Local-to-global learning for iterative training of production SLU models on new features

no code implementations • NAACL (ACL) 2022 • Yulia Grishina, Daniil Sorokin

First, we apply the original LGL schedule on our data and then adapt LGL to the production setting where the full data is not available at initial training iterations.

intent-classification Intent Classification +3

Data-Efficient Paraphrase Generation to Bootstrap Intent Classification and Slot Labeling for New Features in Task-Oriented Dialog Systems

no code implementations • COLING 2020 • Shailza Jolly, Tobias Falke, Caglar Tirkaz, Daniil Sorokin

Recent progress through advanced neural models pushed the performance of task-oriented dialog systems to almost perfect accuracy on existing benchmark datasets for intent classification and slot labeling.

intent-classification Intent Classification +1

Leveraging User Paraphrasing Behavior In Dialog Systems To Automatically Collect Annotations For Long-Tail Utterances

no code implementations • COLING 2020 • Tobias Falke, Markus Boese, Daniil Sorokin, Caglar Tirkaz, Patrick Lehnen

In large-scale commercial dialog systems, users express the same request in a wide variety of alternative ways with a long tail of less frequent alternatives.

Interactive Instance-based Evaluation of Knowledge Base Question Answering

1 code implementation • EMNLP 2018 • Daniil Sorokin, Iryna Gurevych

Most approaches to Knowledge Base Question Answering are based on semantic parsing.

Entity Linking Knowledge Base Question Answering +1

Frame- and Entity-Based Knowledge for Common-Sense Argumentative Reasoning

1 code implementation • WS 2018 • Teresa Botschen, Daniil Sorokin, Iryna Gurevych

Common-sense argumentative reasoning is a challenging task that requires holistic understanding of the argumentation where external knowledge about the world is hypothesized to play a key role.

Argument Mining Common Sense Reasoning +8

UKP-Athene: Multi-Sentence Textual Entailment for Claim Verification

1 code implementation • WS 2018 • Andreas Hanselowski, Hao Zhang, Zile Li, Daniil Sorokin, Benjamin Schiller, Claudia Schulz, Iryna Gurevych

The Fact Extraction and VERification (FEVER) shared task was launched to support the development of systems able to verify claims by extracting supporting or refuting facts from raw text.

Claim Verification Entity Linking +4

Modeling Semantics with Gated Graph Neural Networks for Knowledge Base Question Answering

1 code implementation • COLING 2018 • Daniil Sorokin, Iryna Gurevych

The most approaches to Knowledge Base Question Answering are based on semantic parsing.

Knowledge Base Question Answering Semantic Parsing

Mixing Context Granularities for Improved Entity Linking on Question Answering Data across Entity Categories

1 code implementation • SEMEVAL 2018 • Daniil Sorokin, Iryna Gurevych

We use the Wikidata knowledge base and available question answering datasets to create benchmarks for entity linking on question answering data.

Entity Disambiguation Entity Linking +1

Context-Aware Representations for Knowledge Base Relation Extraction

1 code implementation • EMNLP 2017 • Daniil Sorokin, Iryna Gurevych

We demonstrate that for sentence-level relation extraction it is beneficial to consider other relations in the sentential context while predicting the target relation.

Question Answering Relation +2

LSDSem 2017: Exploring Data Generation Methods for the Story Cloze Test

1 code implementation • WS 2017 • Michael Bugert, Yevgeniy Puzikov, Andreas R{\"u}ckl{\'e}, Judith Eckle-Kohler, Teresa Martin, Eugenio Mart{\'\i}nez-C{\'a}mara, Daniil Sorokin, Maxime Peyrard, Iryna Gurevych

The Story Cloze test is a recent effort in providing a common test scenario for text understanding systems.

Cloze Test