Dense retrievers have demonstrated significant potential for neural information retrieval; however, they exhibit a lack of robustness to domain shifts, thereby limiting their efficacy in zero-shot settings across diverse domains. Previous research has investigated unsupervised domain adaptation techniques to adapt dense retrievers to target domains. However, these studies have not focused on explainability analysis to understand how such adaptations alter the model's behavior. In this paper, we propose utilizing the integrated gradients framework to develop an interpretability method that provides both instance-based and ranking-based explanations for dense retrievers. To generate these explanations, we introduce a novel baseline that reveals both query and document attributions. This method is used to analyze the effects of domain adaptation on input attributions for query and document tokens across two datasets: the financial question answering dataset (FIQA) and the biomedical information retrieval dataset (TREC-COVID). Our visualizations reveal that domain-adapted models focus more on in-domain terminology compared to non-adapted models, exemplified by terms such as "hedge," "gold," "corona," and "disease." This research addresses how unsupervised domain adaptation techniques influence the behavior of dense retrievers when adapted to new domains. Additionally, we demonstrate that integrated gradients are a viable choice for explaining and analyzing the internal mechanisms of these opaque neural models.
Information retrieval (IR) is essential in biomedical knowledge acquisition and clinical decision support. While recent progress has shown that language model encoders perform better semantic retrieval, training such models requires abundant query-article annotations that are difficult to obtain in biomedicine. As a result, most biomedical IR systems only conduct lexical matching. In response, we introduce MedCPT, a first-of-its-kind Contrastively Pre-trained Transformer model for zero-shot semantic IR in biomedicine. To train MedCPT, we collected an unprecedented scale of 255 million user click logs from PubMed. With such data, we use contrastive learning to train a pair of closely-integrated retriever and re-ranker. Experimental results show that MedCPT sets new state-of-the-art performance on six biomedical IR tasks, outperforming various baselines including much larger models such as GPT-3-sized cpt-text-XL. In addition, MedCPT also generates better biomedical article and sentence representations for semantic evaluations. As such, MedCPT can be readily applied to various real-world biomedical IR tasks.
ChatGPT has drawn considerable attention from both the general public and domain experts with its remarkable text generation capabilities. This has subsequently led to the emergence of diverse applications in the field of biomedicine and health. In this work, we examine the diverse applications of large language models (LLMs), such as ChatGPT, in biomedicine and health. Specifically we explore the areas of biomedical information retrieval, question answering, medical text summarization, information extraction, and medical education, and investigate whether LLMs possess the transformative power to revolutionize these tasks or whether the distinct complexities of biomedical domain presents unique challenges. Following an extensive literature survey, we find that significant advances have been made in the field of text generation tasks, surpassing the previous state-of-the-art methods. For other applications, the advances have been modest. Overall, LLMs have not yet revolutionized biomedicine, but recent rapid progress indicates that such methods hold great potential to provide valuable means for accelerating discovery and improving health. We also find that the use of LLMs, like ChatGPT, in the fields of biomedicine and health entails various risks and challenges, including fabricated information in its generated responses, as well as legal and privacy concerns associated with sensitive patient data. We believe this survey can provide a comprehensive and timely overview to biomedical researchers and healthcare practitioners on the opportunities and challenges associated with using ChatGPT and other LLMs for transforming biomedicine and health.
Language models have become increasingly popular in recent years for tasks like information retrieval. As use-cases become oriented toward specific domains, fine-tuning becomes default for standard performance. To fine-tune these models for specific tasks and datasets, it is necessary to carefully tune the model's hyperparameters and training techniques. In this paper, we present an in-depth analysis of the performance of four transformer-based language models on the task of biomedical information retrieval. The models we consider are DeepMind's RETRO (7B parameters), GPT-J (6B parameters), GPT-3 (175B parameters), and BLOOM (176B parameters). We compare their performance on the basis of relevance, accuracy, and interpretability, using a large corpus of 480000 research papers on protein structure/function prediction as our dataset. Our findings suggest that smaller models, with <10B parameters and fine-tuned on domain-specific datasets, tend to outperform larger language models on highly specific questions in terms of accuracy, relevancy, and interpretability by a significant margin (+50% on average). However, larger models do provide generally better results on broader prompts.
Recent work has shown that small distilled language models are strong competitors to models that are orders of magnitude larger and slower in a wide range of information retrieval tasks. This has made distilled and dense models, due to latency constraints, the go-to choice for deployment in real-world retrieval applications. In this work, we question this practice by showing that the number of parameters and early query-document interaction play a significant role in the generalization ability of retrieval models. Our experiments show that increasing model size results in marginal gains on in-domain test sets, but much larger gains in new domains never seen during fine-tuning. Furthermore, we show that rerankers largely outperform dense ones of similar size in several tasks. Our largest reranker reaches the state of the art in 12 of the 18 datasets of the Benchmark-IR (BEIR) and surpasses the previous state of the art by 3 average points. Finally, we confirm that in-domain effectiveness is not a good indicator of zero-shot effectiveness. Code is available at https://github.com/guilhermemr04/scaling-zero-shot-retrieval.git
Decoder transformers have continued increasing in scale reaching hundreds of billions of parameters. Due to their scale the same decoder sets state-of-the-art results on various language tasks via prompting or fine-tuning. Yet, these large foundation models remain unusable for the related fields of semantic search and sentence embeddings. This prevents possibly new state-of-the-art results and forces organizations to train and maintain separate models. To this end, we propose SGPT to use decoders for sentence embeddings and semantic search via prompting or fine-tuning. At 5.8 billion parameters SGPT improves on the previously best sentence embeddings by a margin of 7% and outperforms a concurrent method with 175 billion parameters as measured on the BEIR search benchmark. Code, models and result files are freely available at https://github.com/Muennighoff/sgpt.
Information retrieval (IR) is essential in search engines and dialogue systems as well as natural language processing tasks such as open-domain question answering. IR serve an important function in the biomedical domain, where content and sources of scientific knowledge may evolve rapidly. Although neural retrievers have surpassed traditional IR approaches such as TF-IDF and BM25 in standard open-domain question answering tasks, they are still found lacking in the biomedical domain. In this paper, we seek to improve information retrieval (IR) using neural retrievers (NR) in the biomedical domain, and achieve this goal using a three-pronged approach. First, to tackle the relative lack of data in the biomedical domain, we propose a template-based question generation method that can be leveraged to train neural retriever models. Second, we develop two novel pre-training tasks that are closely aligned to the downstream task of information retrieval. Third, we introduce the ``Poly-DPR'' model which encodes each context into multiple context vectors. Extensive experiments and analysis on the BioASQ challenge suggest that our proposed method leads to large gains over existing neural approaches and beats BM25 in the small-corpus setting. We show that BM25 and our method can complement each other, and a simple hybrid model leads to further gains in the large corpus setting.
Here we study the semantic search and retrieval problem in biomedical digital libraries. First, we introduce MedGraph, a knowledge graph embedding-based method that provides semantic relevance retrieval and ranking for the biomedical literature indexed in PubMed. Second, we evaluate our method using PubMed's Best Match algorithm. Moreover, we compare our method MedGraph to a traditional TFIDF based algorithm. We use a dataset extracted from PubMed, including 30 million articles' metadata such as abstracts, author information, citation information, and extracted biological entity mentions. We do that by pulling a subset of the dataset to evaluate MedGraph using predefined queries with ground truth ranked results. To our knowledge, this technique has not been explored before in biomedical information retrieval. In addition, our results provide evidence that semantic approaches to search and relevance in biomedical digital libraries that rely on knowledge graph modeling offer better search relevance results when compared with traditional approaches in terms of objective metrics.
Existing neural information retrieval (IR) models have often been studied in homogeneous and narrow settings, which has considerably limited insights into their out-of-distribution (OOD) generalization capabilities. To address this, and to facilitate researchers to broadly evaluate the effectiveness of their models, we introduce Benchmarking-IR (BEIR), a robust and heterogeneous evaluation benchmark for information retrieval. We leverage a careful selection of 18 publicly available datasets from diverse text retrieval tasks and domains and evaluate 10 state-of-the-art retrieval systems including lexical, sparse, dense, late-interaction and re-ranking architectures on the BEIR benchmark. Our results show BM25 is a robust baseline and re-ranking and late-interaction-based models on average achieve the best zero-shot performances, however, at high computational costs. In contrast, dense and sparse-retrieval models are computationally more efficient but often underperform other approaches, highlighting the considerable room for improvement in their generalization capabilities. We hope this framework allows us to better evaluate and understand existing retrieval systems, and contributes to accelerating progress towards better robust and generalizable systems in the future. BEIR is publicly available at https://github.com/UKPLab/beir.
Speculation is a naturally occurring phenomena in textual data, forming an integral component of many systems, especially in the biomedical information retrieval domain. Previous work addressing cue detection and scope resolution (the two subtasks of speculation detection) have ranged from rule-based systems to deep learning-based approaches. In this paper, we apply three popular transformer-based architectures, BERT, XLNet and RoBERTa to this task, on two publicly available datasets, BioScope Corpus and SFU Review Corpus, reporting substantial improvements over previously reported results (by at least 0.29 F1 points on cue detection and 4.27 F1 points on scope resolution). We also experiment with joint training of the model on multiple datasets, which outperforms the single dataset training approach by a good margin. We observe that XLNet consistently outperforms BERT and RoBERTa, contrary to results on other benchmark datasets. To confirm this observation, we apply XLNet and RoBERTa to negation detection and scope resolution, reporting state-of-the-art results on negation scope resolution for the BioScope Corpus (increase of 3.16 F1 points on the BioScope Full Papers, 0.06 F1 points on the BioScope Abstracts) and the SFU Review Corpus (increase of 0.3 F1 points).
Representation learning provides new and powerful graph analytical approaches and tools for the highly valued data science challenge of mining knowledge graphs. Since previous graph analytical methods have mostly focused on homogeneous graphs, an important current challenge is extending this methodology for richly heterogeneous graphs and knowledge domains. The biomedical sciences are such a domain, reflecting the complexity of biology, with entities such as genes, proteins, drugs, diseases, and phenotypes, and relationships such as gene co-expression, biochemical regulation, and biomolecular inhibition or activation. Therefore, the semantics of edges and nodes are critical for representation learning and knowledge discovery in real world biomedical problems. In this paper, we propose the edge2vec model, which represents graphs considering edge semantics. An edge-type transition matrix is trained by an Expectation-Maximization approach, and a stochastic gradient descent model is employed to learn node embedding on a heterogeneous graph via the trained transition matrix. edge2vec is validated on three biomedical domain tasks: biomedical entity classification, compound-gene bioactivity prediction, and biomedical information retrieval. Results show that by considering edge-types into node embedding learning in heterogeneous graphs, \textbf{edge2vec}\ significantly outperforms state-of-the-art models on all three tasks. We propose this method for its added value relative to existing graph analytical methodology, and in the real world context of biomedical knowledge discovery applicability.
Publications in the life sciences are characterized by a large technical vocabulary, with many lexical and semantic variations for expressing the same concept. Towards addressing the problem of relevance in biomedical literature search, we introduce a deep learning model for the relevance of a document's text to a keyword style query. Limited by a relatively small amount of training data, the model uses pre-trained word embeddings. With these, the model first computes a variable-length Delta matrix between the query and document, representing a difference between the two texts, which is then passed through a deep convolution stage followed by a deep feed-forward network to compute a relevance score. This results in a fast model suitable for use in an online search engine. The model is robust and outperforms comparable state-of-the-art deep learning approaches.