Publications | Hadas Raviv

2008

EJC

Growth Retardation and Survival Prolongation of Experimental Lung Carcinoma By Interstitial Ra-224 Loaded Wires Releasing Diffusing Alpha-Emitting Atoms

Tomer Cooks, Margalit Efrati, Hadas Bittan (Raviv), and 4 more authors

EJC Supplements, 2008

2009

IJROBP

Local Control of Lung Derived Tumors by Diffusing Alpha-Emitting Atoms Released From Intratumoral Wires Loaded With Radium-224

Tomer Cooks, Michael Schmidt, Hadas Bittan (Raviv), and 4 more authors

International Journal of Radiation Oncology Biology Physics, 2009
EJC

2044 Tumor Growth Inhibition and Necrosis Following Treatment of Experimental Solid Malignant Tumors by Intra-Tumoral Ra-224 Loaded Sources

Yona Keisari, Tomer Cooks, Hadas Bittan (Raviv), and 7 more authors

EJC Supplements, 2009

2012

JIWES

A Ranking Framework for Entity Oriented Search Using Markov Random Fields

Hadas Raviv, David Carmel, and Oren Kurland

In Proceedings of the 1st Joint International Workshop on Entity-Oriented and Semantic Search, 2012

Abs PDF

In this work we present a general model for entity ranking that is based on the Markov Random Field approach for modeling various types of dependencies between the query and the entity. We show that this model actually extends existing approaches for entity ranking while aggregating all pieces of relevance evidences in a unified way. We evaluated the performance of our model using the INEX datasets. Our results show that our ranking model significantly out-performs leading INEX systems in the tracks of 2007 and 2008, and is equivalent to the best results achieved in the 2009 track.
Translational

Local control of experimental malignant pancreatic tumors by treatment with a combination of chemotherapy and intratumoral 224Radium-loaded wires releasing alpha-emitting atoms

Galit Horev-Drori, Tomer Cooks, Hadas Bittan (Raviv), and 6 more authors

Translational Research, 2012

Abs PDF

We developed 224Ra-loaded wires that when inserted into solid tumors, release radioactive atoms that spread in the tumor and irradiate it effectively with alpha particles (diffusing alpha-emitters radiation therapy [DaRT]). In this study, we tested the ability of intratumoral 224Ra-loaded wires to control the local growth of pancreatic tumors and the enhancement of this effect by chemotherapy. Pancreatic mouse tumors (Panc02) were treated with 224Ra-loaded wire(s) with or without gemcitabine. The tumor size and survival were monitored, and autoradiography was performed to evaluate the spread of radioactive atoms inside the tumor. Mouse and human pancreatic cancer cells, irradiated in vitro by alpha particles with or without chemotherapy, were evaluated for cell growth inhibition. The insertion of 224Ra-loaded wires into pancreatic tumors in combination with gemcitabine achieved significant local control and was superior to each treatment alone. A dosimetric analysis showed the spread of radioactive atoms in the tumor around the wires. Alpha particles combined with gemcitabine or 5-FU killed mouse and human cells in vitro better than each treatment alone. DaRT in combination with gemcitabine was proven effective against pancreatic tumors in vivo and in vitro, and the process may be applicable as a palliative treatment for patients with pancreatic cancer.

2013

SIGIR

The Cluster Hypothesis for Entity Oriented Search

Hadas Raviv, Oren Kurland, and David Carmel

In Proceedings of the 36th International ACM SIGIR Conference on Research and Development in Information Retrieval, 2013

Abs PDF

In this work we study the cluster hypothesis for entity oriented search (EOS). Specifically, we show that the hypothesis can hold to a substantial extent for several entity similarity measures. We also demonstrate the retrieval effectiveness merits of using clusters of similar entities for EOS.

2014

SIGIR

Query Performance Prediction for Entity Retrieval

Hadas Raviv, Oren Kurland, and David Carmel

In Proceedings of the 37th International ACM SIGIR Conference on Research & Development in Information Retrieval, 2014

Abs PDF

We address the query-performance-prediction task for entity retrieval; that is, retrieval effectiveness is estimated with no relevance judgements. First we show how to adapt state-of-the-art query-performance predictors proposed for document retrieval to the entity retrieval domain. We then present a novel predictor that is based on the cluster hypothesis. Evaluation performed with the INEX entity ranking track collections shows that our predictor can often outperform the most effective predictors we experimented with.
SIGIR

Entity-Based Retrieval

Hadas Raviv

In Proceedings of the 37th International ACM SIGIR Conference on Research & Development in Information Retrieval, 2014

Abs PDF

We address the core challenge of the entity retrieval task: ranking entities in response to a query by their presumed relevance to the information need that the query represents. As an initial research direction we explored two models for entity ranking that were evaluated using the INEX entity ranking dataset and which posted promising performance. A natural future direction to explore is how to generalize these models to address various types of information needs that are associated with entities.

2016

SIGIR

Document Retrieval Using Entity-Based Language Models

Hadas Raviv, Oren Kurland, and David Carmel

In Proceedings of the 39th International ACM SIGIR Conference on Research and Development in Information Retrieval, 2016

Abs PDF

We address the ad hoc document retrieval task by devising novel types of entity-based language models. The models utilize information about single terms in the query and documents as well as term sequences marked as entities by some entity-linking tool. The key principle of the language models is accounting, simultaneously, for the uncertainty inherent in the entity-markup process and the balance between using entity-based and term-based information. Empirical evaluation demonstrates the merits of using the language models for retrieval. For example, the performance transcends that of a state-of-the-art term proximity method. We also show that the language models can be effectively used for cluster-based document retrieval and query expansion.

2020

NeurIPS

Exemplar Guided Active Learning

Jason S. Hartford, Kevin Leyton-Brown, Hadas Raviv, and 3 more authors

In Advances in Neural Information Processing Systems, 2020

Abs PDF

We consider the problem of wisely using a limited budget to label a small subset of a large unlabeled dataset. For example, consider the NLP problem of word sense disambiguation. For any word, we have a set of candidate labels from a knowledge base, but the label set is not necessarily representative of what occurs in the data: there may exist labels in the knowledge base that very rarely occur in the corpus because the sense is rare in modern English; and conversely there may exist true labels that do not exist in our knowledge base. Our aim is to obtain a classifier that performs as well as possible on examples of each “common class” that occurs with frequency above a given threshold in the unlabeled set while annotating as few examples as possible from “rare classes” whose labels occur with less than this frequency. The challenge is that we are not informed which labels are common and which are rare, and the true label distribution may exhibit extreme skew. We describe an active learning approach that (1) explicitly searches for rare classes by leveraging the contextual embedding spaces provided by modern language models, and (2) incorporates a stopping rule that ignores classes once we prove that they occur below our target threshold with high probability. We prove that our algorithm only costs logarithmically more than a hypothetical approach that knows all true label frequencies and show experimentally that incorporating automated search can significantly reduce the number of samples needed to reach target accuracy levels.