient when explaining a static black-box model.
Approach: They propose a Lifelong Explanation approach that continuously trains a student explainer under the supervision of a teacher on different tasks undertaken in LL.
Outcome: The proposed approach can be extended to include a teacher and maintain the same level of faithfulness to the black-box model as the student explainer while being up to 102 times faster at test time.
Presentation Matters: How to Communicate Science in the NLP Venues and in the Wild? (2024.acl-tutorials)

Copied to clipboard

Challenge: a tutorial on communication skills is being proposed to help early career researchers . the tutorial would cover writing, oral presentation and social media presence .
Approach: a tutorial on communication skills is proposed to help early career researchers . the tutorial would cover writing, oral presentation and social media presence .
Outcome: a new tutorial will cover communication skills, including writing, oral presentation and social media presence . the tutorial will allow attendees to ask questions and clarify their research .
NNE: A Dataset for Nested Named Entity Recognition in English Newswire (P19-1)

Copied to clipboard

Challenge: Named entity recognition (NER) is widely used in downstream tasks but most tools focus on flat mention structure over coarse schemas.
Approach: They describe a fine-grained, nested named entity dataset over the Wall Street Journal portion of the Penn Treebank.
Outcome: The proposed dataset comprises 279,795 mentions of 114 entity types with up to 6 layers of nesting.
Using Similarity Measures to Select Pretraining Data for NER (N19-1)

Copied to clipboard

Challenge: Existing studies on how to select appropriate data to pretrain word vectors or LMs are lacking.
Approach: They propose to quantify aspects of similarity between pretraining and target data.
Outcome: The proposed measures are good predictors of the usefulness of pretrained models for Named Entity Recognition over 30 data pairs.
Figurative Usage Detection of Symptom Words to Improve Personal Health Mention Detection (P19-1)

Copied to clipboard

Challenge: Past work in personal health mention detection uses classification-based methods with human-engineered features or word embedding-based features.
Approach: They propose to combine a pipeline-based and a feature augmentation-based approach to combine personal health mention detection with figurative usage detection to improve the accuracy of the prediction.
Outcome: The proposed method improves the F-score of personal health mention detection by 2.21% over the pipeline-based approach and feature augmentation-based approaches.
Do Text-to-Vis Benchmarks Test Real Use of Visualisations? (2024.emnlp-main)

Copied to clipboard

Challenge: Existing benchmarks for visualisations are limited and do not reflect real-world use.
Approach: They analysed visualisation code from Python, R, Javascript, and Vega to find similarities and differences between real-world and benchmark datasets.
Outcome: The results show that benchmark datasets do not test the same distribution of chart types, attributes, and actions as real-world examples.
An Effective Transition-based Model for Discontinuous NER (2020.acl-main)

Copied to clipboard

Challenge: Named Entity Recognition (NER) data sets often contain mentions consisting of discontinuous spans.
Approach: They propose a transition-based model with generic neural encoding for discontinuous NER that can recognize discontinuous mentions without sacrificing the accuracy on continuous mentions.
Outcome: The proposed model can recognize discontinuous mentions without sacrificing accuracy on continuous mentions.
Recognising Agreement and Disagreement between Stances with Reason Comparing Networks (P19-1)

Copied to clipboard

Challenge: Existing methods for (dis)agreement detection focus on conversational settings . however, non-dialogic stance-bearing utterances are common in real-world scenarios .
Approach: They propose a reason comparing network to leverage reason information for stance comparison.
Outcome: The proposed method outperforms baselines on a well-known stance corpus.
Assessing Social License to Operate from the Public Discourse on Social Media (2020.coling-industry)

Copied to clipboard

Challenge: Social License to Operate (SLO) is the level of support organisations gain from the public.
Approach: They propose to extract and transform peoples’ stances towards an organisation into SLO levels by performing a chain of three text classification tasks.
Outcome: The proposed system extracts and transforms peoples’ stances towards an organisation into SLO levels.
Reevaluating Argument Component Extraction in Low Resource Settings (D19-61)

Copied to clipboard

Challenge: Argument component extraction is a challenging and complex high-level semantic extraction task.
Approach: They propose to use character-level, GloVe, ELMo, and BERT encodings to compare arguments extracted using standard BiLSTM-CRF encoders.
Outcome: The proposed approaches perform better than baselines in higher-level semantic extraction tasks and suggest future improvements.
Cost-effective Selection of Pretraining Data: A Case Study of Pretraining BERT on Social Media (2020.findings-emnlp)

Copied to clipboard

Challenge: Recent studies show that domain-specific BERT models can be improved when in-domain data is used for pretraining.
Approach: They propose to use Twitter and forum text as pretraining sources for two BERT models and use similarity measures to nominate in-domain data for pretraining.
Outcome: The proposed method can be used to improve performance on downstream tasks by using in-domain data.
Adversarial Attacks Against Automated Fact-Checking: A Survey (2025.emnlp-main)

Copied to clipboard

Challenge: Existing fact-checking systems are vulnerable to adversarial attacks that manipulate or generate claims, evidence, or claim-evidence pairs.
Approach: They examine the impact of adversarial attacks on existing AFC systems and examine their impact on existing ones.
Outcome: The findings highlight the need for resilient fact-checking frameworks in limiting misinformation spread and supporting public trust.
Learning to Explain: Generating Stable Explanations Fast (2021.acl-long)

Copied to clipboard

Challenge: Existing methods for explaining outcome of machine learning models produce explanations, or rationales, which identify the attributions of features in an input example.
Approach: They propose a Learning to Explain approach that learns the behaviour of an underlying explanation algorithm simultaneously from all training examples.
Outcome: The proposed approach is 5 to 7.5104 times faster than existing models and has comparable faithfulness to the black-box model.

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