Search Results for author: Marc Najork

Found 28 papers, 7 papers with code

Learning Groupwise Multivariate Scoring Functions Using Deep Neural Networks

2 code implementations11 Nov 2018 Qingyao Ai, Xuanhui Wang, Sebastian Bruch, Nadav Golbandi, Michael Bendersky, Marc Najork

To overcome this limitation, we propose a new framework for multivariate scoring functions, in which the relevance score of a document is determined jointly by multiple documents in the list.

Learning-To-Rank

Self-Attentive Document Interaction Networks for Permutation Equivariant Ranking

no code implementations21 Oct 2019 Rama Kumar Pasumarthi, Xuanhui Wang, Michael Bendersky, Marc Najork

It thus motivates us to study how to leverage cross-document interactions for learning-to-rank in the deep learning framework.

Information Retrieval Learning-To-Rank +1

Learning-to-Rank with BERT in TF-Ranking

no code implementations17 Apr 2020 Shuguang Han, Xuanhui Wang, Mike Bendersky, Marc Najork

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.

Document Ranking Learning-To-Rank +2

Beyond 512 Tokens: Siamese Multi-depth Transformer-based Hierarchical Encoder for Long-Form Document Matching

1 code implementation26 Apr 2020 Liu Yang, Mingyang Zhang, Cheng Li, Michael Bendersky, Marc Najork

In order to better capture sentence level semantic relations within a document, we pre-train the model with a novel masked sentence block language modeling task in addition to the masked word language modeling task used by BERT.

Clustering Information Retrieval +9

Active Learning for Skewed Data Sets

no code implementations23 May 2020 Abbas Kazerouni, Qi Zhao, Jing Xie, Sandeep Tata, Marc Najork

Furthermore, there is usually only a small amount of initial training data available when building machine-learned models to solve such problems.

Active Learning

Representation Learning for Information Extraction from Form-like Documents

1 code implementation ACL 2020 Bodhisattwa Majumder, Navneet Potti, Sandeep Tata, James B. Wendt, Qi Zhao, Marc Najork

We propose a novel approach using representation learning for tackling the problem of extracting structured information from form-like document images.

Representation Learning

Leveraging Semantic and Lexical Matching to Improve the Recall of Document Retrieval Systems: A Hybrid Approach

no code implementations2 Oct 2020 Saar Kuzi, Mingyang Zhang, Cheng Li, Michael Bendersky, Marc Najork

A hybrid approach, which leverages both semantic (deep neural network-based) and lexical (keyword matching-based) retrieval models, is proposed.

Re-Ranking Retrieval

Neural Rankers are hitherto Outperformed by Gradient Boosted Decision Trees

no code implementations ICLR 2021 Zhen Qin, Le Yan, Honglei Zhuang, Yi Tay, Rama Kumar Pasumarthi, Xuanhui Wang, Michael Bendersky, Marc Najork

We first validate this concern by showing that most recent neural LTR models are, by a large margin, inferior to the best publicly available Gradient Boosted Decision Trees (GBDT) in terms of their reported ranking accuracy on benchmark datasets.

Learning-To-Rank

Natural Language Understanding with Privacy-Preserving BERT

no code implementations15 Apr 2021 Chen Qu, Weize Kong, Liu Yang, Mingyang Zhang, Michael Bendersky, Marc Najork

We investigate the privacy and utility implications of applying dx-privacy, a variant of Local Differential Privacy, to BERT fine-tuning in NLU applications.

Language Modelling Natural Language Understanding +1

Rethinking Search: Making Domain Experts out of Dilettantes

no code implementations5 May 2021 Donald Metzler, Yi Tay, Dara Bahri, Marc Najork

When experiencing an information need, users want to engage with a domain expert, but often turn to an information retrieval system, such as a search engine, instead.

Information Retrieval Question Answering +1

Dynamic Language Models for Continuously Evolving Content

no code implementations11 Jun 2021 Spurthi Amba Hombaiah, Tao Chen, Mingyang Zhang, Michael Bendersky, Marc Najork

To this end, we both explore two different vocabulary composition methods, as well as propose three sampling methods which help in efficient incremental training for BERT-like models.

Rank4Class: Examining Multiclass Classification through the Lens of Learning to Rank

no code implementations29 Sep 2021 Nan Wang, Zhen Qin, Le Yan, Honglei Zhuang, Xuanhui Wang, Michael Bendersky, Marc Najork

We further demonstrate that the most popular MCC architecture in deep learning can be mathematically formulated as a LTR pipeline equivalently, with a specific set of choices in terms of ranking model architecture and loss function.

Image Classification Information Retrieval +4

Improving Neural Ranking via Lossless Knowledge Distillation

no code implementations30 Sep 2021 Zhen Qin, Le Yan, Yi Tay, Honglei Zhuang, Xuanhui Wang, Michael Bendersky, Marc Najork

We explore a novel perspective of knowledge distillation (KD) for learning to rank (LTR), and introduce Self-Distilled neural Rankers (SDR), where student rankers are parameterized identically to their teachers.

Knowledge Distillation Learning-To-Rank

Rank4Class: A Ranking Formulation for Multiclass Classification

no code implementations17 Dec 2021 Nan Wang, Zhen Qin, Le Yan, Honglei Zhuang, Xuanhui Wang, Michael Bendersky, Marc Najork

Multiclass classification (MCC) is a fundamental machine learning problem of classifying each instance into one of a predefined set of classes.

Classification Image Classification +4

Data-Efficient Information Extraction from Form-Like Documents

no code implementations7 Jan 2022 Beliz Gunel, Navneet Potti, Sandeep Tata, James B. Wendt, Marc Najork, Jing Xie

Automating information extraction from form-like documents at scale is a pressing need due to its potential impact on automating business workflows across many industries like financial services, insurance, and healthcare.

Transfer Learning

Out-of-Domain Semantics to the Rescue! Zero-Shot Hybrid Retrieval Models

no code implementations25 Jan 2022 Tao Chen, Mingyang Zhang, Jing Lu, Michael Bendersky, Marc Najork

In this work, we carefully select five datasets, including two in-domain datasets and three out-of-domain datasets with different levels of domain shift, and study the generalization of a deep model in a zero-shot setting.

Language Modelling Passage Retrieval +1

Regression Compatible Listwise Objectives for Calibrated Ranking with Binary Relevance

no code implementations2 Nov 2022 Aijun Bai, Rolf Jagerman, Zhen Qin, Le Yan, Pratyush Kar, Bing-Rong Lin, Xuanhui Wang, Michael Bendersky, Marc Najork

As Learning-to-Rank (LTR) approaches primarily seek to improve ranking quality, their output scores are not scale-calibrated by design.

Learning-To-Rank regression

DSI++: Updating Transformer Memory with New Documents

no code implementations19 Dec 2022 Sanket Vaibhav Mehta, Jai Gupta, Yi Tay, Mostafa Dehghani, Vinh Q. Tran, Jinfeng Rao, Marc Najork, Emma Strubell, Donald Metzler

In this work, we introduce DSI++, a continual learning challenge for DSI to incrementally index new documents while being able to answer queries related to both previously and newly indexed documents.

Continual Learning Natural Questions +1

Towards Disentangling Relevance and Bias in Unbiased Learning to Rank

no code implementations28 Dec 2022 Yunan Zhang, Le Yan, Zhen Qin, Honglei Zhuang, Jiaming Shen, Xuanhui Wang, Michael Bendersky, Marc Najork

We give both theoretical analysis and empirical results to show the negative effects on relevance tower due to such a correlation.

Learning-To-Rank

"Why is this misleading?": Detecting News Headline Hallucinations with Explanations

no code implementations12 Feb 2023 Jiaming Shen, Jialu Liu, Dan Finnie, Negar Rahmati, Michael Bendersky, Marc Najork

With the growing need for news headline generation, we argue that the hallucination issue, namely the generated headlines being not supported by the original news stories, is a critical challenge for the deployment of this feature in web-scale systems Meanwhile, due to the infrequency of hallucination cases and the requirement of careful reading for raters to reach the correct consensus, it is difficult to acquire a large dataset for training a model to detect such hallucinations through human curation.

Hallucination Headline Generation +1

Do Not Blindly Imitate the Teacher: Using Perturbed Loss for Knowledge Distillation

no code implementations8 May 2023 Rongzhi Zhang, Jiaming Shen, Tianqi Liu, Jialu Liu, Michael Bendersky, Marc Najork, Chao Zhang

In this work, we argue that such a learning objective is sub-optimal because there exists a discrepancy between the teacher's output distribution and the ground truth label distribution.

Knowledge Distillation

Exploring the Viability of Synthetic Query Generation for Relevance Prediction

no code implementations19 May 2023 Aditi Chaudhary, Karthik Raman, Krishna Srinivasan, Kazuma Hashimoto, Mike Bendersky, Marc Najork

While our experiments demonstrate that these modifications help improve performance of QGen techniques, we also find that QGen approaches struggle to capture the full nuance of the relevance label space and as a result the generated queries are not faithful to the desired relevance label.

Information Retrieval Question Answering +2

Creator Context for Tweet Recommendation

no code implementations29 Nov 2023 Spurthi Amba Hombaiah, Tao Chen, Mingyang Zhang, Michael Bendersky, Marc Najork, Matt Colen, Sergey Levi, Vladimir Ofitserov, Tanvir Amin

In other words, grounding the interpretation of the tweet in the context of its creator plays an important role in deciphering the true intent and the importance of the tweet.

Cannot find the paper you are looking for? You can Submit a new open access paper.