--- title: "Participation d'EDF R&D à DEFT 2018 (Here the title in English)" description: "EDF R&D entered the DEFT 2018 challenge on French tweets about public transport in Île-de-France. 8 references." authors: ["Philippe Suignard", "Lou Charaudeau", "Manel Boumghar", "Meryl Bothua", "Delphine Lagarde"] year: 2018 venue: "Actes de la Conférence TALN. Volume 2 - Démonstrations, articles des Rencontres Jeunes Chercheurs, ateliers DeFT" source: "https://aclanthology.org/2018.jeptalnrecital-deft.2/" licence: "CC BY 4.0 (ACL Anthology)" licence_url: "https://creativecommons.org/licenses/by/4.0/" summary_licence: "Elamur Cosmic License" canonical: "https://research.elamur.ai/free/en/papers/suignard-2018-participation-d-edf-r-d/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/suignard-2018-participation-d-edf-r-d/) [home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2018](https://md.research.elamur.ai/free/en/papers/2018/page/8/) / Participation d'EDF R&D à DEFT 2018 (Here the title in English) # Participation d'EDF R&D à DEFT 2018 (Here the title in English) **Authors:** Philippe Suignard, Lou Charaudeau, Manel Boumghar, Meryl Bothua and Delphine Lagarde · **Year:** 2018 · **Venue:** [Actes de la Conférence TALN. Volume 2 - Démonstrations, articles des Rencontres Jeunes Chercheurs, ateliers DeFT](https://md.research.elamur.ai/free/en/venues/jeptalnrecital/) ([JEP-TALN-RECITAL (the French-speaking conferences on speech and natural language processing) 2018](https://md.research.elamur.ai/free/en/venues/jeptalnrecital/2018/)) · **Publisher:** [ATALA](https://md.research.elamur.ai/free/en/publishers/atala/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/) **Links:** [Publisher's page](https://aclanthology.org/2018.jeptalnrecital-deft.2/) · [PDF](https://aclanthology.org/2018.jeptalnrecital-deft.2.pdf) · [OpenAlex](https://openalex.org/W3081868753) **Citations:** 0 citations (OpenAlex, 2026-10-14) ## Summary EDF R&D entered the DEFT 2018 challenge on French tweets about public transport in Île-de-France. They took part in two tasks: telling transport tweets apart from unrelated ones (T1), and assigning an overall polarity to transport tweets (T2: positive, negative, neutral or mixed). They used only the official "simple" corpus of about 54,000 tweets, split 80/20 for training and validation, with no outside data. They compared three approaches: - a Word2Vec model trained with category labels inserted as pseudo-words, from which similarity-based features feed WEKA classifiers; - LSTM networks; - CNN networks. For the LSTM and CNN runs, tweets were first enriched with polarity tags from small hand-built lexicons. Every submitted run scored above the campaign mean. On T1 the Word2Vec pipeline was narrowly best. On T2 the LSTM led with F≈0.80. The team placed 5th of 11 on T1 and 4th of 12 on T2, the top non-academic entrant. The authors see the methods as easy to reuse for other short-text classification needs, such as separating EDF the utility from EDF the national football team. ## Key points - **Data handling:** The ~14,000-tweet "batch_b" corpus was discarded because every item carried the label "inconnu". Final predictions were made on 7,816 evaluation tweets. - **Word2Vec setup:** skip-gram, window of 5, 200 dimensions, hierarchical softmax, minimum word frequency 30, 1000 iterations, plus a stop-list. Similarity statistics gave 14 features for T1 and 44 for T2. The features were fed to Logistic Regression and Random Forest. - **Polarity lexicons:** 121 positive and 291 negative entries, emoticons included. The tags they injected improved training accuracy by roughly 5%. - **LSTM settings:** - T1: embedding 150, padding 40, hidden size 60. - T2: embedding 300, padding 40, hidden size 100, with 20% dropout. - **CNN settings:** embedding 300, filter and pooling windows of 5 words. - **T2 F-measures:** | Run | F-measure | |---|---| | LSTM | 0.80249 | | CNN | 0.80067 | | LSTM with reduced vocabulary | 0.79957 | | Word2Vec + Logistic Regression | 0.7435 | | Word2Vec + Random Forest | 0.73969 | | Campaign mean | 0.7293 | | Campaign max | 0.82288 | - **T1 result:** the Word2Vec run scored 0.90124, against a campaign mean of 0.88813 and a max of 0.90785. ## Interesting ideas - Wrapping each training sentence in its class label as an extra pseudo-token puts labels and words in one vector space, so similarity to a label becomes a cheap category signal. - Noisy text is normalised by collapsing repeated letters and replacing URLs, dates, clock times, durations and emoticons with typed placeholder tokens, which shrinks the vocabulary and absorbs many spelling variants. - To detect mixed polarity, the authors use the largest and smallest jumps in label similarity between successive words, treating a sharp internal contrast as evidence of mixed sentiment. - Lexicon matches are written straight into the text as inline tags, so a learned model receives symbolic hints without any architectural change, and this alone gave a measurable gain. - Each hyperparameter configuration was trained ten times, and both mean validation accuracy and mean loss were compared, rather than trusting a single lucky run. ## For Mova How these ideas could serve Mova, our small open language model — its files, stages and tests: - **I1** (world): candidate verb-class or frame memberships for rare verbs could be proposed this way and then kept only after explicit checks against VerbNet/WordNet entries. - **I2** (tokens): typed placeholders like DATE/DURATION could be emitted with a recorded original span, giving the tagger stable tokens while keeping the measure value for later stages. - **I3** (frames): a polarity-contrast signal across clauses could serve as one explainable cue for irony or concessive speech acts. - **I4** (learn): explicit lexicon or rule annotations could be injected as marker tokens into gparse training input, with a negative-control run without them to measure their real effect. - **I5** (learn): repeated seeded runs with averaged metrics would make parser or reader comparisons less noisy before a configuration is adopted. *Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.* 📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works 🧭 Topics (1): [English](https://md.research.elamur.ai/free/en/topics/english/) · 2,379 works ## Cite Cite as: Philippe Suignard, Lou Charaudeau, Manel Boumghar, Meryl Bothua and Delphine Lagarde. 2018. Participation d'EDF R&D à DEFT 2018 (Here the title in English). Actes de la Conférence TALN. Volume 2 - Démonstrations, articles des Rencontres Jeunes Chercheurs, ateliers DeFT. The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @inproceedings{suignard2018participation, title = {{Participation d'EDF R\&D à DEFT 2018 (Here the title in English)}}, author = {Philippe Suignard, Lou Charaudeau, Manel Boumghar, Meryl Bothua and Delphine Lagarde}, booktitle = {Actes de la Conférence TALN. Volume 2 - Démonstrations, articles des Rencontres Jeunes Chercheurs, ateliers DeFT}, year = {2018}, url = {https://aclanthology.org/2018.jeptalnrecital-deft.2/} } ``` - [← previous Making sense: The glamorous history of English grammar (a review)](https://md.research.elamur.ai/free/en/papers/tomalin-2018-making-sense-glamorous-history-english/) - [next → Resolving scope ambiguity in written texts (English data)](https://md.research.elamur.ai/free/en/papers/apresyan-2018-resolving-scope-ambiguity-written/) - [↑ back to papers of 2018](https://md.research.elamur.ai/free/en/papers/2018/page/8/) ## References 8 references, 3 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. D AUPHIN Y. N., F AN , A., A ULI M., & G RANGIER D. (2016). [Language modeling with gated convolutional networks](https://md.research.elamur.ai/free/en/papers/dauphin-2016-language-modeling-gated-convolutional-networks/). arXiv preprint arXiv:1612.08083. [↗](https://arxiv.org/abs/1612.08083) 2. H ALL M., F RANK E., H OLMES G., P FAHRINGER B., R EUTEMANN P., & W ITTEN I.H. (2009). The WEKA data mining software: an update. ACM SIGKDD explorations newsletter, 11(1), 10-18. [find](https://scholar.google.com/scholar?q=H+ALL+M%2E%2C+F+RANK+E%2E%2C+H+OLMES+G%2E%2C+P+FAHRINGER+B%2E%2C+R+EUTEMANN+P%2E%2C+%26+W+ITTEN+I%2EH%2E+%282009%29%2E+The+WEKA+data+mining+software%3A+an+update%2E+ACM+SIGKDD+explorations+newsletter%2C+11%281%29%2C+10%2D18%2E) 3. H OCHREITER .S, AND S CHMIDHUBER J. “Long short-term memory.” Neural computation 9.8 (1997): 1735-1780. [find](https://scholar.google.com/scholar?q=H+OCHREITER+%2ES%2C+AND+S+CHMIDHUBER+J%2E+%E2%80%9CLong+short%2Dterm+memory%2E%E2%80%9D+Neural+computation+9%2E8+%281997%29%3A+1735%2D1780%2E) 4. L E C UN Y., B OTTOU L., B ENGIO Y., & H AFFNER P. (1998). Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11), 2278-2324. [find](https://scholar.google.com/scholar?q=L+E+C+UN+Y%2E%2C+B+OTTOU+L%2E%2C+B+ENGIO+Y%2E%2C+%26+H+AFFNER+P%2E+%281998%29%2E+Gradient%2Dbased+learning+applied+to+document+recognition%2E+Proceedings+of+the+IEEE%2C+86%2811%29%2C+2278%2D2324%2E) 5. M IKOLOV T., S UTSKEVER I., C HEN K., C ORRADO G. S., & D EAN J. (2013). [Distributed representations of words and phrases and their compositionality](https://md.research.elamur.ai/free/en/papers/mikolov-2013-distributed-representations-words-phrases-their/). In Advances in neural information processing systems (pp. 3111-3119). 6. M IKOLOV T., C HEN K., C ORRADO G., & D EAN J. (2013). [Efficient estimation of word representations in vector space](https://md.research.elamur.ai/free/en/papers/mikolov-2013-efficient-estimation-word-representations-vector/). arXiv preprint arXiv:1301.3781. P AROUBEK P., G ROUIN C., B ELLOT P., C LAVEAU V., E SHKOL -T ARAVELLA I., F RAISSE A., J ACKIEWICZ A., K AROUI J., M ONCEAUX L., T ORRES -M ORENO J.M. DEFT2018 : recherche d’information et analyse de sentiments dans des tweets concernant les transports en Île de France. In: Actes de DEFT. Rennes, France. [↗](https://arxiv.org/abs/1301.3781) 7. W ENPENG Y., K ATHARINA K., M O Y., H INRICH S. (2017) Comparative study of CNN and RNN for language processing. AR X IV PREPRINT AR X IV :1702.01923. [find](https://scholar.google.com/scholar?q=W+ENPENG+Y%2E%2C+K+ATHARINA+K%2E%2C+M+O+Y%2E%2C+H+INRICH+S%2E+%282017%29+Comparative+study+of+CNN+and+RNN+for+language+processing%2E+AR+X+IV+PREPRINT+AR+X+IV+%3A1702%2E01923%2E) 8. X ING L., & P AUL M. J. (2017). Incorporating Metadata into Content-Based User Embeddings. In Proceedings of the 3rd Workshop on Noisy User-generated Text (pp. 45-49). [find](https://scholar.google.com/scholar?q=X+ING+L%2E%2C+%26+P+AUL+M%2E+J%2E+%282017%29%2E+Incorporating+Metadata+into+Content%2DBased+User+Embeddings%2E+In+Proceedings+of+the+3rd+Workshop+on+Noisy+User%2Dgenerated+Text+%28pp%2E+45%2D49%29%2E) *Updated 2 November 2026*