Search Results for author:
Found 35 papers, 18 papers with code
Dwell in the Beginning: How Language Models Embed Long Documents for Dense Retrieval
This study investigates the existence of positional biases in Transformer-based models for text representation learning, particularly in the context of web document retrieval.
Building Retrieval Systems for the ClueWeb22-B Corpus
The ClueWeb22 dataset containing nearly 10 billion documents was released in 2022 to support academic and industry research.
Active Retrieval Augmented Generation
In this work, we provide a generalized view of active retrieval augmented generation, methods that actively decide when and what to retrieve across the course of the generation.
Precise Zero-Shot Dense Retrieval without Relevance Labels
Given a query, HyDE first zero-shot instructs an instruction-following language model (e. g. InstructGPT) to generate a hypothetical document.
Retrieval as Attention: End-to-end Learning of Retrieval and Reading within a Single Transformer
Systems for knowledge-intensive tasks such as open-domain question answering (QA) usually consist of two stages: efficient retrieval of relevant documents from a large corpus and detailed reading of the selected documents to generate answers.
Ranked #1 on
Passage Retrieval
on Natural Questions
ClueWeb22: 10 Billion Web Documents with Visual and Semantic Information
ClueWeb22, the newest iteration of the ClueWeb line of datasets, provides 10 billion web pages affiliated with rich information.
PAL: Program-aided Language Models
Much of this success can be attributed to prompting methods such as "chain-of-thought'', which employ LLMs for both understanding the problem description by decomposing it into steps, as well as solving each step of the problem.
Ranked #17 on
Arithmetic Reasoning
on GSM8K
Long Document Re-ranking with Modular Re-ranker
In this paper, we propose instead to model full query-to-document interaction, leveraging the attention operation and modular Transformer re-ranker framework.
Tevatron: An Efficient and Flexible Toolkit for Dense Retrieval
In this paper, we present Tevatron, a dense retrieval toolkit optimized for efficiency, flexibility, and code simplicity.
Improving Query Representations for Dense Retrieval with Pseudo Relevance Feedback
This paper proposes ANCE-PRF, a new query encoder that uses pseudo relevance feedback (PRF) to improve query representations for dense retrieval.
Unsupervised Corpus Aware Language Model Pre-training for Dense Passage Retrieval
Recent research demonstrates the effectiveness of using fine-tuned language models~(LM) for dense retrieval.
Condenser: a Pre-training Architecture for Dense Retrieval
Pre-trained Transformer language models (LM) have become go-to text representation encoders.
COIL: Revisit Exact Lexical Match in Information Retrieval with Contextualized Inverted List
Classical information retrieval systems such as BM25 rely on exact lexical match and carry out search efficiently with inverted list index.
Rethink Training of BERT Rerankers in Multi-Stage Retrieval Pipeline
Pre-trained deep language models~(LM) have advanced the state-of-the-art of text retrieval.
Assessing the Benefits of Model Ensembles in Neural Re-Ranking for Passage Retrieval
Our work aimed at experimentally assessing the benefits of model ensembling within the context of neural methods for passage reranking.
PGT: Pseudo Relevance Feedback Using a Graph-Based Transformer
Most research on pseudo relevance feedback (PRF) has been done in vector space and probabilistic retrieval models.
Scaling Deep Contrastive Learning Batch Size under Memory Limited Setup
Contrastive learning has been applied successfully to learn vector representations of text.
Making Information Seeking Easier: An Improved Pipeline for Conversational Search
Given an input question, it uses a BERT-based classifier (trained with weak supervision) to de-contextualize the input by selecting relevant terms from the dialog history.
Generating Categories for Sets of Entities
Category systems are central components of knowledge bases, as they provide a hierarchical grouping of semantically related concepts and entities.
Ranking Clarification Questions via Natural Language Inference
Given a natural language query, teaching machines to ask clarifying questions is of immense utility in practical natural language processing systems.
Understanding BERT Rankers Under Distillation
Deep language models such as BERT pre-trained on large corpus have given a huge performance boost to the state-of-the-art information retrieval ranking systems.
Summarizing and Exploring Tabular Data in Conversational Search
We propose to generate natural language summaries as answers to describe the complex information contained in a table.
Complementing Lexical Retrieval with Semantic Residual Embedding
This paper presents CLEAR, a retrieval model that seeks to complement classical lexical exact-match models such as BM25 with semantic matching signals from a neural embedding matching model.
Modularized Transfomer-based Ranking Framework
Recent innovations in Transformer-based ranking models have advanced the state-of-the-art in information retrieval.
TREC CAsT 2019: The Conversational Assistance Track Overview
A common theme through the runs is the use of BERT-based neural reranking methods.
Context-Aware Sentence/Passage Term Importance Estimation For First Stage Retrieval
When applied to passages, DeepCT-Index produces term weights that can be stored in an ordinary inverted index for passage retrieval.
Deeper Text Understanding for IR with Contextual Neural Language Modeling
Neural networks provide new possibilities to automatically learn complex language patterns and query-document relations.
Ranked #5 on
Ad-Hoc Information Retrieval
on TREC Robust04
Consistency and Variation in Kernel Neural Ranking Model
This paper studies the consistency of the kernel-based neural ranking model K-NRM, a recent state-of-the-art neural IR model, which is important for reproducible research and deployment in the industry.
Towards Better Text Understanding and Retrieval through Kernel Entity Salience Modeling
The salience model also improves ad hoc search accuracy, providing effective ranking features by modeling the salience of query entities in candidate documents.
Convolutional Neural Networks for Soft Matching N-Grams in Ad-hoc Search
This paper presents Conv-KNRM, a Convolutional Kernel-based Neural Ranking Model that models n-gram soft matches for ad-hoc search.
Word-Entity Duet Representations for Document Ranking
This paper presents a word-entity duet framework for utilizing knowledge bases in ad-hoc retrieval.
End-to-End Neural Ad-hoc Ranking with Kernel Pooling
Given a query and a set of documents, K-NRM uses a translation matrix that models word-level similarities via word embeddings, a new kernel-pooling technique that uses kernels to extract multi-level soft match features, and a learning-to-rank layer that combines those features into the final ranking score.
WebSets: Extracting Sets of Entities from the Web Using Unsupervised Information Extraction
We describe a open-domain information extraction method for extracting concept-instance pairs from an HTML corpus.
Exploratory Learning
In multiclass semi-supervised learning (SSL), it is sometimes the case that the number of classes present in the data is not known, and hence no labeled examples are provided for some classes.
