Due to high annotation costs making the best use of existing human-created training data is an important research direction. We, therefore, carry out a systematic evaluation of transferability of BERT-based neural ranking models across five English datasets. Previous studies focused primarily on zero-shot and few-shot transfer from a large dataset to a dataset with a small number of queries. In contrast, each of our collections has a substantial number of queries, which enables a full-shot evaluation mode and improves reliability of our results. Furthermore, since source datasets licences often prohibit commercial use, we compare transfer learning to training on pseudo-labels generated by a BM25 scorer. We find that training on pseudo-labels -- possibly with subsequent fine-tuning using a modest number of annotated queries -- can produce a competitive or better model compared to transfer learning. Yet, it is necessary to improve the stability and/or effectiveness of the few-shot training, which, sometimes, can degrade performance of a pretrained model.
This paper studies the performances and behaviors of BERT in ranking tasks. We explore several different ways to leverage the pre-trained BERT and fine-tune it on two ranking tasks: MS MARCO passage reranking and TREC Web Track ad hoc document ranking. Experimental results on MS MARCO demonstrate the strong effectiveness of BERT in question-answering focused passage ranking tasks, as well as the fact that BERT is a strong interaction-based seq2seq matching model. Experimental results on TREC show the gaps between the BERT pre-trained on surrounding contexts and the needs of ad hoc document ran…
College of Information and Computer Sciences（信息与计算机科学学院）；University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）
The bidirectional encoder representations from transformers (BERT) model has recently advanced the state-of-the-art in passage re-ranking. In this paper, we analyze the results produced by a fine-tuned BERT model to better understand the reasons behind such substantial improvements. To this aim, we focus on the MS MARCO passage re-ranking dataset and provide potential reasons for the successes and failures of BERT for retrieval. In more detail, we empirically study a set of hypotheses and provide additional analysis to explain the successful performance of BERT.
Ranking is the most important component in a search system. Mostsearch systems deal with large amounts of natural language data,hence an effective ranking system requires a deep understandingof text semantics. Recently, deep learning based natural languageprocessing (deep NLP) models have generated promising results onranking systems. BERT is one of the most successful models thatlearn contextual embedding, which has been applied to capturecomplex query-document relations for search ranking. However,this is generally done by exhaustively interacting each query wordwith each document word, whic…
University of Chinese Academy of Sciences（中国科学院大学）；Institute of Software, Chinese Academy of Sciences（中国科学院软件研究所）；Amazon Alexa（亚马逊 Alexa）；Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）
Query expansion aims to mitigate the mismatch between the language used in a query and in a document. However, query expansion methods can suffer from introducing non-relevant information when expanding the query. To bridge this gap, inspired by recent advances in applying contextualized models like BERT to the document retrieval task, this paper proposes a novel query expansion model that leverages the strength of the BERT model to select relevant document chunks for expansion. In evaluation on the standard TREC Robust04 and GOV2 test collections, the proposed BERT-QE model significantly outp…
The quality of non-default ranking on e-commerce platforms, such as based on ascending item price or descending historical sales volume, often suffers from acute relevance problems, since the irrelevant items are much easier to be exposed at the top of the ranking results. In this work, we propose a two-stage ranking scheme, which first recalls wide range of candidate items through refined query/title keyword matching, and then classifies the recalled items using BERT-Large fine-tuned on human label data. We also implemented parallel prediction on multiple GPU hosts and a C++ tokenization cust…
The extraction of labels from radiology text reports enables large-scale training of medical imaging models. Existing approaches to report labeling typically rely either on sophisticated feature engineering based on medical domain knowledge or manual annotations by experts. In this work, we introduce a BERT-based approach to medical image report labeling that exploits both the scale of available rule-based systems and the quality of expert annotations. We demonstrate superior performance of a biomedically pretrained BERT model first trained on annotations of a rule-based labeler and then finet…
Web search engines focus on serving highly relevant results within hundreds of milliseconds. Pre-trained language transformer models such as BERT are therefore hard to use in this scenario due to their high computational demands. We present our real-time approach to the document ranking problem leveraging a BERT-based siamese architecture. The model is already deployed in a commercial search engine and it improves production performance by more than 3%. For further research and evaluation, we release DaReCzech, a unique data set of 1.6 million Czech user query-document pairs with manually assi…
New York University（纽约大学）；Facebook AI Research（Facebook人工智能研究院）
Recently, neural models pretrained on a language modeling task, such as ELMo (Peters et al., 2017), OpenAI GPT (Radford et al., 2018), and BERT (Devlin et al., 2018), have achieved impressive results on various natural language processing tasks such as question-answering and natural language inference. In this paper, we describe a simple re-implementation of BERT for query-based passage re-ranking. Our system is the state of the art on the TREC-CAR dataset and the top entry in the leaderboard of the MS MARCO passage retrieval task, outperforming the previous state of the art by 27% (relative) …
BERT-based text ranking models have dramatically advanced the state-of-the-art in ad-hoc retrieval, wherein most models tend to consider individual query-document pairs independently. In the mean time, the importance and usefulness to consider the cross-documents interactions and the query-specific characteristics in a ranking model have been repeatedly confirmed, mostly in the context of learning to rank. The BERT-based ranking model, however, has not been able to fully incorporate these two types of ranking context, thereby ignoring the inter-document relationships from the ranking and the d…
This paper describes a machine learning algorithm for document (re)ranking, in which queries and documents are firstly encoded using BERT [1], and on top of that a learning-to-rank (LTR) model constructed with TF-Ranking (TFR) [2] is applied to further optimize the ranking performance. This approach is proved to be effective in a public MS MARCO benchmark [3]. Our first two submissions achieve the best performance for the passage re-ranking task [4], and the second best performance for the passage full-ranking task as of April 10, 2020 [5]. To leverage the lately development of pre-trained lan…
Georgetown University（乔治城大学）；Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）；Allen Institute for Artificial Intelligence（艾伦人工智能研究所）
Although considerable attention has been given to neural ranking architectures recently, far less attention has been paid to the term representations that are used as input to these models. In this work, we investigate how two pretrained contextualized language models (ELMo and BERT) can be utilized for ad-hoc document ranking. Through experiments on TREC benchmarks, we find that several existing neural ranking architectures can benefit from the additional context provided by contextualized language models. Furthermore, we propose a joint approach that incorporates BERT's classification vector…
David R. Cheriton School of Computer Science, University of Waterloo（滑铁卢大学大卫·切里顿计算机科学学院）；University of Amsterdam（阿姆斯特丹大学）；Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）
The goal of text ranking is to generate an ordered list of texts retrieved from a corpus in response to a query. Although the most common formulation of text ranking is search, instances of the task can also be found in many natural language processing applications. This survey provides an overview of text ranking with neural network architectures known as transformers, of which BERT is the best-known example. The combination of transformers and self-supervised pretraining has been responsible for a paradigm shift in natural language processing (NLP), information retrieval (IR), and beyond. In…
Although considerable efforts have been devoted to transformer-based ranking models for document search, the relevance-efficiency tradeoff remains a critical problem for ad-hoc ranking. To overcome this challenge, this paper presents BECR (BERT-based Composite Re-Ranking), a composite re-ranking scheme that combines deep contextual token interactions and traditional lexical term-matching features. In particular, BECR exploits a token encoding mechanism to decompose the query representations into pre-computable uni-grams and skip-n-grams. By applying token encoding on top of a dual-encoder arch…
Recent progress in Natural Language Understanding (NLU) is driving fast-paced advances in Information Retrieval (IR), largely owed to fine-tuning deep language models (LMs) for document ranking. While remarkably effective, the ranking models based on these LMs increase computational cost by orders of magnitude over prior approaches, particularly as they must feed each query-document pair through a massive neural network to compute a single relevance score. To tackle this, we present ColBERT, a novel ranking model that adapts deep LMs (in particular, BERT) for efficient retrieval. ColBERT intro…
BERT-based re-ranking and dense retrieval (DR) systems have been shown to improve search effectiveness for spoken content retrieval (SCR). However, both methods can still show a reduction in effectiveness when using ASR transcripts in comparison to accurate manual transcripts. We find that a known-item search task on the How2 dataset of spoken instruction videos shows a reduction in mean reciprocal rank (MRR) scores of 10-14%. As a potential method to reduce this disparity, we investigate the use of semi-supervised ASR transcripts and N-best ASR transcripts to mitigate ASR errors for spoken se…
Passage retrieval and ranking is a key task in open-domain question answering and information retrieval. Current effective approaches mostly rely on pre-trained deep language model-based retrievers and rankers. These methods have been shown to effectively model the semantic matching between queries and passages, also in presence of keyword mismatch, i.e. passages that are relevant to a query but do not contain important query keywords. In this paper we consider the Dense Retriever (DR), a passage retrieval method, and the BERT re-ranker, a popular passage re-ranking method. In this context, we…
School of Biomedical Informatics, The University of Texas Health Science Center at Houston（德克萨斯大学休斯顿健康科学中心生物医学信息学院）
Developing high-performance entity normalization algorithms that can alleviate the term variation problem is of great interest to the biomedical community. Although deep learning-based methods have been successfully applied to biomedical entity normalization, they often depend on traditional context-independent word embeddings. Bidirectional Encoder Representations from Transformers (BERT), BERT for Biomedical Text Mining (BioBERT) and BERT for Clinical Text Mining (ClinicalBERT) were recently introduced to pre-train contextualized word representation models using bidirectional Transformers, a…
In this paper, we propose a \textit{weak supervision} framework for neural ranking tasks based on the data programming paradigm \citep{Ratner2016}, which enables us to leverage multiple weak supervision signals from different sources. Empirically, we consider two sources of weak supervision signals, unsupervised ranking functions and semantic feature similarities. We train a BERT-based passage-ranking model (which achieves new state-of-the-art performances on two benchmark datasets with full supervision) in our weak supervision framework. Without using ground-truth training labels, BERT-PR mod…
TU Wien（维也纳工业大学）；Microsoft（微软）；University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）
An emerging recipe for achieving state-of-the-art effectiveness in neural document re-ranking involves utilizing large pre-trained language models - e.g., BERT - to evaluate all individual passages in the document and then aggregating the outputs by pooling or additional Transformer layers. A major drawback of this approach is high query latency due to the cost of evaluating every passage in the document with BERT. To make matters worse, this high inference cost and latency varies based on the length of the document, with longer documents requiring more time and computation. To address this ch…
Seoul National University（首尔国立大学）；Naver Corp.（Naver公司）
A BERT-based Neural Ranking Model (NRM) can be either a crossencoder or a bi-encoder. Between the two, bi-encoder is highly efficient because all the documents can be pre-processed before the actual query time. In this work, we show two approaches for improving the performance of BERT-based bi-encoders. The first approach is to replace the full fine-tuning step with a lightweight fine-tuning. We examine lightweight fine-tuning methods that are adapter-based, prompt-based, and hybrid of the two. The second approach is to develop semi-Siamese models where queries and documents are handled with a…
Product ranking is a crucial component for many e-commerce services. One of the major challenges in product search is the vocabulary mismatch between query and products, which may be a larger vocabulary gap problem compared to other information retrieval domains. While there is a growing collection of neural learning to match methods aimed specifically at overcoming this issue, they do not leverage the recent advances of large language models for product search. On the other hand, product ranking often deals with multiple types of engagement signals such as clicks, add-to-cart, and purchases, …
Two step document ranking, where the initial retrieval is done by a classical information retrieval method, followed by neural re-ranking model, is the new standard. The best performance is achieved by using transformer-based models as re-rankers, e.g., BERT. We employ Longformer, a BERT-like model for long documents, on the MS MARCO document re-ranking task. The complete code used for training the model can be found on: https://github.com/isekulic/longformer-marco
Retrieval and ranking models are the backbone of many applications such as web search, open domain QA, or text-based recommender systems. The latency of neural ranking models at query time is largely dependent on the architecture and deliberate choices by their designers to trade-off effectiveness for higher efficiency. This focus on low query latency of a rising number of efficient ranking architectures make them feasible for production deployment. In machine learning an increasingly common approach to close the effectiveness gap of more efficient models is to apply knowledge distillation fro…
Tandon School of Engineering, New York University（纽约大学坦登工程学院）；David R. Cheriton School of Computer Science, University of Waterloo（滑铁卢大学大卫·R·切里顿计算机科学学院）；Courant Institute of Mathematical Sciences, New York University（纽约大学柯朗数学科学研究所）；Center for Data Science, New York University（纽约大学数据科学中心）；Facebook AI Research（脸书人工智能研究院）
The advent of deep neural networks pre-trained via language modeling tasks has spurred a number of successful applications in natural language processing. This work explores one such popular model, BERT, in the context of document ranking. We propose two variants, called monoBERT and duoBERT, that formulate the ranking problem as pointwise and pairwise classification, respectively. These two models are arranged in a multi-stage ranking architecture to form an end-to-end search system. One major advantage of this design is the ability to trade off quality against latency by controlling the admi…
Recently, pre-trained contextual models, such as BERT, have shown to perform well in language related tasks. We revisit the design decisions that govern the applicability of these models for the passage re-ranking task in open-domain question answering. We find that common approaches in the literature rely on fine-tuning a pre-trained BERT model and using a single, global representation of the input, discarding useful fine-grained relevance signals in token- or sentence-level representations. We argue that these discarded tokens hold useful information that can be leveraged. In this paper, we …
While large-scale pre-trained language models like BERT have advanced the state-of-the-art in IR, its application in query performance prediction (QPP) is so far based on pointwise modeling of individual queries. Meanwhile, recent studies suggest that the cross-attention modeling of a group of documents can effectively boost performances for both learning-to-rank algorithms and BERT-based re-ranking. To this end, a BERT-based groupwise QPP model is proposed, in which the ranking contexts of a list of queries are jointly modeled to predict the relative performance of individual queries. Extensi…
Bosch Center for Artificial Intelligence（博世人工智能中心）；Carnegie Mellon University（卡内基梅隆大学）
We study the utility of the lexical translation model (IBM Model 1) for English text retrieval, in particular, its neural variants that are trained end-to-end. We use the neural Model1 as an aggregator layer applied to context-free or contextualized query/document embeddings. This new approach to design a neural ranking system has benefits for effectiveness, efficiency, and interpretability. Specifically, we show that adding an interpretable neural Model 1 layer on top of BERT-based contextualized embeddings (1) does not decrease accuracy and/or efficiency; and (2) may overcome the limitation …
BERT-based information retrieval models are expensive, in both time (query latency) and computational resources (energy, hardware cost), making many of these models impractical especially under resource constraints. The reliance on a query encoder that only performs tokenization and on the pre-processing of passage representations at indexing, has allowed the recently proposed TILDE method to overcome the high query latency issue typical of BERT-based models. This however is at the expense of a lower effectiveness compared to other BERT-based re-rankers and dense retrievers. In addition, the o…
Contextual ranking models based on BERT are now well established for a wide range of passage and document ranking tasks. However, the robustness of BERT-based ranking models under adversarial inputs is under-explored. In this paper, we argue that BERT-rankers are not immune to adversarial attacks targeting retrieved documents given a query. Firstly, we propose algorithms for adversarial perturbation of both highly relevant and non-relevant documents using gradient-based optimization methods. The aim of our algorithms is to add/replace a small number of tokens to a highly relevant or non-releva…
In this paper, we present our approaches for the case law retrieval and the legal case entailment task in the Competition on Legal Information Extraction/Entailment (COLIEE) 2021. As first stage retrieval methods combined with neural re-ranking methods using contextualized language models like BERT achieved great performance improvements for information retrieval in the web and news domain, we evaluate these methods for the legal domain. A distinct characteristic of legal case retrieval is that the query case and case description in the corpus tend to be long documents and therefore exceed the…
Johannes Kepler University Linz（约翰内斯·开普勒林茨大学）；Know-Center GmbH（知识中心有限公司）
Societal biases resonate in the retrieved contents of information retrieval (IR) systems, resulting in reinforcing existing stereotypes. Approaching this issue requires established measures of fairness in respect to the representation of various social groups in retrieval results, as well as methods to mitigate such biases, particularly in the light of the advances in deep ranking models. In this work, we first provide a novel framework to measure the fairness in the retrieved text contents of ranking models. Introducing a ranker-agnostic measurement, the framework also enables the disentangle…
Term-based ranking with pre-trained transformer-based language models has recently gained attention as they bring the contextualization power of transformer models into the highly efficient term-based retrieval. In this work, we examine the generalizability of two of these deep contextualized term-based models in the context of query-by-example (QBE) retrieval in which a seed document acts as the query to find relevant documents. In this setting -- where queries are much longer than common keyword queries -- BERT inference at query time is problematic as it involves quadratic complexity. We in…
Although BERT-based ranking models have been commonly used in commercial search engines, they are usually time-consuming for online ranking tasks. Knowledge distillation, which aims at learning a smaller model with comparable performance to a larger model, is a common strategy for reducing the online inference latency. In this paper, we investigate the effect of different loss functions for uniform-architecture distillation of BERT-based ranking models. Here "uniform-architecture" denotes that both teacher and student models are in cross-encoder architecture, while the student models include s…
The ever-increasing number of applications to job positions presents a challenge for employers to find suitable candidates manually. We present an end-to-end solution for ranking candidates based on their suitability to a job description. We accomplish this in two stages. First, we build a resume parser which extracts complete information from candidate resumes. This parser is made available to the public in the form of a web application. Second, we use BERT sentence pair classification to perform ranking based on their suitability to the job description. To approximate the job description, we…
School of Information, Renmin University of China（中国人民大学信息学院）；Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学高瓴人工智能学院）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；Huawei Noah’s Ark Lab（华为诺亚方舟实验室）
Recently, pre-trained language models such as BERT have been applied to document ranking for information retrieval, which first pre-train a general language model on an unlabeled large corpus and then conduct ranking-specific fine-tuning on expert-labeled relevance datasets. Ideally, an IR system would model relevance from a user-system dualism: the user's view and the system's view. User's view judges the relevance based on the activities of "real users" while the system's view focuses on the relevance signals from the system side, e.g., from the experts or algorithms, etc. Inspired by the us…
BERT-based Neural Ranking Models (NRMs) can be classified according to how the query and document are encoded through BERT's self-attention layers - bi-encoder versus cross-encoder. Bi-encoder models are highly efficient because all the documents can be pre-processed before the query time, but their performance is inferior compared to cross-encoder models. Both models utilize a ranker that receives BERT representations as the input and generates a relevance score as the output. In this work, we propose a method where multi-teacher distillation is applied to a cross-encoder NRM and a bi-encoder…
Raytheon BBN Technologies（雷神BBN技术公司）；University of Pittsburgh（匹兹堡大学）
Multiple neural language models have been developed recently, e.g., BERT and XLNet, and achieved impressive results in various NLP tasks including sentence classification, question answering and document ranking. In this paper, we explore the use of the popular bidirectional language model, BERT, to model and learn the relevance between English queries and foreign-language documents in the task of cross-lingual information retrieval. A deep relevance matching model based on BERT is introduced and trained by finetuning a pretrained multilingual BERT model with weak supervision, using home-made …
In precision-oriented tasks like answer ranking, it is more important to rank many relevant answers highly than to retrieve all relevant answers. It follows that a good ranking strategy would be to learn how to identify the easiest correct answers first (i.e., assign a high ranking score to answers that have characteristics that usually indicate relevance, and a low ranking score to those with characteristics that do not), before incorporating more complex logic to handle difficult cases (e.g., semantic matching or reasoning). In this work, we apply this idea to the training of neural answer r…
On a wide range of natural language processing and information retrieval tasks, transformer-based models, particularly pre-trained language models like BERT, have demonstrated tremendous effectiveness. Due to the quadratic complexity of the self-attention mechanism, however, such models have difficulties processing long documents. Recent works dealing with this issue include truncating long documents, in which case one loses potential relevant information, segmenting them into several passages, which may lead to miss some information and high computational complexity when the number of passage…
National Taiwan University（国立台湾大学）；National Cheng Kung University（国立成功大学）
While relation extraction is an essential task in knowledge acquisition and representation, and new-generated relations are common in the real world, less effort is made to predict unseen relations that cannot be observed at the training stage. In this paper, we formulate the zero-shot relation extraction problem by incorporating the text description of seen and unseen relations. We propose a novel multi-task learning model, zero-shot BERT (ZS-BERT), to directly predict unseen relations without hand-crafted attribute labeling and multiple pairwise classifications. Given training instances cons…
Recent work has shown the surprising ability of multi-lingual BERT to serve as a zero-shot cross-lingual transfer model for a number of language processing tasks. We combine this finding with a similarly-recently proposal on sentence-level relevance modeling for document retrieval to demonstrate the ability of multi-lingual BERT to transfer models of relevance across languages. Experiments on test collections in five different languages from diverse language families (Chinese, Arabic, French, Hindi, and Bengali) show that models trained with English data improve ranking quality, without any sp…
Although neural information retrieval has witnessed great improvements, recent works showed that the generalization ability of dense retrieval models on target domains with different distributions is limited, which contrasts with the results obtained with interaction-based models. To address this issue, researchers have resorted to adversarial learning and query generation approaches; both approaches nevertheless resulted in limited improvements. In this paper, we propose to use a self-supervision approach in which pseudo-relevance labels are automatically generated on the target domain. To do…
University of Queensland（昆士兰大学）；Leipzig University（莱比锡大学）；CSIRO（联邦科学与工业研究组织）
Medical systematic reviews typically require assessing all the documents retrieved by a search. The reason is two-fold: the task aims for ``total recall''; and documents retrieved using Boolean search are an unordered set, and thus it is unclear how an assessor could examine only a subset. Screening prioritisation is the process of ranking the (unordered) set of retrieved documents, allowing assessors to begin the downstream processes of the systematic review creation earlier, leading to earlier completion of the review, or even avoiding screening documents ranked least relevant. Screening pri…
Parallel deep learning architectures like fine-tuned BERT and MT-DNN, have quickly become the state of the art, bypassing previous deep and shallow learning methods by a large margin. More recently, pre-trained models from large related datasets have been able to perform well on many downstream tasks by just fine-tuning on domain-specific datasets . However, using powerful models on non-trivial tasks, such as ranking and large document classification, still remains a challenge due to input size limitations of parallel architecture and extremely small datasets (insufficient for fine-tuning). In…
Athens University of Economics and Business（雅典经济与商业大学）；Research Center ‘Athena’（“雅典娜”研究中心）；Institute for Language and Speech Processing（语言与语音处理研究所）
Question answering (QA) systems for large document collections typically use pipelines that (i) retrieve possibly relevant documents, (ii) re-rank them, (iii) rank paragraphs or other snippets of the top-ranked documents, and (iv) select spans of the top-ranked snippets as exact answers. Pipelines are conceptually simple, but errors propagate from one component to the next, without later components being able to revise earlier decisions. We present an architecture for joint document and snippet ranking, the two middle stages, which leverages the intuition that relevant documents have good snip…
