Papers by Pavel Smrz
Claim-Dissector: An Interpretable Fact-Checking System with Joint Re-ranking and Veracity Prediction (2023.findings-acl)
Copied to clipboard
| Challenge: | a novel latent variable model for fact-checking and analysis learns to identify the veracity of a claim and its relevant evidences. |
| Approach: | They propose to disentangle the per-evidence relevance probability and its contribution to the final veracity probability in an interpretable way. |
| Outcome: | The proposed model can achieve competitive results on the FEVER dataset while using significantly fewer parameters. |
BelarusianGLUE: Towards a Natural Language Understanding Benchmark for Belarusian (2025.acl-long)
Copied to clipboard
| Challenge: | Recent advances in NLP, such as large language models, have had groundbreaking impact on the field. |
| Approach: | They propose a benchmark for Belarusian, an East Slavic language, with 15K instances in five tasks: sentiment analysis, linguistic acceptability, word in context, Winograd schema challenge, textual entailment. |
| Outcome: | The proposed model underperforms on sentiment analysis, linguistic acceptability, word in context, Winograd schema challenge and textual entailment, but is competitive for linguistic acceptance. |
R2-D2: A Modular Baseline for Open-Domain Question Answering (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Using extractive and generative reader, we demonstrate its strength across three open-domain QA datasets: NaturalQuestions, TriviaQA and EfficientQA. |
| Approach: | They propose a four-stage open-domain QA pipeline with a retriever, passage reranker, extractive reader, generative reader and a mechanism that aggregates the final prediction from all system’s components. |
| Outcome: | The proposed pipeline outperforms state-of-the-art on three open-domain QA datasets and is twice as effective as the posterior averaging ensemble of the same models with different parameters. |