On the Interpolation of Contextualized Term-based Ranking with BM25 for Query-by-Example Retrieval

Abolghasemi, Amin; Askari, Arian; Verberne, Suzan

doi:10.1145/3539813.3545133

Cited by 9 publications

(4 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is noteworthy to mention that in this paper, we concentrate on analyzing the improvement by combining the first-stage retriever and a BERT-based re-ranker: BM25 and CE CAT respectively. However, we are aware that combining scores of BM25 and Dense Retrievers that both are first-stage retrievers has also shown improvements [70][71][72] that are outside the scope of our study. In particular, CLEAR [10] proposes an approach to train the dense retrievers to encode semantics that BM25 fails to capture for first stage retrieval.…”

Section: Methods For Combining Rankersmentioning

confidence: 89%

Injecting the score of the first-stage retriever as text improves BERT-based re-rankers

Askari,

Abolghasemi,

Pasi

et al. 2024

Discov Computing

Self Cite

View full text Add to dashboard Cite

In this paper we propose a novel approach for combining first-stage lexical retrieval models and Transformer-based re-rankers: we inject the relevance score of the lexical model as a token into the input of the cross-encoder re-ranker. It was shown in prior work that interpolation between the relevance score of lexical and Bidirectional Encoder Representations from Transformers (BERT) based re-rankers may not consistently result in higher effectiveness. Our idea is motivated by the finding that BERT models can capture numeric information. We compare several representations of the Best Match 25 (BM25) and Dense Passage Retrieval (DPR) scores and inject them as text in the input of four different cross-encoders. Since knowledge distillation, i.e., teacher-student training, proved to be highly effective for cross-encoder re-rankers, we additionally analyze the effect of injecting the relevance score into the student model while training the model by three larger teacher models. Evaluation on the MSMARCO Passage collection and the TREC DL collections shows that the proposed method significantly improves over all cross-encoder re-rankers as well as the common interpolation methods. We show that the improvement is consistent for all query types. We also find an improvement in exact matching capabilities over both the first-stage rankers and the cross-encoders. Our findings indicate that cross-encoder re-rankers can efficiently be improved without additional computational burden or extra steps in the pipeline by adding the output of the first-stage ranker to the model input. This effect is robust for different models and query types.

show abstract

Section: Methods For Combining Rankersmentioning

confidence: 89%

Injecting the score of the first-stage retriever as text improves BERT-based re-rankers

Askari,

Abolghasemi,

Pasi

et al. 2024

Discov Computing

Self Cite

View full text Add to dashboard Cite

show abstract

“…It is noteworthy to mention that in this paper, we concentrate on analyzing the improvement by combining the first-stage retriever and a BERT-based re-ranker: BM25 and CE CAT respectively. However, we are aware that combining scores of BM25 and Dense Retrievers that both are first-stage retrievers has also shown improvements [39][40][41] that are outside the scope of our study. In particular, CLEAR [10] proposes an approach to train the dense retrievers to encode semantics that BM25 fails to capture for first stage retrieval.…”

Section: Methods For Combining Rankersmentioning

confidence: 89%

Injecting the Score of the First-stage Retriever as Text Improves BERT-Based Re-rankers

Askari,

Abolghasemi,

Pasi

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

In this paper we propose a novel approach for combining first-stage lexical retrieval models and Transformer-based re-rankers: we inject the relevance score of the lexical model as a token into the the input of the cross-encoder re-ranker. It was shown in prior work that interpolation between the relevance score of lexical and BERT-based re-rankers may not consistently result in higher effectiveness. Our idea is motivated by the finding that BERT models can capture numeric information. We compare several representations of the BM25 and Dense Passage Retrieval (DPR) scores and inject them as text in the input of four different cross-encoders. Since knowledge distillation, i.e., teacher-student training, proved to be highly effective for cross-encoder re-rankers, we additionally analyze the effect of injecting the relevance score into the student model while training the model by three larger teacher models. Evaluation on the MSMARCO Passage collection and the TREC DL collections shows that the proposed method significantly improves over all cross-encoder re-rankers as well as the common interpolation methods. We show that the improvement is consistent for all query types. We also find an improvement in exact matching capabilities over both the first-stage rankers and the cross-encoders. Our findings indicate that cross-encoder re-rankers can efficiently be improved without additional computational burden or extra steps in the pipeline by adding the output of the first-stage ranker to the model input. This effect is robust for different models and query types.

show abstract

“…It is noteworthy to mention that in this paper, we concentrate on analyzing the improvement by combining the first-stage retriever and a BERT-based re-ranker: BM25 and CE CAT respectively. However, we are aware that combining scores of BM25 and Dense Retrievers that both are first-stage retrievers has also shown improvements [55,1,6] that are outside the scope of our study. In particular, CLEAR [20] proposes an approach to train the dense retrievers to encode semantics that BM25 fails to capture for first stage retrieval.…”

Section: Related Workmentioning

confidence: 89%

Injecting the BM25 Score as Text Improves BERT-Based Re-rankers

Askari¹,

Abolghasemi²,

Pasi³

et al. 2023

Preprint

View full text Add to dashboard Cite

In this paper we propose a novel approach for combining first-stage lexical retrieval models and Transformer-based re-rankers: we inject the relevance score of the lexical model as a token in the middle of the input of the cross-encoder re-ranker. It was shown in prior work that interpolation between the relevance score of lexical and BERT-based rerankers may not consistently result in higher effectiveness. Our idea is motivated by the finding that BERT models can capture numeric information. We compare several representations of the BM25 score and inject them as text in the input of four different cross-encoders. We additionally analyze the effect for different query types, and investigate the effectiveness of our method for capturing exact matching relevance. Evaluation on the MSMARCO Passage collection and the TREC DL collections shows that the proposed method significantly improves over all cross-encoder re-rankers as well as the common interpolation methods. We show that the improvement is consistent for all query types. We also find an improvement in exact matching capabilities over both BM25 and the cross-encoders. Our findings indicate that cross-encoder re-rankers can efficiently be improved without additional computational burden and extra steps in the pipeline by explicitly adding the output of the first-stage ranker to the model input, and this effect is robust for different models and query types.

show abstract

On the Interpolation of Contextualized Term-based Ranking with BM25 for Query-by-Example Retrieval

Cited by 9 publications

References 22 publications

Injecting the score of the first-stage retriever as text improves BERT-based re-rankers

Injecting the score of the first-stage retriever as text improves BERT-based re-rankers

Injecting the Score of the First-stage Retriever as Text Improves BERT-Based Re-rankers

Injecting the BM25 Score as Text Improves BERT-Based Re-rankers

Contact Info

Product

Resources

About