Aleksandr Chuklin
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Aleksandr Chuklin has a total of 19 co-authors. Here are the top co-authors by number of shared publications:
- Aliaksei Severyn
Google, Zurich, Switzerland
2 shared publications - Alexey Borisov
Samara National Research University Samara Russia
1 shared publication - Anne Schuth
University of Amsterdam, Amsterdam, The Netherlands
1 shared publication - Damiano Spina
RMIT University, Melbourne, Australia
1 shared publication - Daniil Mirylenka
Google, Zurich, Switzerland
1 shared publication Enrique Alfonseca
Google research
1 shared publication
Latest Publications
- Open Access
- 4 August 2023
- Published by Association for Computing Machinery (ACM)
- p. 5815-5816
Fast Text Generation with Text-Editing Models
Text-editing models have recently become a prominent alternative to seq2seq models for monolingual text-generation tasks such as grammatical error correction, simplification, and style transfer. These tasks share a common trait -- they exhibit a large amount of textual overlap between the source and target texts. Text-editing models take advantage of this observation and learn to generate the output by predicting edit operations applied to the source sequence. In contrast, seq2seq models generate outputs word-by-word from scratch thus making them slow at inference time. Text-editing models provide several benefits over seq2seq models including faster inference speed, higher sample efficiency, and better control and explainability of the outputs. This tutorial provides a comprehensive overview of text-editing models and discusses how they can be used to mitigate hallucination and bias, both pressing challenges in the field of text generation. Finally, we discuss how to optimize latency of large language models via distillation to text-editing models and other means.
- 4 August 2023
- Published by Association for Computing Machinery (ACM)
- p. 5815-5816
Open AccessFast Text Generation with Text-Editing Models
Text-editing models have recently become a prominent alternative to seq2seq models for monolingual text-generation tasks such as grammatical error correction, simplification, and style transfer. These tasks share a common trait -- they exhibit a large amount of textual overlap between the source and target texts. Text-editing models take advantage of this observation and learn to generate the output by predicting edit operations applied to the source sequence. In contrast, seq2seq models generate outputs word-by-word from scratch thus making them slow at inference time. Text-editing models provide several benefits over seq2seq models including faster inference speed, higher sample efficiency, and better control and explainability of the outputs. This tutorial provides a comprehensive overview of text-editing models and discusses how they can be used to mitigate hallucination and bias, both pressing challenges in the field of text generation. Finally, we discuss how to optimize latency of large language models via distillation to text-editing models and other means.
- 3 August 2019
- Published by Springer Nature
- p. 164-170
Using Audio Transformations to Improve Comprehension in Voice Question Answering
- 3 August 2019
- Published by Springer Nature
- p. 164-170
Using Audio Transformations to Improve Comprehension in Voice Question Answering
- Open Access
- 1 October 2017
- Published by Association for Computing Machinery (ACM)
- p. 333-334
Search-Oriented Conversational AI (SCAI)
- 1 October 2017
- Published by Association for Computing Machinery (ACM)
- p. 333-334
Open AccessSearch-Oriented Conversational AI (SCAI)
- Open Access
- 17 February 2015
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 33 (2) , 1-38
A Comparative Analysis of Interleaving Methods for Aggregated Search
A result page of a modern search engine often goes beyond a simple list of “10 blue links.” Many specific user needs (e.g., News, Image, Video) are addressed by so-called aggregated or vertical search solutions: specially presented documents, often retrieved from specific sources, that stand out from the regular organic Web search results. When it comes to evaluating ranking systems, such complex result layouts raise their own challenges. This is especially true for so-called interleaving methods that have arisen as an important type of online evaluation: by mixing results from two different result pages, interleaving can easily break the desired Web layout in which vertical documents are grouped together, and hence hurt the user experience. We conduct an analysis of different interleaving methods as applied to aggregated search engine result pages. Apart from conventional interleaving methods, we propose two vertical-aware methods: one derived from the widely used Team-Draft Interleaving method by adjusting it in such a way that it respects vertical document groupings, and another based on the recently introduced Optimized Interleaving framework. We show that our proposed methods are better at preserving the user experience than existing interleaving methods while still performing well as a tool for comparing ranking systems. For evaluating our proposed vertical-aware interleaving methods, we use real-world click data as well as simulated clicks and simulated ranking systems.
- 17 February 2015
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 33 (2) , 1-38
Open AccessA Comparative Analysis of Interleaving Methods for Aggregated Search
A result page of a modern search engine often goes beyond a simple list of “10 blue links.” Many specific user needs (e.g., News, Image, Video) are addressed by so-called aggregated or vertical search solutions: specially presented documents, often retrieved from specific sources, that stand out from the regular organic Web search results. When it comes to evaluating ranking systems, such complex result layouts raise their own challenges. This is especially true for so-called interleaving methods that have arisen as an important type of online evaluation: by mixing results from two different result pages, interleaving can easily break the desired Web layout in which vertical documents are grouped together, and hence hurt the user experience. We conduct an analysis of different interleaving methods as applied to aggregated search engine result pages. Apart from conventional interleaving methods, we propose two vertical-aware methods: one derived from the widely used Team-Draft Interleaving method by adjusting it in such a way that it respects vertical document groupings, and another based on the recently introduced Optimized Interleaving framework. We show that our proposed methods are better at preserving the user experience than existing interleaving methods while still performing well as a tool for comparing ranking systems. For evaluating our proposed vertical-aware interleaving methods, we use real-world click data as well as simulated clicks and simulated ranking systems.