[PlanetKR] Open PhD position at QWANT search engine and INRIA on Artificial Intelligence: Argument Mining and Emotions

villata villata at i3s.unice.fr
Thu Dec 14 22:15:15 EST 2017

==== Open PhD position at QWANT search engine and INRIA on Artificial Intelligence: Argument Mining and Emotions ====

--- About Inria ---

Inria, the French National Institute for computer science and applied mathematics, promotes "scientific excellence for technology transfer and society". Graduates from the world’s top universities, Inria's 2,700 employees rise to the challenges of digital sciences. With its open, agile model, Inria is able to explore original approaches with its partners in industry and academia and provide an efficient response to the multidisciplinary and application challenges of the digital transformation. Inria is the source of many innovations that add value and create jobs.

--- Context ---

The ANSWER project is leaded by the QWANT search engine and the INRIA Sophia Antipolis Méditerranée research center. This proposal is the winner of the "Grand Challenges du Numérique" (BPI) and aims to develop the new version of the search engine www.qwant.com with radical innovations in terms of search criteria, indexed content and privacy of users. The scientific and technological challenges addressed by the project consider several evolutions of the Web to adapt to them on the one hand (heterogeneity of data) and to anticipate them on the other hand (personalization and respect for privacy, increase in granularity and number of criteria for qualification of Web content). This job description describes one of the open positions within this project.

--- Assignment ---

This position will be attached to Inria. 
The field of emotion analysis and sentiment analysis is not new, and it is often oriented towards the analysis of the emotions of the users and the determination of the polarity of a text, i.e., the text is positive or negative. In the ANSWER project, we aim to tackle the opposite challenge, namely we aim to answer the following research question: how to indicate to the user which are the emotions characterizing the results of her search in order to make it a criterion of choice? We focus on powerful algorithms to define new criterions for filtering search results, i.e., the expression of a feeling in the answers found by the search engine. The final goal is to extract effective and scalable indicators of sentiment, emotions, and argumentative relations in order to offer the users additional means to filter the results selected by the search engine.

--- Main activities ---

Wa aim to address the above mentioned issue with an innovative approach, so that the textual elements to which we wish to associate a polarity will no longer be considered in their individuality but connected to each other by polarized relations to be analysed in a higher level setting. The three main tasks of this PhD thesis will be:

1) Automatic detection of emotions and sentiment in the text (i.e., the association of a positive/negative polarity to a paragraph based on the polarity of the terms present in the text).
2) From the annotated data in step (1), prediction of the polarity of relations between the text spans with the combination of argument mining methods for relation prediction and emotion detection techniques.
3) Active Learning approach to improve sentiment analysis algorithms, based on predicted relations predicted in step (2).

--- Skills ---

- Master degree in Computer Science or Computer Engineering is required.
- Programming skills.
- Basic knowledge of Natural Language Processing and Machine Learning is preferred. 
- Fluent English required, both oral and written.

--- Benefits package ---

- Subsidized catering service
- Partially-reimbursed public transport
- Sports facilities

--- Terms of the PhD position ---

Duration: 3 years.

Hosting team: WIMMICS (http://wimmics.inria.fr/) is a research team of Université Côte d’Azur - INRIA. The research fields of this team are graph-oriented knowledge representation, reasoning and operationalization to model and support actors, actions and interactions in web-based epistemic communities.

Location: I3S laboratory, Sophia Antipolis, France. Regular visits to the QWANT team in Nice have to be planned.

Salary: ~2000 euros/month (gross salary).

Applications : a curriculum vitae together with a motivation letter should be sent to Fabien Gandon (fabien.gandon at inria.fr) and Serena Villata (villata at i3s.unice.fr).

Deadline for applications: January 10th, 2018

More information about the PlanetKR mailing list