Team DOMLIN: Exploiting Evidence Enhancement for the FEVER Shared Task

Stammbach, Dominik; Neumann, Guenter

doi:10.18653/v1/d19-6616

Cited by 35 publications

(32 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Evidence sentence retrieval component in almost all previous works retrieves all the evidences through a single iteration (Yoneda et al, 2018;Hanselowski et al, 2018b;Nie et al, 2019;Chen et al, 2017;Soleimani et al, 2020;Liu et al, 2020). Stammbach and Neumann (2019) uses a multi-hop retrieval strategy through two iterations to retrieve evidence sentences that are conditioned on the retrieval of other evidence sentences. Then, they choose all the top-most relevant evidence sentences with the highest relevance scores and combine them.…”

Section: Related Workmentioning

confidence: 99%

“…In claim verification component, Nie et al (2019); Yoneda et al (2018); Hanselowski et al (2018b) use a modified ESIM model (Chen et al, 2017) for verification. Recent works (Soleimani et al, 2020;Zhou et al, 2019;Stammbach and Neumann, 2019) use BERT model (Devlin et al, 2019) for claim verification. Few other works (Zhou et al, 2019;Liu et al, 2020) use graph based models for fine-grained semantic reasoning.…”

Section: Related Workmentioning

confidence: 99%

Section: Multi-hop Evidence Retrievalmentioning

confidence: 99%

“…As shown in Table 2, we compare the performance of our model with two baselines, UNC NLP (Nie et al, 2019) and BERT based model (Stammbach and Neumann, 2019). UNC NLP uses ESIM (Chen et al, 2017) based model, and Stammbach and Neumann (2019) uses a BERT based model. Since most other previous works either use ESIM based model or BERT based model for evidence retrieval, we compare with these two representative baselines (i.e., the results of the other 5 baselines in evidence retrieval would be similar to one of them).…”

Section: Multi-hop Evidence Retrievalmentioning

confidence: 99%

See 3 more Smart Citations

Hierarchical Evidence Set Modeling for Automated Fact Extraction and Verification

Subramanian¹,

Lee²

2020

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

View full text Add to dashboard Cite

Automated fact extraction and verification is a challenging task that involves finding relevant evidence sentences from a reliable corpus to verify the truthfulness of a claim. Existing models either (i) concatenate all the evidence sentences, leading to the inclusion of redundant and noisy information; or (ii) process each claim-evidence sentence pair separately and aggregate all of them later, missing the early combination of related sentences for more accurate claim verification. Unlike the prior works, in this paper, we propose Hierarchical Evidence Set Modeling (HESM), a framework to extract evidence sets (each of which may contain multiple evidence sentences), and verify a claim to be supported, refuted or not enough info, by encoding and attending the claim and evidence sets at different levels of hierarchy. Our experimental results show that HESM outperforms 7 state-of-the-art methods for fact extraction and claim verification. Our source code is available at https://github.com/ ShyamSubramanian/HESM. ClaimWentworth is an Australian television series. Wentworth [TV series]A sixth season was commissioned by Foxtel on 9 May 2017. Foxtel Foxtel is an Australian pay television company. Wentworth [TV series] It was first broadcast on SoHo on 1 May 2013. Verdict Supports / Refutes / Not Enough Info Verdict Supports / Refutes / Not Enough Info SoHo [TV channel] SoHo was an Australian cable and satellite channel.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Multi-hop Evidence Retrievalmentioning

confidence: 99%

Section: Multi-hop Evidence Retrievalmentioning

confidence: 99%

See 2 more Smart Citations

Hierarchical Evidence Set Modeling for Automated Fact Extraction and Verification

Subramanian¹,

Lee²

2020

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

View full text Add to dashboard Cite

show abstract

“…Team DOMLIN (Stammbach and Neumann, 2019) used the document retrieval module of Hanselowski et al (2018) and a BERT model for two-staged sentence selection based on the work by (Nie et al, 2019). They also use a BERT-based model for the NLI stage.…”

Section: Builders Phasementioning

confidence: 99%

The FEVER2.0 Shared Task

Thorne¹,

Vlachos²,

Cocarascu³

et al. 2019

Proceedings of the Second Workshop on Fact Extraction and VERification (FEVER)

View full text Add to dashboard Cite

We present the results of the second Fact Extraction and VERification (FEVER2.0) Shared Task. The task challenged participants to both build systems to verify factoid claims using evidence retrieved from Wikipedia and to generate adversarial attacks against other participant's systems. The shared task had three phases: building, breaking and fixing. There were 8 systems in the builder's round, three of which were new qualifying submissions for this shared task, and 5 adversaries generated instances designed to induce classification errors and one builder submitted a fixed system which had higher FEVER score and resilience than their first submission. All but one newly submitted systems attained FEVER scores higher than the best performing system from the first shared task and under adversarial evaluation, all systems exhibited losses in FEVER score. There was a great variety in adversarial attack types as well as the techniques used to generate the attacks, In this paper, we present the results of the shared task and a summary of the systems, highlighting commonalities and innovations among participating systems.

show abstract

Artificially Intelligent Solutions: Detection, Debunking, and Fact-Checking

Rubin

2022

Misinformation and Disinformation

View full text Add to dashboard Cite

Team DOMLIN: Exploiting Evidence Enhancement for the FEVER Shared Task

Cited by 35 publications

References 9 publications

Hierarchical Evidence Set Modeling for Automated Fact Extraction and Verification

Hierarchical Evidence Set Modeling for Automated Fact Extraction and Verification

The FEVER2.0 Shared Task

Artificially Intelligent Solutions: Detection, Debunking, and Fact-Checking

Contact Info

Product

Resources

About