Abstract 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.

Retrieval with extremely long queries and documents is a well-known and challenging task in information retrieval and is commonly known as Query-by-Document (QBD) retrieval. Specifically designed Transformer models that can handle long input sequences have not shown high effectiveness in QBD tasks in previous work. We propose a Re-Ranker based on the novel Proportional Relevance Score (RPRS) to compute the relevance score between a query and the top- k candidate documents. Our extensive evaluation shows RPRS obtains significantly better results than the state-of-the-art models on five different datasets. Furthermore, RPRS is highly efficient, since all documents can be pre-processed, embedded, and indexed before query time that gives our re-ranker the advantage of having a complexity of O(N) , where N is the total number of sentences in the query and candidate documents. Furthermore, our method solves the problem of the low-resource training in QBD retrieval tasks as it does not need large amounts of training data and has only three parameters with a limited range that can be optimized with a grid search even if a small amount of labeled data is available. Our detailed analysis shows that RPRS benefits from covering the full length of candidate documents and queries.

Ranking with pre-trained language models (PLMs) has shown to be highly effective for various Information Retrieval tasks. Previous studies investigated the performance of these models in terms of effectiveness and efficiency. However, there is no prior work on evaluating PLM-based rankers in terms of their retrievability bias. In this paper, we evaluate the retrievability bias of PLM-based rankers with the use of synthetically generated queries. We compare the retrievability bias in two of the most common PLM-based rankers, a Bi-Encoder BERT ranker and a Cross-Encoder BERT re-ranker against BM25, which was found to be one of the least biased models in prior work. We conduct a series of experiments with which we explore the plausibility of using synthetic queries generated with a generative model, docT5query, in the evaluation of retrievability bias. Our experiments show promising results on the use of synthetically generated queries for the purpose of retrievability bias estimation. Moreover, we find that the estimated bias values resulting from synthetically generated queries are lower than the ones estimated with user-generated queries on the MS MARCO evaluation benchmark. This indicates that synthetically generated queries might cause less bias than user-generated queries and therefore, by using such queries in training PLM-based rankers, we might be able to reduce the retrievability bias in these models.

In this paper, we investigate the task of response ranking in conversational legal search. We propose a novel method for conversational passage response retrieval (ConvPR) for long conversations in domains with mixed levels of expertise. Conversational legal search is challenging because the domain includes long, multi-participant dialogues with domain-specific language. Furthermore, as opposed to other domains, there typically is a large knowledge gap between the questioner (a layperson) and the responders (lawyers), participating in the same conversation. We collect and release a large-scale real-world dataset called LegalConv with nearly one million legal conversations from a legal community question answering (CQA) platform. We address the particular challenges of processing legal conversations, with our novel Conversational Legal Longformer with Expertise-Aware Response Ranker, called CLosER. The proposed method has two main innovations compared to state-of-the-art methods for ConvPR: (i) Expertise-Aware Post-Training; a learning objective that takes into account the knowledge gap difference between participants to the conversation; and (ii) a simple but effective strategy for re-ordering the context utterances in long conversations to overcome the limitations of the sparse attention mechanism of the Longformer architecture. Evaluation on LegalConv shows that our proposed method substantially and significantly outperforms existing state-of-the-art models on the response selection task. Our analysis indicates that our Expertise-Aware PostTraining, i.e., continued pre-training or domain/task adaptation, plays an important role in the achieved effectiveness. Our proposed method is generalizable to other tasks with domain-specific challenges and can facilitate future research on conversational search in other domains.