Papers by Cecile Paris
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
Fanzhen Liu, Sharif Abuadbba, Kristen Moore, Surya Nepal, Cecile Paris, Jia Wu, Jian Yang, Quan Z. Sheng
| 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. |