[Applications closed] ERC PhD in ML/NLP – information extraction, critical citations, claims and counter-claims in scholarly communication and social networks

• Location: LIG laboratory (Grenoble, France)
• Start date: 1 November 2022
• Contract duration: 36-month fixed-term contract 
• Application deadline: 20 June 2022
• Interview date : 28 June 2022 (preferably)
• Reporting line: Cyril Labbé, Frédérique Bordignon, François Portet

Keywords: natural language processing, citation classification, transfer learning, deep learning

Context

The NanoBubbles ERC project objective is to understand how, when and why science fails to correct itself. The project’s focus is nanobiology and it combines approaches from the natural, computer science, and social sciences and the humanities (Science and Technology Studies) to understand how error correction in science works and what obstacles it faces. For this purpose, we aim to trace claims and corrections in various channels of scientific communication (journals, social media, advertisements, conference programs, etc.) via natural language processing.
The challenge is to analyse the rapidly evolving ecology of online comments complementary to scientific records.

Project objectives

Although there is a consensus that scientific knowledge is constructed through critical debate, critical citations are rare in the scientific literature and difficult to identify. Nevertheless, it can be hypothesized that they would constitute a means of detecting controversy about a particular topic, including the retrieval of claims and counter-claims. The PhD student will have to explore this line of research by taking advantage of classification and citation polarity detection methods. But since controversy often takes place outside of the scholarly communication arena, he/she will also have to explore alternative important sources such as PubPeer, Twitter and specialized blogs.

Recent works in NLP [Bakhti2018,Jurgens2016,Pride2019,Yu2020] explore citation behaviours and habits. New large language models [Zhang2022] may be useful to explore approaches suited to understand error correction in the field of nanobiology,
Information extraction is useful in other domains such as medicine [Kocabiyikoglu2021], errors detection [Park2022,Labbe2020] or Natural Language Understanding [Desot2022], for instance.

Skills

• Master 2 in Natural Language Processing, computer science or data science.
• Programming experience in Python and in a deep learning framework.
• Previous experience in NER, RE and dataset manipulation would be a plus.

Scientific environment

The thesis will be conducted within the Sigma and Getalp teams of the LIG laboratory (http://sigma.imag.fr/ and https://lig-getalp.imag.fr/). The GETALP team has strong expertise and track record in Natural Language Processing, SIGMA team strong expertise in Database and NLP. The recruited person will be welcomed within the teams which offer a stimulating, multinational and pleasant working environment. The means to carry out the PhD will be provided both in terms of missions in France and abroad and in terms of equipment (personal computer, access to the LIG GPU servers).
The PhD student will collaborate with several team members involved in the ERC Nanobubbles project, in particular with researchers from the LISIS lab (Marne-la-vallée, France), University of Sorbonne Paris-Nord as well as researchers from Maastricht University, Radboud Universiteit and University of Twente based in the Netherlands.

Instructions for applying

Applications are expected until July 5th, 2021. They must contain: CV + letter/message of motivation + master notes + be ready to provide letter(s) of recommendation; and be addressed to Cyril Labbé (cyril.labbe@imag.fr), François Portet (francois.Portet@imag.fr) and Frédérique Bordignon (frederique.bordignon@enpc.fr).

We celebrate diversity and are committed to creating an inclusive environment for all employees.

Applications will be considered case-by-case. It is therefore advised to apply as soon as possible.

References:

• [Bakhti2018] Bakhti, K., Niu, Z., Yousif, A., & Nyamawe, A. S. (2018). Citation function classification based on ontologies and convolutional neural networks. In International Workshop on Learning Technology for Education in Cloud (pp. 105-115). Springer, Cham.
• [Bordignon22] F. Bordignon. (2022). Critical citations in knowledge construction and citation analysis: from paradox to definition. Scientometrics, Springer Verlag.
• [Desot 2022] Desot, T., Portet, F., & Vacher, M. (2022). End-to-End Spoken Language Understanding: Performance analyses of a voice command task in a low resource setting. Computer Speech & Language, 75, 101369.
• [Jurgens2016] Jurgens, D., Kumar, S., Hoover, R., McFarland, D., & Jurafsky, D. (2016). Citation classification for behavioral analysis of a scientific field. arXiv preprint arXiv:1609.00435.
• [Kocabiyikoglu2021] Kocabiyikoglu, A. C., Babouchkine, J. M., Portet, F., & Qader, R. (2021). Neural Medication Extraction: A Comparison of Recent Models in Supervised and Semi-supervised Learning Settings. In 2021 IEEE 9th International Conference on Healthcare Informatics (ICHI) (pp. 148-152). IEEE.
• [Labbe2020]Labbé, C., Cabanac, G., West, R.A. et al. (2020). Flagging incorrect nucleotide sequence reagents in biomedical papers: To what extent does the leading publication format impede automatic error detection?. Scientometrics 124, 1139–1156.
• [Pride2019] Pride, D., Knoth, P., & Harag, J. (2019). ACT: an annotation platform for citation typing at scale. In 2019 ACM/IEEE Joint Conference on Digital Libraries (JCDL)
  (pp. 329-330). IEEE.
• [Park2022] Y. Park, R. A West, P. Pathmendra, B. Favier, T. Stoeger, A. Capes-Davis, G. Cabanac, C. Labbé, J. A Byrne, Incorrect nucleotide sequence reagents, Life Science Alliance Jan 2022
• [Yu2020] Yu, W., Yu, M., Zhao, T., & Jiang, M. (2020). Identifying referential intention with heterogeneous contexts. In Proceedings of The Web Conference 2020 (pp. 962-972).
• [Zhang2022] Zhang, Susan, et al. “OPT: Open Pre-trained Transformer Language Models.” arXiv preprint arXiv:2205.01068 (2022).