Gal Elidan
Authored Publications
Sort By
Factually Consistent Summarization via Reinforcement Learning with Textual Entailment Feedback
Paul Roit
Johan Ferret
Geoffrey Cideron
Matthieu Geist
Sertan Girgin
Léonard Hussenot
Nikola Momchev
Piotr Stanczyk
Nino Vieillard
Olivier Pietquin
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics, Association for Computational Linguistics (2023), 6252–6272
Preview abstract
Despite the seeming success of contemporary grounded text generation systems, they often tend to generate factually inconsistent text with respect to their input. This phenomenon is emphasized in tasks like summarization, in which the generated summaries should be corroborated by their source article. In this work we leverage recent progress on textual entailment models to directly address this problem for abstractive summarization systems. We use reinforcement learning with reference-free, textual-entailment rewards to optimize for factual consistency and explore the ensuing trade-offs, as improved consistency may come at the cost of less informative or more extractive summaries. Our results, according to both automatic metrics and human evaluation, show that our method considerably improves the faithfulness, salience and conciseness of the generated summaries.
View details
A Neural Encoder for Earthquake Rate Forecasting
Oleg Zlydenko
Brendan Meade
Alexandra Sharon Molchanov
Sella Nevo
Yohai bar Sinai
Scientific Reports (2023)
Preview abstract
Forecasting the timing of earthquakes is a long-standing challenge. Moreover, it is still debated how to formulate this problem in a useful manner, or to compare the predictive power of different models.
Here, we develop a versatile neural encoder of earthquake catalogs, and apply it to the fundamental problem of earthquake rate prediction, in the spatio-temporal point process framework. The epidemic
type aftershock sequence model (ETAS) effectively learns a small number of parameters to constrain assumed functional forms for the space and time relationships of earthquake sequences (e.g., Omori-Utsu law). Here we introduce learned spatial and temporal embeddings for point process earthquake forecast models that capture complex correlation structures. We demonstrate the generality of this neural representation as compared with ETAS model using train-test data splits and how it enables the incorporation of additional geophysical information. In rate prediction tasks, the generalized model shows > 4% improvement in information gain per earthquake and the simultaneous learning of anisotropic spatial structures analogous to fault traces. The trained network can be also used to perform short-term prediction tasks, showing similar improvement while providing a 1,000-fold reduction in run-time.
View details
Covering Uncommon Ground: Followup Question Generation for Answer Assessment
Alexandre Djerbetian
Reut Tsarfaty
ACL (2023) (to appear)
Preview abstract
In educational dialogue settings students often provide answers that are incomplete. In other words, there is a gap between the answer the student provides and the perfect answer expected by the teacher. Successful dialogue hinges on the teacher asking about this gap in an effective manner, thus creating a rich and interactive educational experience. Here we focus on the problem of generating such gap-focused questions (GFQ) automatically. We define the task, highlight key desired aspects of a good GFQ, and propose a model that satisfies these. Finally, we provide an evaluation of our generated questions and compare them to manually generated ones, demonstrating competitive performance.
View details
Active Learning with Label Comparisons
Shay Moran
Uncertainty in Artificial Intelligence (submitted) (2022)
Preview abstract
Supervised learning typically relies on manual annotation of the true labels. However, when there are many potential labels, it will be time consuming for a human annotator to search these for the best one. On the other hand, comparing two candidate labels is often much easier. In this paper, we focus on this type of pairwise supervision, and ask how it can be used effectively in learning, and in particular active learning. We obtain several surprising results in this context. In principle, finding the best label out of $k$ can be done with $k-1$ active queries. However, we show that there is a natural class where this approach is in fact sub-optimal, and that there is a more comparison-efficient active learning scheme. A key element in our analysis is the ``label neighborhood graph'' of the true distribution, which has an edge between two classes if they share a decision boundary. We also show that in the PAC setting, pairwise comparisons cannot provide improved sample complexity in the worst case. We complement our theoretical results with experiments, clearly demonstrating the effect of the neighborhood graph on sample complexity.
View details
Flood forecasting with machine learning models in an operational framework
Asher Metzger
Chen Barshai
Dana Weitzner
Frederik Kratzert
Gregory Begelman
Guy Shalev
Hila Noga
Moriah Royz
Niv Giladi
Ronnie Maor
Sella Nevo
Yotam Gigi
Zvika Ben-Haim
HESS (2022)
Preview abstract
Google’s operational flood forecasting system was developed to provide accurate real-time flood warnings to agencies and the public, with a focus on riverine floods in large, gauged rivers. It became operational in 2018 and has since expanded geographically. This forecasting system consists of four subsystems: data validation, stage forecasting, inundation modeling, and alert distribution. Machine learning is used for two of the subsystems. Stage forecasting is modeled with the Long Short-Term Memory (LSTM) networks and the Linear models. Flood inundation is computed with the Thresholding and the Manifold models, where the former computes inundation extent and the latter computes both inundation extent and depth. The Manifold model, presented here for the first time, provides a machine-learning alternative to hydraulic modeling of flood inundation. When evaluated on historical data, all models achieve sufficiently high-performance metrics for operational use. The LSTM showed higher skills than the Linear model, while the Thresholding and Manifold models achieved similar performance metrics for modeling inundation extent. During the 2021 monsoon season, the flood warning system was operational in India and Bangladesh, covering flood-prone regions around rivers with a total area of 287,000 km2, home to more than 350M people. More than 100M flood alerts were sent to affected populations, to relevant authorities, and to emergency organizations. Current and future work on the system includes extending coverage to additional flood-prone locations, as well as improving modeling capabilities and accuracy.
View details
Explaining in Style: Training a GAN to explain a classifier in StyleSpace
Yossi Gandelsman
Michal Yarom
Yoav Itzhak Wald
Phillip Isola
Michal Irani
Proc. ICCV 2021
Preview abstract
Image classification models can depend on multiple different semantic attributes of the image. An explanation of the decision of the classifier needs to both discover and visualize these properties. Here we present StylEx, a method for doing this, by training a generative model to specifically explain multiple attributes that underlie classifier decisions. A natural source for such attributes is the S-space of StyleGAN, which is known to generate semantically meaningful dimensions in the image. However, these will typically not correspond to classifier-specific attributes since standard GAN training is not dependent on the classifier. To overcome this, we propose training procedure for
a StyleGAN, which incorporates the classifier model. This results in an S-space that captures distinct attributes underlying classifier outputs. After training, the model can be used to visualize the effect of changing multiple attributes per image, thus providing an image-specific explanation. We apply StylEx to multiple domains, including animals, leaves, faces and retinal images. For these, we show how an image can be changed in different ways to change its classifier prediction.
Our results show that the method finds attributes that align well with semantic ones, generate meaningful image-specific explanations, and are interpretable as measured in user-studies.
View details
HydroNets: Leveraging River Structure for Hydrologic Modeling
Zach Moshe
Asher Feivel Metzger
Frederik Kratzert
Sella Nevo
Ran El-Yaniv
ICLR 2020, Workshop on AI for Earth Sciences (to appear)
Preview abstract
Accurate and scalable hydrologic models are essential building blocks of several
important applications, from water resource management to timely flood warnings. However, as the climate changes, precipitation and rainfall-runoff pattern
variations become more extreme, and accurate training data that can account for
the resulting distributional shifts become more scarce. In this work we present
a novel family of hydrologic models, called HydroNets, which leverages river
network structure. HydroNets are deep neural network models designed to exploit both basin specific rainfall-runoff signals, and upstream network dynamics,
which can lead to improved predictions at longer horizons. The injection of the
river structure prior knowledge reduces sample complexity and allows for scalable
and more accurate hydrologic modeling even with only a few years of data. We
present an empirical study over two large basins in India that convincingly support
the proposed model and its advantages.
View details
ML-based Flood Forecasting: Advances in Scale, Accuracy and Reach
Sella Nevo
Guy Shalev
NeurIPS HADR Workshop (2020)
Preview abstract
Floods are among the most common and deadly natural disasters in the world, and flood warning systems have been shown to be effective in reducing harm. Yet the majority of the world's vulnerable population does not have access to reliable and actionable warning systems, due to core challenges in scalability, computational costs, and data availability. In this paper we present two components of flood forecasting systems which were developed over the past year, providing access to these critical systems to 75 million people who didn't have this access before.
View details
Dynamic Composition for Conversational Domain Exploration
Eran Ofek
Sagie Israel Pudinsky
Asaf Revach
Shimi Salant
The Web Conference, ACM (2020), 872–883
Preview abstract
We study conversational domain exploration (CODEX), where the user’s goal is to enrich her knowledge of a given domain by conversing with an informative bot. Such conversations should be well grounded in high-quality domain knowledge as well as engaging and open-ended. A CODEX bot should be proactive and introduce relevant information even if not directly asked for by the user. The bot should also appropriately pivot the conversation to undiscovered regions of the domain. To address these dialogue characteristics, we introduce a novel approach termed dynamic composition that decouples candidate content generation from the flexible composition of bot responses. This allows the bot to control the source, correctness and quality of the offered content, while achieving flexibility via a dialogue manager that selects the most appropriate contents in a compositional manner. We implemented a CODEX bot based on dynamic composition and integrated it into the Google Assistant. As an example domain, the bot conversed about the NBA basketball league in a seamless experience, such that users were not aware whether they were conversing with the vanilla system or the one augmented with our CODEX bot. Results are positive and offer insights into what makes for a good conversation. To the best of our knowledge, this is the first real user experiment of open-ended dialogues as part of a commercial
assistant system.
View details
Spectral Algorithm for Shared Low-rank Matrix Regressions
Yotam Gigi
Sella Nevo
Ami Wiesel
2020 IEEE 11th Sensor Array and Multichannel Signal Processing Workshop (SAM) (2020)
Preview abstract
We consider multiple matrix regression tasks that share common weights in order to reduce sample complexity. For this purpose, we introduce the common mechanism regression model which assumes a shared right low-rank component across all tasks, but allows an individual per-task left low-rank component. We provide a closed form spectral algorithm for recovering the common component and derive a bound on its error as a function of the number of related tasks and the number of samples available for each of them. Both the algorithm and its analysis are natural extensions of known results in the context of phase retrieval and low rank reconstruction. We demonstrate the efficacy of our approach for the challenging task of remote river discharge estimation across multiple river sites, where data for each task is naturally scarce. In this scenario sharing a low-rank component between the tasks translates to a shared spectral reflection of the water, which is a true underlying physical model. We also show the benefit of the approach in the setting of image classification where the common component can be interpreted as the shared convolution filters.
View details
