arXiv subjects

Benjamin Piwowarski

Publications and source records attributed to Benjamin Piwowarski.

53 records · Page 3Linked to original sources

arXiv2021

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

Due to the discrete nature of words, language GANs require to be optimized from rewards provided by discriminator networks, via reinforcement learning methods. This is a much harder setting than for continuous tasks, which enjoy gradient flows from discriminators to generators, usually leading to dramatic learning instabilities. However, we claim that this can be solved by making discriminator and generator networks cooperate to produce output sequences during training. These cooperative outputs, inherently built to obtain higher discrimination scores, not only provide denser rewards for training, but also form a more compact artificial set for discriminator training, hence improving its accuracy and stability. In this paper, we show that our SelfGAN framework, built on this cooperative principle, outperforms Teacher Forcing and obtains state-of-the-art results on two challenging tasks, Summarization and Question Generation.

cs.CL↗

arXiv2021

QuestEval: Summarization Asks for Fact-based Evaluation

Summarization evaluation remains an open research problem: current metrics such as ROUGE are known to be limited and to correlate poorly with human judgments. To alleviate this issue, recent work has proposed evaluation metrics which rely on question answering models to assess whether a summary contains all the relevant information in its source document. Though promising, the proposed approaches have so far failed to correlate better than ROUGE with human judgments. In this paper, we extend previous approaches and propose a unified framework, named QuestEval. In contrast to established metrics such as ROUGE or BERTScore, QuestEval does not require any ground-truth reference. Nonetheless, QuestEval substantially improves the correlation with human judgments over four evaluation dimensions (consistency, coherence, fluency, and relevance), as shown in the extensive experiments we report.

cs.CL↗

arXiv2020

A White Box Analysis of ColBERT

Transformer-based models are nowadays state-of-the-art in ad-hoc Information Retrieval, but their behavior is far from being understood. Recent work has claimed that BERT does not satisfy the classical IR axioms. However, we propose to dissect the matching process of ColBERT, through the analysis of term importance and exact/soft matching patterns. Even if the traditional axioms are not formally verified, our analysis reveals that ColBERT: (i) is able to capture a notion of term importance; (ii) relies on exact matches for important terms.

cs.IR↗

arXiv2020

Transductive Zero-Shot Learning using Cross-Modal CycleGAN

In Computer Vision, Zero-Shot Learning (ZSL) aims at classifying unseen classes -- classes for which no matching training image exists. Most of ZSL works learn a cross-modal mapping between images and class labels for seen classes. However, the data distribution of seen and unseen classes might differ, causing a domain shift problem. Following this observation, transductive ZSL (T-ZSL) assumes that unseen classes and their associated images are known during training, but not their correspondence. As current T-ZSL approaches do not scale efficiently when the number of seen classes is high, we tackle this problem with a new model for T-ZSL based upon CycleGAN. Our model jointly (i) projects images on their seen class labels with a supervised objective and (ii) aligns unseen class labels and visual exemplars with adversarial and cycle-consistency objectives. 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. We further validate CM-GAN on a language grounding task, and on a new task that we propose: zero-shot sentence-to-image matching on MS COCO.

cs.CV↗

arXiv2020

Discriminative Adversarial Search for Abstractive Summarization

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. Inspired by Generative Adversarial Networks (GANs), wherein a discriminator is used to improve the generator, our method differs from GANs in that the generator parameters are not updated at training time and the discriminator is only used to drive sequence generation at inference time. We investigate the effectiveness of the proposed approach on the task of Abstractive Summarization: the results obtained show that a naive application of DAS improves over the state-of-the-art methods, with further gains obtained via discriminator retraining. Moreover, we show how DAS can be effective for cross-domain adaptation. Finally, all results reported are obtained without additional rule-based filtering strategies, commonly used by the best performing systems available: this indicates that DAS can effectively be deployed without relying on post-hoc modifications of the generated outputs.

cs.CL↗

arXiv2020

ColdGANs: Taming Language GANs with Cautious Sampling Strategies

Training regimes based on Maximum Likelihood Estimation (MLE) suffer from known limitations, often leading to poorly generated text sequences. At the root of these limitations is the mismatch between training and inference, i.e. the so-called exposure bias, exacerbated by considering only the reference texts as correct, while in practice several alternative formulations could be as good. Generative Adversarial Networks (GANs) can mitigate those limitations but the discrete nature of text has hindered their application to language generation: the approaches proposed so far, based on Reinforcement Learning, have been shown to underperform MLE. Departing from previous works, we analyze the exploration step in GANs applied to text generation, and show how classical sampling results in unstable training. We propose to consider alternative exploration strategies in a GAN framework that we name ColdGANs, where we force the sampling to be close to the distribution modes to get smoother learning dynamics. For the first time, to the best of our knowledge, the proposed language GANs compare favorably to MLE, and obtain improvements over the state-of-the-art on three generative tasks, namely unconditional text generation, question generation, and abstractive summarization.

cs.CL↗

arXiv2020

MLSUM: The Multilingual Summarization Corpus

We present MLSUM, the first large-scale MultiLingual SUMmarization dataset. Obtained from online newspapers, it contains 1.5M+ article/summary pairs in five different languages -- namely, French, German, Spanish, Russian, Turkish. Together with English newspapers from the popular CNN/Daily mail dataset, the collected data form a large scale multilingual dataset which can enable new research directions for the text summarization community. We report cross-lingual comparative analyses based on state-of-the-art systems. These highlight existing biases which motivate the use of a multi-lingual dataset.

cs.CL↗

arXiv2020

Incorporating Visual Semantics into Sentence Representations within a Grounded Space

Language grounding is an active field aiming at enriching textual representations with visual information. Generally, textual and visual elements are embedded in the same representation space, which implicitly assumes a one-to-one correspondence between modalities. This hypothesis does not hold when representing words, and becomes problematic when used to learn sentence representations --- the focus of this paper --- as a visual scene can be described by a wide variety of sentences. To overcome this limitation, we propose to transfer visual information to textual representations by learning an intermediate representation space: the grounded space. We further propose two new complementary objectives ensuring that (1) sentences associated with the same visual content are close in the grounded space and (2) similarities between related elements are preserved across modalities. We show that this model outperforms the previous state-of-the-art on classification and semantic relatedness tasks.

cs.CL↗

arXiv2019

Answers Unite! Unsupervised Metrics for Reinforced Summarization Models

Abstractive summarization approaches based on Reinforcement Learning (RL) have recently been proposed to overcome classical likelihood maximization. RL enables to consider complex, possibly non-differentiable, metrics that globally assess the quality and relevance of the generated outputs. ROUGE, the most used summarization metric, is known to suffer from bias towards lexical similarity as well as from suboptimal accounting for fluency and readability of the generated abstracts. We thus explore and propose alternative evaluation measures: the reported human-evaluation analysis shows that the proposed metrics, based on Question Answering, favorably compares to ROUGE -- with the additional property of not requiring reference summaries. Training a RL-based model on these metrics leads to improvements (both in terms of human or automated metrics) over current approaches that use ROUGE as a reward.

cs.CL↗

arXiv2019

Context-Aware Zero-Shot Learning for Object Recognition

Zero-Shot Learning (ZSL) aims at classifying unlabeled objects by leveraging auxiliary knowledge, such as semantic representations. A limitation of previous approaches is that only intrinsic properties of objects, e.g. their visual appearance, are taken into account while their context, e.g. the surrounding objects in the image, is ignored. Following the intuitive principle that objects tend to be found in certain contexts but not others, we propose a new and challenging approach, context-aware ZSL, that leverages semantic representations in a new way to model the conditional likelihood of an object to appear in a given context. Finally, through extensive experiments conducted on Visual Genome, we show that contextual information can substantially improve the standard ZSL approach and is robust to unbalanced classes.

cs.CV↗

arXiv2017

Learning Multi-Modal Word Representation Grounded in Visual Context

Representing the semantics of words is a long-standing problem for the natural language processing community. Most methods compute word semantics given their textual context in large corpora. More recently, researchers attempted to integrate perceptual and visual features. Most of these works consider the visual appearance of objects to enhance word representations but they ignore the visual environment and context in which objects appear. We propose to unify text-based techniques with vision-based techniques by simultaneously leveraging textual and visual context to learn multimodal word embeddings. We explore various choices for what can serve as a visual context and present an end-to-end method to integrate visual context elements in a multimodal skip-gram model. We provide experiments and extensive analysis of the obtained results.

cs.CL↗

arXiv2016

Efficient Document Indexing Using Pivot Tree

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. Mostly, documents are stored as bag-of-words tf-idf representation. One of the most used ways of computing similarity between a pair of documents is cosine similarity between the vector representations, but cosine similarity is not a metric distance measure as it doesn't follow triangle inequality, therefore most metric searching methods can not be applied directly. We propose an efficient method for indexing documents using a pivot tree that leads to efficient retrieval. We also study the relation between precision and efficiency for the proposed method and compare it with a state of the art in the area of document searching based on inner product.

cs.IR↗

arXiv2015

Parameterized Neural Network Language Models for Information Retrieval

Information Retrieval (IR) models need to deal with two difficult issues, vocabulary mismatch and term dependencies. Vocabulary mismatch corresponds to the difficulty of retrieving relevant documents that do not contain exact query terms but semantically related terms. Term dependencies refers to the need of considering the relationship between the words of the query when estimating the relevance of a document. A multitude of solutions has been proposed to solve each of these two problems, but no principled model solve both. In parallel, in the last few years, language models based on neural networks have been used to cope with complex natural language processing tasks like emotion and paraphrase detection. 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. This is both computationally unfeasible and prone to over-fitting. Based on a recent work that proposed to learn a generic language model that can be modified through a set of document-specific parameters, we explore use of new neural network models that are adapted to ad-hoc IR tasks. Within the language model IR framework, we propose and study the use of a generic language model as well as a document-specific language model. Both can be used as a smoothing component, but the latter is more adapted to the document at hand and has the potential of being used as a full document language model. We experiment with such models and analyze their results on TREC-1 to 8 datasets.

cs.IR↗

arXiv2013

Diversification Based Static Index Pruning - Application to Temporal Collections

Nowadays, web archives preserve the history of large portions of the web. As medias are shifting from printed to digital editions, accessing these huge information sources is drawing increasingly more attention from national and international institutions, as well as from the research community. These collections are intrinsically big, leading to index files that do not fit into the memory and an increase query response time. Decreasing the index size is a direct way to decrease this query response time. Static index pruning methods reduce the size of indexes by removing a part of the postings. In the context of web archives, it is necessary to remove postings while preserving the temporal diversity of the archive. None of the existing pruning approaches take (temporal) diversification into account. In this paper, we propose a diversification-based static index pruning method. It differs from the existing pruning approaches by integrating diversification within the pruning context. We aim at pruning the index while preserving retrieval effectiveness and diversity by pruning while maximizing a given IR evaluation metric like DCG. We show how to apply this approach in the context of web archives. Finally, we show on two collections that search effectiveness in temporal collections after pruning can be improved using our approach rather than diversity oblivious approaches.

cs.IR↗

arXiv2012

Beyond Cumulated Gain and Average Precision: Including Willingness and Expectation in the User Model

In this paper, we define a new metric family based on two concepts: The definition of the stopping criterion and the notion of satisfaction, where the former depends on the willingness and expectation of a user exploring search results. Both concepts have been discussed so far in the IR literature, but we argue in this paper that defining a proper single valued metric depends on merging them into a single conceptual framework.

cs.IR↗

arXiv2012

The Kernel Quantum Probabilities (KQP) Library

In this document, we show how the different quantities necessary to compute kernel quantum probabilities can be computed. This document form the basis of the implementation of the Kernel Quantum Probability (KQP) open source project

cs.MS↗

arXiv2010

Exploring a Multidimensional Representation of Documents and Queries (extended version)

In Information Retrieval (IR), whether implicitly or explicitly, queries and documents are often represented as vectors. However, it may be more beneficial to consider documents and/or queries as multidimensional objects. Our belief is this would allow building "truly" interactive IR systems, i.e., where interaction is fully incorporated in the IR framework. The probabilistic formalism of quantum physics represents events and densities as multidimensional objects. This paper presents our first step towards building an interactive IR framework upon this formalism, by stating how the first interaction of the retrieval process, when the user types a query, can be formalised. Our framework depends on a number of parameters affecting the final document ranking. In this paper we experimentally investigate the effect of these parameters, showing that the proposed representation of documents and queries as multidimensional objects can compete with standard approaches, with the additional prospect to be applied to interactive retrieval.

cs.IR↗