Pavel Braslavski

Characterizing health-related community question answering

Our ongoing project is aimed at improving information access to narrow-domain collections of questions and answers. This poster demonstrates how out-of-the-box tools and domain dictionaries can be applied to community question answering (CQA) content in health domain. This approach can be used to improve user interfaces and search over CQA data, as well as to evaluate content quality. The study is a first-time use of a sizable dataset from the Russian CQA site Otvety@Mail.Ru.

Advances in information retrieval: 35th European Conference on IR Research, ECIR 2013, Moscow, Russia, March 24-27, 2013: proceedings

User Aspects.- Multimedia and Cross-Media IR.- Data Mining.- IR Theory and Formal Models.- IR System Architectures.- Classification.- Web.- Event Detection.- Temporal IR.- Microblog Search.

Towards Automatic Evaluation of Health-Related CQA Data

The paper reports on evaluation of Russian community question answering (CQA) data in health domain. About 1,500 question–answer pairs were manually evaluated by medical professionals, in addition automatic evaluation based on reference disease–medicine pairs was performed. Although the results of the manual and automatic evaluation do not fully match, we find the method still promising and propose several improvements. Automatic processing can be used to dynamically monitor the quality of the CQA content and to compare different data sources. Moreover, the approach can be useful for symptomatic surveillance and health education campaigns.

What Do You Mean Exactly?: Analyzing Clarification Questions in CQA

Search as a dialogue is an emerging paradigm that is fueled by the proliferation of mobile devices and technological advances, e.g. in speech recognition and natural language processing. Such an interface allows search systems to engage in a dialogue with users aimed at fulfilling their information needs. One key capability required to make such search dialogues effective is asking clarification questions (CLARQ) proactively, when a users intent is not clear, which could help the system provide more useful responses. With this in mind, we explore the dialogues between the users on a community question answering (CQA) website as a rich repository of information-seeking interactions. In particular, we study the clarification questions asked by CQA users in two different domains, analyze their behavior, and the types of clarification questions asked. Our results suggest that the types of CLARQ are very diverse, while the questions themselves tend to be specific and require both domain- and general knowledge. However, focusing on popular CLARQ types and domains can be fruitful. As a first step towards automatic generation of clarification questions, we explore the problem of predicting the specific subject of a clarification question. Our findings can be useful for future improvements of intelligent dialog search and question answering systems.

How to Evaluate Humorous Response Generation, Seriously?

Nowadays natural language user interfaces, such as chatbots and conversational agents, are very common. A desirable trait of such applications is a sense of humor. It is, therefore, important to be able to measure quality of humorous responses. However, humor evaluation is hard since humor is highly subjective. To address this problem, we conducted an online evaluation of 30 dialog jokes from different sources by almost 300 participants -- volunteers and Mechanical Turk workers. We collected joke ratings along with participants» age, gender, and language proficiency. Results show that demographics and joke topics can partly explain variation in humor judgments. We expect that these insights will aid humor evaluation and interpretation. The findings can also be of interest for humor generation methods in conversational systems.

A Pinch of Humor for Short-Text Conversation: An Information Retrieval Approach

The paper describes a work in progress on humorous response generation for short-text conversation using information retrieval approach. We gathered a large collection of funny tweets and implemented three baseline retrieval models: BM25, the query term reweighting model based on syntactic parsing and named entity recognition, and the doc2vec similarity model. We evaluated these models in two ways: in situ on a popular community question answering platform and in laboratory settings. The approach proved to be promising: even simple search techniques demonstrated satisfactory performance. The collection, test questions, evaluation protocol, and assessors’ judgments create a ground for future research towards more sophisticated models.

Ten Months of Digital Reading: An Exploratory Log Study

We address digital reading practices in Russia analyzing 10 months of logging data from a commercial ebook mobile app. We describe the data and focus on three aspects: reading schedule, reading speed, and book abandonment. The exploratory study proves a high potential of the data and proposed approach.

Family Matters: Company Relations Extraction from Wikipedia

The study described in the paper deals with the extraction of relations between organizations from the Russian Wikipedia. We experiment with two data sources for supervised methods – manual annotations made from scratch and relations from infoboxes with subsequent sentence matching, as well as different feature sets and learning methods – SVM, CRF, and UIMA Ruta. Results show that the automatically obtained training data delivers worse results than manually annotated data, but the former approach is promising due to its scalability. Evaluation of relations extracted from a subset of Wikipedia pages that are mapped to the Russian state company registry proves that external sources can enrich and complement official databases.

7th Russian summer school in information retrieval (RuSSIR 2013)

The 7 Russian Summer School in Information Retrieval (RuSSIR 2013) was held on September 16-20, 2013 in Kazan, Russia. The school was co-organized by the Kazan Federal University and the Russian Information Retrieval Evaluation Seminar (ROMIP). The RuSSIR school series started in 2007 and has developed into a renowned academic event with solid international participation. Previously, RuSSIR took place in Yekaterinburg, Taganrog, Petrozavodsk, Voronezh, Saint Petersburg, and Yaroslavl. RuSSIR courses were taught by many prominent international researchers in IR and cognate areas. Kazan, about 800 km east of Moscow, has the population of about 1.1 million people and is one of the oldest Russian cities. Geographical and cultural aspects of both Europe and Asia come together here. Founded in 1804, Kazan University is the third oldest university in Russia. It has over 40,000 full-time students in 180 major degree programmes. Kazan University is the alma mater and life-long affiliation of the Russian mathematician Nikolai Lobachevsky (1792–1856), the developer of non-Euclidean geometry, a fact that was symbolised by a hyperbolic triangle on RuSSIR t-shirts. In 2013, the RuSSIR programme featured a track on audio and music IR alongside core information retrieval topics. This led to fruitful discussions among participants coming from different domains and allowed students to learn cross-disciplinary competencies. The school programme consisted of a plenary invited course, six courses running in two parallel sessions, two sponsor presentations, as well as the RuSSIR Young Scientist Conference. Music Hackathon, a co-located event with a focus on hands-on development, was an innovation of this year.

Report on the 11th Russian Summer School in Information Retrieval (RuSSIR 2017)

The 11 Russian Summer School in Information Retrieval (RuSSIR 2017) was held on August 21–25 in Yekaterinburg, Russia. The school was co-organized by Ural Federal University and the Russian Information Retrieval Evaluation Seminar (ROMIP). The RuSSIR school series started in 2007 and has evolved into a renowned academic event with extensive international participation [1, 2, 3, 4]. Previously, RuSSIR has taken place in Yekaterinburg, Taganrog, Petrozavodsk, Voronezh, St. Petersburg, Yaroslavl, Kazan, Nizhny Novgorod, and Saratov. Over the years, RuSSIR courses have been taught by world-renowned researchers in Information Retrieval (IR) and related areas. There were 91 students attending RuSSIR 2017, and about 120 participants in total (counting in students, teachers, organizers, and sponsors’ representatives). The majority of participants were from Russia, there were also representatives from the Netherlands, Belarus, Austria, Italy, Latvia, Portugal, United Kingdom, Australia, and Algeria. School participation was free of charge due to support from the school’s sponsors. In addition, five international students as well as two teachers received travel support from the European Science Foundation (ESF) through ELIAS network and ACM SIGIR. Moreover, seven accommodation grants were awarded to participants by organizers.