Krisztian Balog

PhD position in Language Modeling for Explainable AI

February 17, 2021May 20, 2021 by krisztianbalog

We have a PhD position, funded by SFI NorwAI, the new 8-year research-based innovation Center for AI Innovation.

AI-powered systems exhibit a growing degree of personalization when recommending content. Users, however, have little knowledge of how these systems work and what personal data they use. There is a need for transparency, in terms of (1) collecting and using personal data, and how it is used for inferring user preferences and (2) explaining and justifying the generated recommendations. The most human-like form of providing explanations is via natural language. This would allow users to better understand how their preferences are understood and interpreted by the system, and also correct it if necessary.

The main goal of the project is to develop novel models that enable semantically rich and context-dependent text-based explainability of user preferences and system recommendations, using either existing metadata or automatically extracted annotations. A starting point for generating explanations is template-based; later, this can be made more human-like using language generation techniques, using large-scale (pre-trained) language models.

Visit Jobbnorge for more information and application details (notice the requirement for a cover letter).
Application deadline: ~~March 15~~ June 1.

Highlights from 2020

January 18, 2021April 2, 2022 by krisztianbalog

A compilation of highlights from 2020:

Organized ICTIR’20 together with Vinay Setty and Trond Linjordet — due to COVID, as a virtual conference.
The Norwegian Research Center for AI Innovation (NorwAI) started its operations, where I lead the work package on Language Technology for AI. There will be 3 PhD positions at UiS.
Published papers that attracted attention, on user simulation (KDD’20), novel entity discovery (WWW’20), entity linking (SIGIR’20), and explanations (SIGIR’20).
Our submission, led by Vinay Setty, achieved top performance at the SMART Challenge.

PhD position in Conversational AI

November 2, 2020November 2, 2020 by krisztianbalog

I have a fully-funded PhD position in Conversational AI. This position is partially funded by an unrestricted gift from Google, and will be co-supervised by Google research scientist Filip Radlinski.

Conversational search is a newly emerging research area within AI that aims to provide access to digitally stored information by means of a conversational user interface. The goal of such systems is to effectively handle a wide range of requests expressed in natural language, with rich user-system dialogue as a crucial component for understanding the user’s intent and refining the answers.

The overall objective of this project is to develop a prototype conversational search system for supporting scholarly activities (Scholarly Conversational Assistant). Scholarly activities of interest include, among others, finding relevant research material, planning conference attendance, or finding relevant experts to serve as speakers, committee members, etc. You can find further details on the envisioned functionality of the Scholarly Conversational Assistant here.

Specific areas of functionality targeted in the project concern the modeling of user knowledge, adapting the assistant’s language usage accordingly, and system-initiated (proactive) notifications.

Visit Jobbnorge for more information and application details (notice the requirement for a cover letter).
Application deadline: Nov 26.

Three recent papers

August 24, 2020August 24, 2020 by krisztianbalog

I’m sharing in this post the preprints of three recent full papers, covering a diverse set of topics, that are to appear in the coming weeks.

The KDD’20 paper “Evaluating Conversational Recommender Systems via User Simulation” (w/ Shuo Zhang) [PDF] represents a new line of work that I’m really excited about. We develop a user simulator for evaluating conversational agents on an item recommendation task. Our user simulator aims to generate responses that a real human would give by considering both individual preferences and the general flow of interaction with the system. We compare three existing conversational recommender systems and show that our simulation methods can achieve high correlation with real users using both automatic evaluation measures and manual human assessments.

The ICTIR’20 paper “Sanitizing Synthetic Training Data Generation for Question Answering over Knowledge Graphs” (w/ Trond Linjordet) [PDF] studies template-based synthetic data generation for neural KGQA systems. We show that there is a leakage of information in current approaches between training and test splits, which affects performance. We raise a series of challenging questions around training models with synthetic (template-based) data using fair conditions, which extend beyond the particular flavor of question answering task we study here.

The CIKM’20 paper “Generating Categories for Sets of Entities” (w/ Shuo Zhang and Jamie Callan) [PDF] addresses problems associated with the maintenance of category systems of large knowledge repositories, like Wikipedia. We aim to aid knowledge editors in the manual process of expanding a category system. Given a set of entities, e.g., in a list or table, we generate suggestions for new categories, which are specific, important and non-redundant. In addition to generating category labels, we also find the appropriate place of these new categories in the hierarchy, by locating the parent nodes that should be extended.

Highlights from 2019

March 28, 2020August 18, 2020 by krisztianbalog

As a first post of 2020, it’s only fitting to start with a brief summary of highlights from 2019.

My sabbatical at Google came to an end in August, and I resumed my professor position at the University of Stavanger. However, I remain part-time affiliated with Google in a visiting researcher position for another year.
I joined NTNU as an Adjunct Professor in AI/NLP.
Two of my PhD students defended their PhD theses: Shuo Zhang and Darío Garigliotti.
Assoc. prof. Vinay Setty joined our research group.
I gave keynotes at ECIR’19 and at TPDL’19.
Together with Shuo Zhang, I gave a tutorial at SIGIR on Web Table Extraction, Retrieval and Augmentation. We also published this material as a survey paper at ACM TIST.