Search Results for author:
Found 54 papers, 36 papers with code
Early Exiting BERT for Efficient Document Ranking
Pre-trained language models such as BERT have shown their effectiveness in various tasks.
A Personalized Dense Retrieval Framework for Unified Information Access
Developing a universal model that can efficiently and effectively respond to a wide range of information access requests -- from retrieval to recommendation to question answering -- has been a long-lasting goal in the information retrieval community.
Sabiá: Portuguese Large Language Models
By evaluating on datasets originally conceived in the target language as well as translated ones, we study the contributions of language-specific pretraining in terms of 1) capturing linguistic nuances and structures inherent to the target language, and 2) enriching the model's knowledge about a domain or culture.
Simple Yet Effective Neural Ranking and Reranking Baselines for Cross-Lingual Information Retrieval
The advent of multilingual language models has generated a resurgence of interest in cross-lingual information retrieval (CLIR), which is the task of searching documents in one language with queries from another.
Evaluating GPT-3.5 and GPT-4 Models on Brazilian University Admission Exams
The present study aims to explore the capabilities of Language Models (LMs) in tackling high-stakes multiple-choice tests, represented here by the Exame Nacional do Ensino M\'edio (ENEM), a multidisciplinary entrance examination widely adopted by Brazilian universities.
NeuralMind-UNICAMP at 2022 TREC NeuCLIR: Large Boring Rerankers for Cross-lingual Retrieval
This paper reports on a study of cross-lingual information retrieval (CLIR) using the mT5-XXL reranker on the NeuCLIR track of TREC 2022.
ExaRanker: Explanation-Augmented Neural Ranker
Recent work has shown that inducing a large language model (LLM) to generate explanations prior to outputting an answer is an effective strategy to improve performance on a wide range of reasoning tasks.
InPars-v2: Large Language Models as Efficient Dataset Generators for Information Retrieval
Recently, InPars introduced a method to efficiently use large language models (LLMs) in information retrieval tasks: via few-shot examples, an LLM is induced to generate relevant queries for documents.
Visconde: Multi-document QA with GPT-3 and Neural Reranking
This paper proposes a question-answering system that can answer questions whose supporting evidence is spread over multiple (potentially long) documents.
In Defense of Cross-Encoders for Zero-Shot Retrieval
We find that the number of parameters and early query-document interactions of cross-encoders play a significant role in the generalization ability of retrieval models.
NeuralSearchX: Serving a Multi-billion-parameter Reranker for Multilingual Metasearch at a Low Cost
We compare our system with Microsoft's Biomedical Search and show that our design choices led to a much cost-effective system with competitive QPS while having close to state-of-the-art results on a wide range of public benchmarks.
mRobust04: A Multilingual Version of the TREC Robust 2004 Benchmark
Robust 2004 is an information retrieval benchmark whose large number of judgments per query make it a reliable evaluation dataset.
MonoByte: A Pool of Monolingual Byte-level Language Models
The zero-shot cross-lingual ability of models pretrained on multilingual and even monolingual corpora has spurred many hypotheses to explain this intriguing empirical result.
Induced Natural Language Rationales and Interleaved Markup Tokens Enable Extrapolation in Large Language Models
Our experimental results show that generating step-by-step rationales and introducing marker tokens are both required for effective extrapolation.
A Boring-yet-effective Approach for the Product Ranking Task of the Amazon KDD Cup 2022
In this work we describe our submission to the product ranking task of the Amazon KDD Cup 2022.
No Parameter Left Behind: How Distillation and Model Size Affect Zero-Shot Retrieval
This has made distilled and dense models, due to latency constraints, the go-to choice for deployment in real-world retrieval applications.
Ranked #1 on
Citation Prediction
on SciDocs (BEIR)
Billions of Parameters Are Worth More Than In-domain Training Data: A case study in the Legal Case Entailment Task
Recent work has shown that language models scaled to billions of parameters, such as GPT-3, perform remarkably well in zero-shot and few-shot scenarios.
InPars: Data Augmentation for Information Retrieval using Large Language Models
In this work, we harness the few-shot capabilities of large pretrained language models as synthetic data generators for IR tasks.
To Tune or Not To Tune? Zero-shot Models for Legal Case Entailment
For that, we participated in the legal case entailment task of COLIEE 2021, in which we use such models with no adaptations to the target domain.
Sequence-to-Sequence Models for Extracting Information from Registration and Legal Documents
A typical information extraction pipeline consists of token- or span-level classification models coupled with a series of pre- and post-processing scripts.
On the ability of monolingual models to learn language-agnostic representations
Pretrained multilingual models have become a de facto default approach for zero-shot cross-lingual transfer.
mMARCO: A Multilingual Version of the MS MARCO Passage Ranking Dataset
In this work, we present mMARCO, a multilingual version of the MS MARCO passage ranking dataset comprising 13 languages that was created using machine translation.
A cost-benefit analysis of cross-lingual transfer methods
An effective method for cross-lingual transfer is to fine-tune a bilingual or multilingual model on a supervised dataset in one language and evaluating it on another language in a zero-shot manner.
Yes, BM25 is a Strong Baseline for Legal Case Retrieval
We describe our single submission to task 1 of COLIEE 2021.
Investigating the Limitations of Transformers with Simple Arithmetic Tasks
In this work, we investigate if the surface form of a number has any influence on how sequence-to-sequence language models learn simple arithmetic tasks such as addition and subtraction across a wide range of values.
Pyserini: An Easy-to-Use Python Toolkit to Support Replicable IR Research with Sparse and Dense Representations
Pyserini is an easy-to-use Python toolkit that supports replicable IR research by providing effective first-stage retrieval in a multi-stage ranking architecture.
Cultural Vocal Bursts Intensity Prediction
Information Retrieval
+1
The Expando-Mono-Duo Design Pattern for Text Ranking with Pretrained Sequence-to-Sequence Models
We propose a design pattern for tackling text ranking problems, dubbed "Expando-Mono-Duo", that has been empirically validated for a number of ad hoc retrieval tasks in different domains.
Designing Templates for Eliciting Commonsense Knowledge from Pretrained Sequence-to-Sequence Models
While internalized {``}implicit knowledge{''} in pretrained transformers has led to fruitful progress in many natural language understanding tasks, how to most effectively elicit such knowledge remains an open question.
Scientific Claim Verification with VERT5ERINI
This work describes the adaptation of a pretrained sequence-to-sequence model to the task of scientific claim verification in the biomedical domain.
Pretrained Transformers for Text Ranking: BERT and Beyond
There are two themes that pervade our survey: techniques for handling long documents, beyond typical sentence-by-sentence processing in NLP, and techniques for addressing the tradeoff between effectiveness (i. e., result quality) and efficiency (e. g., query latency, model and index size).
Can questions summarize a corpus? Using question generation for characterizing COVID-19 research
What are the latent questions on some textual data?
PTT5: Pretraining and validating the T5 model on Brazilian Portuguese data
In natural language processing (NLP), there is a need for more resources in Portuguese, since much of the data used in the state-of-the-art research is in other languages.
Lite Training Strategies for Portuguese-English and English-Portuguese Translation
Despite the widespread adoption of deep learning for machine translation, it is still expensive to develop high-quality translation models.
Covidex: Neural Ranking Models and Keyword Search Infrastructure for the COVID-19 Open Research Dataset
We present Covidex, a search engine that exploits the latest neural ranking models to provide information access to the COVID-19 Open Research Dataset curated by the Allen Institute for AI.
Rapidly Deploying a Neural Search Engine for the COVID-19 Open Research Dataset
The Neural Covidex is a search engine that exploits the latest neural ranking architectures to provide information access to the COVID-19 Open Research Dataset (CORD-19) curated by the Allen Institute for AI.
Multi-Stage Conversational Passage Retrieval: An Approach to Fusing Term Importance Estimation and Neural Query Rewriting
Conversational search plays a vital role in conversational information seeking.
Rapidly Bootstrapping a Question Answering Dataset for COVID-19
We present CovidQA, the beginnings of a question answering dataset specifically designed for COVID-19, built by hand from knowledge gathered from Kaggle's COVID-19 Open Research Dataset Challenge.
Rapidly Deploying a Neural Search Engine for the COVID-19 Open Research Dataset: Preliminary Thoughts and Lessons Learned
We present the Neural Covidex, a search engine that exploits the latest neural ranking architectures to provide information access to the COVID-19 Open Research Dataset curated by the Allen Institute for AI.
Conversational Question Reformulation via Sequence-to-Sequence Architectures and Pretrained Language Models
This paper presents an empirical study of conversational question reformulation (CQR) with sequence-to-sequence architectures and pretrained language models (PLMs).
TTTTTackling WinoGrande Schemas
We applied the T5 sequence-to-sequence model to tackle the AI2 WinoGrande Challenge by decomposing each example into two input text strings, each containing a hypothesis, and using the probabilities assigned to the "entailment" token as a score of the hypothesis.
Document Ranking with a Pretrained Sequence-to-Sequence Model
We investigate this observation further by varying target words to probe the model's use of latent knowledge.
Ranked #1 on
Ad-Hoc Information Retrieval
on TREC Robust04
Electricity Theft Detection with self-attention
In this work we propose a novel self-attention mechanism model to address electricity theft detection on an imbalanced realistic dataset that presents a daily electricity consumption provided by State Grid Corporation of China.
Navigation-Based Candidate Expansion and Pretrained Language Models for Citation Recommendation
Citation recommendation systems for the scientific literature, to help authors find papers that should be cited, have the potential to speed up discoveries and uncover new routes for scientific exploration.
Meta Answering for Machine Reading
We investigate a framework for machine reading, inspired by real world information-seeking problems, where a meta question answering system interacts with a black box environment.
Multi-Stage Document Ranking with BERT
The advent of deep neural networks pre-trained via language modeling tasks has spurred a number of successful applications in natural language processing.
Portuguese Named Entity Recognition using BERT-CRF
Recent advances in language representation using neural networks have made it viable to transfer the learned internal states of a trained model to downstream natural language processing tasks, such as named entity recognition (NER) and question answering.
Learning Representations and Agents for Information Retrieval
We argue, however, that although this approach has been very successful for tasks such as machine translation, storing the world's knowledge as parameters of a learning machine can be very hard.
Document Expansion by Query Prediction
One technique to improve the retrieval effectiveness of a search engine is to expand documents with terms that are related or representative of the documents' content. From the perspective of a question answering system, this might comprise questions the document can potentially answer.
Ranked #1 on
Passage Re-Ranking
on TREC-PM
Multi-agent query reformulation: Challenges and the role of diversity
We investigate methods to efficiently learn diverse strategies in reinforcement learning for a generative structured prediction problem: query reformulation.
Passage Re-ranking with BERT
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.
Ranked #3 on
Passage Re-Ranking
on MS MARCO
(using extra training data)
Learning to Coordinate Multiple Reinforcement Learning Agents for Diverse Query Reformulation
We propose a method to efficiently learn diverse strategies in reinforcement learning for query reformulation in the tasks of document retrieval and question answering.
EpiRL: A Reinforcement Learning Agent to Facilitate Epistasis Detection
Epistasis (gene-gene interaction) is crucial to predicting genetic disease.
Task-Oriented Query Reformulation with Reinforcement Learning
In this work, we introduce a query reformulation system based on a neural network that rewrites a query to maximize the number of relevant documents returned.
End-to-End Goal-Driven Web Navigation
We propose a goal-driven web navigation as a benchmark task for evaluating an agent with abilities to understand natural language and plan on partially observed environments.
