Search Results for author: Benjamin Piwowarski

Found 19 papers, 7 papers with code

SPLADE v2: Sparse Lexical and Expansion Model for Information Retrieval

1 code implementation21 Sep 2021 Thibault Formal, Carlos Lassance, Benjamin Piwowarski, Stéphane Clinchant

Meanwhile, there has been a growing interest in learning \emph{sparse} representations for documents and queries, that could inherit from the desirable properties of bag-of-words models such as the exact matching of terms and the efficiency of inverted indexes.

Information Retrieval

Skim-Attention: Learning to Focus via Document Layout

1 code implementation2 Sep 2021 Laura Nguyen, Thomas Scialom, Jacopo Staiano, Benjamin Piwowarski

Motivated by human reading strategies, this paper presents Skim-Attention, a new attention mechanism that takes advantage of the structure of the document and its layout.

Language Modelling

SPLADE: Sparse Lexical and Expansion Model for First Stage Ranking

1 code implementation12 Jul 2021 Thibault Formal, Benjamin Piwowarski, Stéphane Clinchant

In neural Information Retrieval, ongoing research is directed towards improving the first retriever in ranking pipelines.

Information Retrieval

To Beam Or Not To Beam: That is a Question of Cooperation for Language GANs

no code implementations11 Jun 2021 Thomas Scialom, Paul-Alexis Dray, Sylvain Lamprier, Benjamin Piwowarski, Jacopo Staiano

Due to the discrete nature of words, language GANs require to be optimized from rewards provided by discriminator networks, via reinforcement learning methods.

Question Generation

Data-QuestEval: A Referenceless Metric for Data-to-Text Semantic Evaluation

2 code implementations15 Apr 2021 Clément Rebuffel, Thomas Scialom, Laure Soulier, Benjamin Piwowarski, Sylvain Lamprier, Jacopo Staiano, Geoffrey Scoutheeten, Patrick Gallinari

QuestEval is a reference-less metric used in text-to-text tasks, that compares the generated summaries directly to the source text, by automatically asking and answering questions.

Data-to-Text Generation Question Generation

QuestEval: Summarization Asks for Fact-based Evaluation

2 code implementations23 Mar 2021 Thomas Scialom, Paul-Alexis Dray, Patrick Gallinari, Sylvain Lamprier, Benjamin Piwowarski, Jacopo Staiano, Alex Wang

Summarization evaluation remains an open research problem: current metrics such as ROUGE are known to be limited and to correlate poorly with human judgments.

Question Answering

A White Box Analysis of ColBERT

no code implementations17 Dec 2020 Thibault Formal, Benjamin Piwowarski, Stéphane Clinchant

Transformer-based models are nowadays state-of-the-art in ad-hoc Information Retrieval, but their behavior is far from being understood.

Ad-Hoc Information Retrieval Information Retrieval

Transductive Zero-Shot Learning using Cross-Modal CycleGAN

no code implementations13 Nov 2020 Patrick Bordes, Eloi Zablocki, Benjamin Piwowarski, Patrick Gallinari

We show the efficiency of our Cross-Modal CycleGAN model (CM-GAN) on the ImageNet T-ZSL task where we obtain state-of-the-art results.

Zero-Shot Learning

Discriminative Adversarial Search for Abstractive Summarization

1 code implementation ICML 2020 Thomas Scialom, Paul-Alexis Dray, Sylvain Lamprier, Benjamin Piwowarski, Jacopo Staiano

We introduce a novel approach for sequence decoding, Discriminative Adversarial Search (DAS), which has the desirable properties of alleviating the effects of exposure bias without requiring external metrics.

Abstractive Text Summarization Domain Adaptation

Incorporating Visual Semantics into Sentence Representations within a Grounded Space

no code implementations IJCNLP 2019 Patrick Bordes, Eloi Zablocki, Laure Soulier, Benjamin Piwowarski, Patrick Gallinari

To overcome this limitation, we propose to transfer visual information to textual representations by learning an intermediate representation space: the grounded space.

Answers Unite! Unsupervised Metrics for Reinforced Summarization Models

1 code implementation IJCNLP 2019 Thomas Scialom, Sylvain Lamprier, Benjamin Piwowarski, Jacopo Staiano

Abstractive summarization approaches based on Reinforcement Learning (RL) have recently been proposed to overcome classical likelihood maximization.

Abstractive Text Summarization Question Answering

Self-Attention Architectures for Answer-Agnostic Neural Question Generation

no code implementations ACL 2019 Thomas Scialom, Benjamin Piwowarski, Jacopo Staiano

Neural architectures based on self-attention, such as Transformers, recently attracted interest from the research community, and obtained significant improvements over the state of the art in several tasks.

Question Generation Word Embeddings

Context-Aware Zero-Shot Learning for Object Recognition

no code implementations24 Apr 2019 Eloi Zablocki, Patrick Bordes, Benjamin Piwowarski, Laure Soulier, Patrick Gallinari

Zero-Shot Learning (ZSL) aims at classifying unlabeled objects by leveraging auxiliary knowledge, such as semantic representations.

Object Recognition Zero-Shot Learning

Learning Multi-Modal Word Representation Grounded in Visual Context

no code implementations9 Nov 2017 Éloi Zablocki, Benjamin Piwowarski, Laure Soulier, Patrick Gallinari

Representing the semantics of words is a long-standing problem for the natural language processing community.

Word Embeddings

Efficient Document Indexing Using Pivot Tree

no code implementations21 May 2016 Gaurav Singh, Benjamin Piwowarski

We present a novel method for efficiently searching top-k neighbors for documents represented in high dimensional space of terms based on the cosine similarity.

Parameterized Neural Network Language Models for Information Retrieval

no code implementations6 Oct 2015 Benjamin Piwowarski, Sylvain Lamprier, Nicolas Despres

Although they present good abilities to cope with both term dependencies and vocabulary mismatch problems, thanks to the distributed representation of words they are based upon, such models could not be used readily in IR, where the estimation of one language model per document (or query) is required.

Information Retrieval Language Modelling

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