Papers by Ido Dagan

CoRefi: A Crowd Sourcing Suite for Coreference Annotation (2020.emnlp-demos)

Challenge:	Recognizing that various textual spans across multiple texts refer to the same entity or event is an important NLP task.
Approach:	They propose a neural architecture for cross-document coreference resolution by representing an event mention using its lexical span, surrounding context, and relation to other mentions via predicate-arguments structures.
Outcome:	The proposed model outperforms the state-of-the-art event coreference model on ECB+ while providing the first entity coreference results on this corpus.

Copied to clipboard

Ari Bornstein, Arie Cattan, Ido Dagan

Asking It All: Generating Contextualized Questions for any Semantic Role (2021.emnlp-main)

Challenge:	Using a web-based coreference annotation suite, we demonstrate that non-expert annotators can be trained to perform and review coreference resolution tasks.
Approach:	They propose a web-based coreference annotation suite oriented for crowdsourcing that provides guided onboarding and a novel algorithm for a reviewing phase.
Outcome:	The proposed tool provides guided onboarding and a novel algorithm for a review phase.

Copied to clipboard

Valentina Pyatkin, Paul Roit, Julian Michael, Yoav Goldberg, Reut Tsarfaty, Ido Dagan

Question Generation

Challenge:	Existing approaches to question generation require conditioning on existing answers in text . previous work required human-curated templates, limiting coverage and question fluency .
Approach:	They propose a task of role question generation that produces a prototype and revises it to be contextually appropriate for the passage.
Outcome:	The proposed model generates diverse and well-formed questions for a large, broad-coverage ontology of predicates and roles.

Peek Across: Improving Multi-Document Modeling via Cross-Document Question-Answering (2023.acl-long)

Copied to clipboard

Avi Caciularu, Matthew Peters, Jacob Goldberger, Ido Dagan, Arman Cohan

WEC: Deriving a Large-scale Cross-document Event Coreference dataset from Wikipedia (2021.naacl-main)

Challenge:	Among recent NLP research, multi-document processing is gaining increasing attention due to the need to handle and process an increasing amount of textual data and available documents online.
Approach:	They propose to pre-train a generic multi-document model from a cross-document question answering pre-training objective by generating salient sentences from one document and challenging it to recover the sentence from which it was generated.
Outcome:	The proposed model outperforms zero-shot GPT-3.5 and GPT-4 in multiple document tasks and generates the correct answer and the salient sentence from a salient document.

Copied to clipboard

Alon Eirew, Arie Cattan, Ido Dagan

QANom: Question-Answer driven SRL for Nominalizations (2020.coling-main)

Challenge:	Existing datasets for cross-document event coreference resolution are limited and small . authors present a method for identifying clusters of text mentions that refer to the same event .
Approach:	They propose a method for generating a large-scale Wikipedia event coreference dataset . they use a generic approach that adapts state-of-the-art models to the cross-document setting .
Outcome:	The proposed method outperforms existing models and can be applied to other languages.

Copied to clipboard

Ayal Klein, Jonathan Mamou, Valentina Pyatkin, Daniela Stepanov, Hangfeng He, Dan Roth, Luke Zettlemoyer, Ido Dagan

CDLM: Cross-Document Language Modeling (2021.findings-emnlp)

Challenge:	Traditionally, SRL annotations focus on verbal predicates, but other types of predicate are frequent in natural language.
Approach:	They propose a semantic scheme for capturing predicate-argument relations for nominalizations, termed QANom, using crowdsourcing and QA-driven annotations.
Outcome:	The proposed scheme outperforms existing annotations and is useful for downstream tasks.

Copied to clipboard

Avi Caciularu, Arman Cohan, Iz Beltagy, Matthew Peters, Arie Cattan, Ido Dagan

Language Models

Challenge:	Existing language models (LMs) provide powerful representations for internal text structure, but there are important applications for multi-text tasks.
Approach:	They propose a pretraining approach that incorporates two key ideas into the masked language modeling objective.
Outcome:	The proposed model improves over existing models and sets of long-range transformers and can be easily applied to multiple multi-text tasks.

QASem Parsing: Text-to-text Modeling of QA-based Semantics (2022.emnlp-main)

Copied to clipboard

Ayal Klein, Eran Hirsch, Ron Eliav, Valentina Pyatkin, Avi Caciularu, Ido Dagan

Question Answering

Challenge:	Existing work suggests the appeals of incorporating explicit semantic representations into NLP . semi-structured natural language structures provide an intermediate meaning-capturing representation .
Approach:	They propose a semi-structured natural-language representation of textual information . they examine input and output linearization strategies and multitask learning .
Outcome:	The proposed model is based on pre-trained sequence-to-sequence language models . it is easy to use and can be used for downstream tasks that benefit from it .

PrefixNLI: Detecting Factual Inconsistencies as Soon as They Arise (2026.acl-long)

Copied to clipboard

Sapir Harary, Eran Hirsch, Aviv Slobodkin, David Wan, Mohit Bansal, Ido Dagan

Textual Inference

Challenge:	Large Language Models (LLMs) are prone to factually inconsistent statements, known as hallucinations.
Approach:	They propose to train a specialized model that detects inconsistencies over text prefixes to improve generation faithfulness by 5-14 F1 points.
Outcome:	The proposed model outperforms baseline models by 5-14 F1 points in prefix-level entailment.

Re-Examining Summarization Evaluation across Multiple Quality Criteria (2023.findings-emnlp)

Copied to clipboard

Ori Ernst, Ori Shapira, Ido Dagan, Ran Levy

Summarization

Challenge:	a number of automated evaluation metrics are evaluated by multiple quality criteria, such as relevance, consistency, fluency and coherence.
Approach:	They propose a method that removes the confounding variable and detects unreliable correlations.
Outcome:	The proposed method detects unreliable correlations between QCs and human scores . it is based on a multi-QC setup, but it fails to detect summary corruptions .

Better Rewards Yield Better Summaries: Learning to Summarise Without References (D19-1)

Copied to clipboard

Florian Böhm, Yang Gao, Christian M. Meyer, Ori Shapira, Ido Dagan, Iryna Gurevych

ABSApp: A Portable Weakly-Supervised Aspect-Based Sentiment Extraction System (D19-3)

Challenge:	Reinforcement Learning (RL)-based document summarisation systems produce state-of-the-art performance in terms of ROUGE scores, but high summaries receive low human judgement.
Approach:	They propose to learn a reward function from human ratings on 2,500 summaries to generate human-appealing summary.
Outcome:	The proposed reward function can generate human-appealing summaries without reference summary input.

Copied to clipboard

Oren Pereg, Daniel Korat, Moshe Wasserblat, Jonathan Mamou, Ido Dagan

Sentiment Analysis

Challenge:	a portable system for weakly-supervised aspect-based sentiment extraction is presented . ABSApp is a weakly supervised aspect based sentiment analysis system .
Approach:	They present a portable system for weakly-supervised aspect-based sentiment extraction . ABSApp generates domain-specific aspect and opinion lexicons based on unlabeled dataset .
Outcome:	The proposed system is interpretable and user friendly and can be quickly and cost-effectively used across domains . it generates domain-specific aspect and opinion lexicons, edits them, and generates an aspect-based sentiment report . the system has been successfully used in movie review analysis and convention impact analysis .

Effective QA-Driven Annotation of Predicate–Argument Relations Across Languages (2026.eacl-long)

Copied to clipboard

Jonathan Davidov, Aviv Slobodkin, Shmuel Tomi Klein, Reut Tsarfaty, Ido Dagan, Ayal Klein

SummHelper: Collaborative Human-Computer Summarization (2023.emnlp-demo)

Challenge:	Explicit representations of predicate-argument relations are a cornerstone of natural language understanding.
Approach:	They propose a cross-linguistic projection approach that reuses an English QA-SRL parser within a constrained translation and word-alignment pipeline to automatically generate question-answer annotations aligned with target-language predicates.
Outcome:	The proposed approach outperforms strong multilingual LLMs in Hebrew, Russian, and French.

Copied to clipboard

Aviv Slobodkin, Niv Nachum, Shmuel Amar, Ori Shapira, Ido Dagan

Summarization

Challenge:	Existing approaches for text summarization are mostly automated, with limited space for human intervention and control.
Approach:	They propose a 2-phase summarization assistant that facilitates human-machine collaboration . it suggests possible content and generates a coherent summary from these selections . authors hope to improve the efficiency of the computer and human-involved approach .
Outcome:	The proposed summarization assistant is a 2-phase summarizing assistant . it suggests potential content and consolidates the output with visual mappings . the proposed system is available for free on youtube .

The Curious Case of Hallucinatory (Un)answerability: Finding Truths in the Hidden States of Over-Confident Large Language Models (2023.emnlp-main)

Copied to clipboard

Aviv Slobodkin, Omer Goldman, Avi Caciularu, Ido Dagan, Shauli Ravfogel

Language Models

Challenge:	Large language models (LLMs) have been shown to possess impressive capabilities, but they are not problem-free.
Approach:	They explore the behavior of large language models when presented with (un)answerable queries.
Outcome:	The proposed models encode the answerability of an input query, the authors show . they also show that the first decoded token is a strong indicator .

Crowdsourcing Lightweight Pyramids for Manual Summary Evaluation (N19-1)

Copied to clipboard

Ori Shapira, David Gabay, Yang Gao, Hadar Ronen, Ramakanth Pasunuru, Mohit Bansal, Yael Amsterdamer, Ido Dagan

Challenge:	Manual evaluation methods are perceived as insufficient due to the high cost of the Pyramid method and the required expertise.
Approach:	They propose a crowdsourced method that compares system summaries to references and uses crowdsourced scripts to analyze the results.
Outcome:	The proposed method shows higher correlation relative to the original Pyramid method.

Extending Multi-Document Summarization Evaluation to the Interactive Setting (2021.naacl-main)

Copied to clipboard

Ori Shapira, Ramakanth Pasunuru, Hadar Ronen, Mohit Bansal, Yael Amsterdamer, Ido Dagan

Design Choices for Crowdsourcing Implicit Discourse Relations: Revealing the Biases Introduced by Task Design (2023.tacl-1)

Challenge:	Existing approaches to interactive summarization are incomparable and divergent . a key gap in the development and adoption of interactive summaries is the lack of evaluation methodologies and benchmarks for meaningful comparison of systems.
Approach:	They propose an end-to-end evaluation framework for interactive summarization based on expansion-based interaction . framework includes procedure of collecting real user sessions, evaluation measures relying on summarizing standards, but adapted to reflect interaction.
Outcome:	The proposed evaluation framework is based on evaluations of baseline implementations and is available publicly as a benchmark.

Copied to clipboard

Valentina Pyatkin, Frances Yung, Merel C. J. Scholman, Reut Tsarfaty, Ido Dagan, Vera Demberg

Challenge:	Disagreement in natural language annotation has been studied from a perspective of biases introduced by the annotators and the annotation frameworks.
Approach:	They propose to analyze task design bias in crowdsourced annotations where lay annotators are used to elicit interpretations.
Outcome:	The proposed methods can push annotators towards certain relations and some discourse relation senses can be better elicited with one or the other approach.

Denoising Word Embeddings by Averaging in a Shared Space (2021.starsem-1)

Copied to clipboard

Avi Caciularu, Ido Dagan, Jacob Goldberger

Representation Learning

Challenge:	Continuous word embeddings have been introduced several years ago as a standard building block for NLP tasks.
Approach:	They propose a method of fusing word embeddings that were trained on the same corpus but with different initializations.
Outcome:	The proposed method improves word embeddings on a range of tasks.

How “Multi” is Multi-Document Summarization? (2022.emnlp-main)

Copied to clipboard

Ruben Wolhandler, Arie Cattan, Ori Ernst, Ido Dagan

Small Models, Big Results: Achieving Superior Intent Extraction through Decomposition (2025.emnlp-main)

Challenge:	Multi-document summarization (MDS) aims at combining information spread across multiple documents . a single document often covers the full summary content .
Approach:	They propose a measure to evaluate the degree to which a summary is "disperse" they propose to combine information from multiple documents into a single document to generate a concise summary .
Outcome:	The proposed measure evaluates the degree to which a summary is "disperse" the measure is applied to several popular MDS datasets and state-of-the-art systems.

Copied to clipboard

Danielle Cohen, Yoni Halpern, Noam Kahlon, Joel Oren, Omri Berkovitch, Sapir Caduri, Ido Dagan, Anatoly Efros

Sentiment Analysis

Challenge:	Large multi-modal large language models are good at extracting user intents from UI sequences, but smaller models struggle with accurate intent inference.
Approach:	They propose a decomposed approach for extracting user intent from small models . they perform structured interaction summarization and intent extraction using a fine-tuned model .
Outcome:	The proposed method surpasses the performance of large MLLMs in the intent extraction task.

Revisiting Sentence Union Generation as a Testbed for Text Consolidation (2023.findings-acl)

Copied to clipboard

Eran Hirsch, Valentina Pyatkin, Ruben Wolhandler, Avi Caciularu, Asi Shefer, Ido Dagan

Challenge:	In order to acquire knowledge on a new subject, it is often necessary to consult multiple sources of written information.
Approach:	They propose to revisit the sentence union generation task as an effective well-defined testbed for assessing text consolidation capabilities.
Outcome:	The proposed evaluation protocol includes human and automatic evaluations.

Revisiting Few-shot Relation Classification: Evaluation Data and Classification Schemes (2021.tacl-1)

Copied to clipboard

Ofer Sabo, Yanai Elazar, Yoav Goldberg, Ido Dagan

Semantic Text Processing

Challenge:	a recent study has focused on few-shot learning (FSL) for relation classification, but it requires large amounts of training data.
Approach:	They propose a method for deriving more realistic few-shot test data from available datasets for supervised RC.
Outcome:	The proposed method yields a challenging benchmark for FSL-RC on which state of the art models show poor performance.

Cross-document Event Coreference Search: Task, Dataset and Modeling (2022.emnlp-main)

Copied to clipboard

Alon Eirew, Avi Caciularu, Ido Dagan

Paraphrase to Explicate: Revealing Implicit Noun-Compound Relations (P18-1)

Challenge:	Cross-document Event Coreference resolution is the task of identifying clusters of text mentions that refer to the same event, whether within a single document or across a document collection.
Approach:	They propose a cross-document coreference search task that searches for all coreferring mentions for a query event in a large document collection.
Outcome:	The proposed model integrates a powerful coreference scoring scheme into the DPR architecture, yielding improved performance.

Copied to clipboard

Vered Shwartz, Ido Dagan

Information Retrieval

Challenge:	Existing methods for paraphrasing nouncompounds lack the ability to generalize and have a hard time interpreting infrequent or new noun-compound.
Approach:	They propose a neural model that generalizes better by representing paraphrases in a continuous space, generalizing for both unseen noun-compounds and rare paraphrase.
Outcome:	The proposed model generalizes better by representing paraphrases in a continuous space, generalizing for unseen noun-compounds and rare paraphrase.

Within-Between Lexical Relation Classification (2020.emnlp-main)

Copied to clipboard

Oren Barkan, Avi Caciularu, Ido Dagan

Text Classification

Challenge:	Existing methods for recognizing lexical-semantic relations between words are path-based and distributional.
Approach:	They propose a novel Within-Between Relation model for recognizing lexical-semantic relations between words.
Outcome:	The proposed model outperforms baselines across various benchmarks and is competitive and competitive.

Superlatives in Context: Modeling the Implicit Semantics of Superlatives (2025.naacl-long)

Copied to clipboard

Valentina Pyatkin, Bonnie Webber, Ido Dagan, Reut Tsarfaty

Challenge:	a study of superlatives shows that the semantics of superlations in context can be challenging for contemporary models.
Approach:	They propose a unified account of superlative semantics which allows for a broad-coverage annotation schema.
Outcome:	The proposed schema allows for interpreting superlative expressions and their semantic interpretations.

QA-Align: Representing Cross-Text Content Overlap by Aligning Question-Answer Propositions (2021.emnlp-main)

Copied to clipboard

Daniela Brook Weiss, Paul Roit, Ayal Klein, Ori Ernst, Ido Dagan

Question Answering

Challenge:	Existing approaches to consolidate textual inputs are difficult to implement . a recent study aims to capture content overlap by combining multiple textual elements .
Approach:	They propose to align predicate-argument relations across texts to represent content overlap . their setting exploits QA-SRL, utilizing question-answer pairs to capture predicates .
Outcome:	The proposed task captures content overlap beyond lexical similarity and complements cross-document coreference with proposition-level links, offering potential use for downstream tasks.

Teach the Rules, Provide the Facts: Targeted Relational-knowledge Enhancement for Textual Inference (2021.starsem-1)

Copied to clipboard

Ohad Rozen, Shmuel Amar, Vered Shwartz, Ido Dagan

Language Models

Challenge:	InferBERT is a method to enhance transformer-based inference models with relevant relational knowledge.
Approach:	They propose to enhance transformer-based inference models with relevant relational knowledge by injecting relevant facts at test time into the model.
Outcome:	The proposed method outperforms existing models on the challenge datasets while outperforming existing models.

Controlled Text Reduction (2022.emnlp-main)

Copied to clipboard

Aviv Slobodkin, Paul Roit, Eran Hirsch, Ori Ernst, Ido Dagan

Supervised Open Information Extraction (N18-1)

Challenge:	Abstractive text summarization models separate the salience detection phase from the text generation phase.
Approach:	They propose to formalize Controlled Text Reduction as a standalone task . they advocate the potential of such models for modular fully-automatic summarization .
Outcome:	The proposed model shows that it is possible to produce a reduced version of a source text using decomposed modeling.

Copied to clipboard

Gabriel Stanovsky, Julian Michael, Luke Zettlemoyer, Ido Dagan

Ranking Generated Summaries by Correctness: An Interesting but Challenging Application for Natural Language Inference (P19-1)

Challenge:	Existing methods for Open Information Extraction (Open IE) use semisupervised approaches or rule-based algorithms.
Approach:	They propose a supervised approach to Open Information Extraction (Open IE) they build on recent deep Semantic Role Labeling models to extract Open IE tuples .
Outcome:	The proposed model outperforms state-of-the-art Open IE systems on benchmark datasets.

Copied to clipboard

Tobias Falke, Leonardo F. R. Ribeiro, Prasetya Ajie Utama, Ido Dagan, Iryna Gurevych

Textual Inference

Challenge:	Recent advances on abstractive summarization have led to fluent summaries, but factual errors in generated summary still severely limit their use in practice.
Approach:	They evaluate summaries produced by state-of-the-art models via crowdsourcing and show that factual errors occur frequently.
Outcome:	The proposed models can detect errors and reduce them by reranking alternative summaries.

Automatic Thesaurus Construction for Modern Hebrew (L18-1)

Copied to clipboard

Chaya Liebeskind, Ido Dagan, Jonathan Schler

Syntactic Text Processing

Challenge:	Modern Hebrew lacks lexical resources fundamental to many natural language processing tools.
Approach:	They propose a method for generating a cooccurrence based thesaurus in a MRL and a distributional similarity method for Hebrew.
Outcome:	The proposed method is not optimal for modern Hebrew, the authors show . they used Hebrew WordNet as their gold standard for the analysis .

LAQuer: Localized Attribution Queries in Content-grounded Generation (2025.acl-long)

Copied to clipboard

Eran Hirsch, Aviv Slobodkin, David Wan, Elias Stengel-Eskin, Mohit Bansal, Ido Dagan

Don’t Add, don’t Miss: Effective Content Preserving Generation from Pre-Selected Text Spans (2023.findings-emnlp)

Challenge:	Existing attribution methods associate entire sentences with source documents, which can be overwhelming for users seeking to fact-check specific claims.
Approach:	They propose a task that localizes selected spans of generated output to their corresponding source spans, allowing fine-grained and user-directed attribution.
Outcome:	The proposed task localizes selected spans of generated output to their corresponding source spans, allowing fine-grained and user-directed attribution.

Copied to clipboard

Aviv Slobodkin, Avi Caciularu, Eran Hirsch, Ido Dagan

Extending Multi-Text Sentence Fusion Resources via Pyramid Annotations (2022.naacl-main)

Challenge:	Existing CTR models are mediocre and lack reliable performance . authors propose an explicit decomposition of these two subtasks into a single task .
Approach:	They propose an isolated task that challenges models to generate coherent text conforming to pre-selected content within the input text ("highlights") authors propose a high-quality, open-source CTR model that tackles two prior key limitations: inadequate enforcement of the content-preservation constraint, and suboptimal silver training data.
Outcome:	The proposed model significantly improves silver training data quality over the existing model, with up to 30 ROUGE-L points.

Copied to clipboard

Daniela Brook Weiss, Paul Roit, Ori Ernst, Ido Dagan

Challenge:	Existing datasets for sentence fusion tasks are limited in size and scope . despite recent advances, cross-document tasks such as multi-document summarization have not progressed with the same pace.
Approach:	They propose to extend a sentence fusion dataset by almost four times its original size . they relabel the dataset and employ more data sources to improve model performance .
Outcome:	The proposed dataset triples the size of an earlier dataset and improves performance . it also includes more complex training instances better reflecting those found in "the wild"

Cross-document Coreference Resolution over Predicted Mentions (2021.findings-acl)

Copied to clipboard

Arie Cattan, Alon Eirew, Gabriel Stanovsky, Mandar Joshi, Ido Dagan

Controlled Crowdsourcing for High-Quality QA-SRL Annotation (2020.acl-main)

Challenge:	Cross-document coreference resolution has been under-explored in recent years . however, the challenge of cross-document resolution remains relatively under-studied .
Approach:	They propose a model for cross-document coreference resolution from raw text that extends a prominent withindocument corefer model to the CD setting.
Outcome:	The proposed model achieves competitive results for event and entity coreference resolution on gold mentions.

Copied to clipboard

Paul Roit, Ayal Klein, Daniela Stepanov, Jonathan Mamou, Julian Michael, Gabriel Stanovsky, Luke Zettlemoyer, Ido Dagan

User-Centric Evidence Ranking for Attribution and Fact Verification (2026.eacl-long)

Challenge:	Question-answer driven Semantic Role Labeling (QA-SRL) is an open and natural flavour of SRL, potentially attainable from laymen.
Approach:	They propose a question-answer driven semantic role labeling approach that uses question-announced questions to label predicate-argument relationships.
Outcome:	The proposed method yields high-quality annotation with dramatically higher coverage, enabling future replicable research of natural semantic annotations.

Copied to clipboard

Guy Alt, Eran Hirsch, Serwar Basch, Ido Dagan, Oren Glickman

Responsible & Trustworthy NLP

Challenge:	Large language models often present users with insufficient or redundant information, leading to inefficient and error-prone verification.
Approach:	They propose a task that prioritizes presenting sufficient information as early as possible in a ranked list.
Outcome:	The proposed task minimizes user reading effort while making all available evidence accessible for sequential verification.

Design Choices in Crowdsourcing Discourse Relation Annotations: The Effect of Worker Selection and Training (2022.lrec-1)

Copied to clipboard

Merel Scholman, Valentina Pyatkin, Frances Yung, Ido Dagan, Reut Tsarfaty, Vera Demberg

Is It Really Long Context if All You Need Is Retrieval? Towards Genuinely Difficult Long Context NLP (2024.emnlp-main)

Challenge:	Recent methods have obtained promising results by extracting relation labels from participants . obtaining linguistic annotations from novice crowdworkers is difficult . crowdsourcing allows for fast and cost-effective collection of labelled data, but because tasks need to be intuitive, crowdworker cannot be asked to perform them.
Approach:	They propose to use a selection-only approach to obtain linguistic annotations from novices . current study shows that the method is cost- and time-intensive .
Outcome:	The current study shows that selection and training improves the agreement between workers and gold labels, but the method is cost- and time-intensive.

Copied to clipboard

Omer Goldman, Alon Jacovi, Aviv Slobodkin, Aviya Maimon, Ido Dagan, Reut Tsarfaty

Information Retrieval

Challenge:	Improvements in language models’ capabilities have pushed their applications towards longer contexts, making long-context evaluation and development an active research area.
Approach:	They propose to unpack the taxonomy of long-context based on the properties that make them more difficult with longer contexts.
Outcome:	The proposed taxonomy is based on the properties that make them more difficult with longer contexts.

Zero-Shot Transfer Learning for Event Extraction (P18-1)

Copied to clipboard

Lifu Huang, Heng Ji, Kyunghyun Cho, Ido Dagan, Sebastian Riedel, Clare Voss

Proposition-Level Clustering for Multi-Document Summarization (2022.naacl-main)

Challenge:	Existing supervised event extraction methods rely on manual annotations and features specific to each event type.
Approach:	They propose a framework that maps event mentions to a specific type in an event ontology . they use existing annotations to extract event types from unstructured text data .
Outcome:	The proposed framework can be applied to new unseen event types without manual annotations.

Copied to clipboard

Ori Ernst, Avi Caciularu, Ori Shapira, Ramakanth Pasunuru, Mohit Bansal, Jacob Goldberger, Ido Dagan

Localizing Factual Inconsistencies in Attributable Text Generation (2026.tacl-1)

Challenge:	Existing methods focused on clustering sentences to indicate information saliency and avoid redundancy.
Approach:	They propose to group together sub-sentential propositions to generate a representative sentence for each cluster via text fusion.
Outcome:	The proposed method improves over the previous state-of-the-art method in the DUC 2004 and TAC 2011 datasets, both in automatic ROUGE scores and human preference.

Copied to clipboard

Arie Cattan, Paul Roit, Shiyue Zhang, David Wan, Roee Aharoni, Idan Szpektor, Mohit Bansal, Ido Dagan

Long Context Question Answering via Supervised Contrastive Learning (2022.naacl-main)

Challenge:	Existing methods for detecting hallucinations in model-generated texts fail to pinpoint errors.
Approach:	They propose a formalism for localizing factual inconsistencies in attributable text generation . they propose to decompose the generated text into simple question-answer pairs .
Outcome:	The proposed method achieves substantial inter-annotator agreement while achieving a substantial consistency score.

Copied to clipboard

Avi Caciularu, Ido Dagan, Jacob Goldberger, Arman Cohan

Semantic Text Processing

Challenge:	Long-context question answering tasks often require identifying evidence spans (e.g., sentences) prior work showed that jointly training models to perform evidence extraction and question answering is important for achieving high performance.
Approach:	They propose a method for equipping long-context QA models with an additional sequence-level objective for better identification of the supporting evidence.
Outcome:	The proposed method exhibits consistent improvements on three different strong long-context transformer models, across two challenging question answering benchmarks – HotpotQA and QAsper.

QADiscourse - Discourse Relations as QA Pairs: Representation, Crowdsourcing and Baselines (2020.emnlp-main)

Copied to clipboard

Valentina Pyatkin, Ayal Klein, Reut Tsarfaty, Ido Dagan

Representation Learning

Challenge:	Discourse relations describe how two propositions relate to one another . annotating discourse relations requires expert annotators .
Approach:	They propose a new representation of discourse relations as question-and-answer pairs that crowd-sources wide-coverage data annotated with discourse relations.
Outcome:	The proposed representation of discourse relations as QA pairs allows crowd-sourcing wide-coverage datasets annotated with discourse relations.

Semantics as a Foreign Language (D18-1)

Copied to clipboard

Gabriel Stanovsky, Ido Dagan

Structured Data in NLP

Challenge:	(2017): Syntactic grammars capture propositions, but graph-based representations aim to capture a wider notion of propositions.
Approach:	They propose a neural sequence-to-sequence framework which can recover syntactic linearizations by a sequence-based approach.
Outcome:	The proposed framework performs almost on-par with previous state-of-the-art approaches while requiring less parallel training annotations.

Evaluating Multiple System Summary Lengths: A Case Study (D18-1)

Copied to clipboard

Ori Shapira, David Gabay, Hadar Ronen, Judit Bar-Ilan, Yael Amsterdamer, Ani Nenkova, Ido Dagan

Multi-Review Fusion-in-Context (2024.findings-naacl)

Challenge:	Practical summarization systems are expected to produce summaries of varying lengths, per user needs.
Approach:	They propose to use ROUGE metric to evaluate system summaries of multiple lengths.
Outcome:	The evaluation protocol in question is competitive, the authors show . they found that the evaluation protocol is competitive with existing benchmarks.

Copied to clipboard

Aviv Slobodkin, Ori Shapira, Ran Levy, Ido Dagan

Selective Annotation via Data Allocation: These Data Should Be Triaged to Experts for Annotation Rather Than the Model (2024.findings-emnlp)

Challenge:	Current methods for generating text are opaque and difficult to control and interpret due to their opaque nature.
Approach:	They propose a modular approach with separate components for each step . they formalize Fusion-in-Context as a standalone task, whose input consists of source texts with highlighted spans of targeted content.
Outcome:	The proposed approach is based on a curated dataset of 1000 instances in the reviews domain and a novel evaluation framework for assessing the faithfulness and coverage of highlights.

Copied to clipboard

Chen Huang, Yang Deng, Wenqiang Lei, Jiancheng Lv, Ido Dagan

Responsible & Trustworthy NLP

Challenge:	Existing methods to obtain high-quality annotations under limited budgets focus on selecting informative data for expert annotations while the rest of the data is assigned to model annotation.
Approach:	They propose a semi-automatic annotation framework that uses error-aware triage and bi-weighting mechanisms to obtain high-quality annotations under limited budget.
Outcome:	The proposed framework outperforms baselines in the data annotation problem under limited budgets.

Interactive Query-Assisted Summarization via Deep Reinforcement Learning (2022.naacl-main)

Copied to clipboard

Ori Shapira, Ramakanth Pasunuru, Mohit Bansal, Ido Dagan, Yael Amsterdamer

Beyond Pairwise: Global Zero-shot Temporal Graph Generation (2025.emnlp-main)

Challenge:	Existing systems that can perform interactive summarization cannot ingest the full document set or operate at sufficient speed for interactivity.
Approach:	They propose two deep reinforcement learning models for interactive summarization task . they use interactive session state and history to refrain from redundancy .
Outcome:	The proposed model improves informativeness while preserving positive user experience.

Copied to clipboard

Alon Eirew, Kfir Bar, Ido Dagan

Low-Resource NLP

Challenge:	Temporal relation extraction (TRE) is a fundamental task in natural language processing (NLP) that involves identifying the temporal relationships between events in a document.
Approach:	They propose a method that generates a document’s complete temporal graph in a single step, followed by temporal constraint optimization to refine predictions and enforce temporal consistency across relations.
Outcome:	The proposed method outperforms existing zero-shot approaches and offers a competitive alternative to supervised TRE models.

CHAMP: Efficient Annotation and Consolidation of Cluster Hierarchies (2023.emnlp-demo)

Copied to clipboard

Arie Cattan, Tom Hope, Doug Downey, Roy Bar-Haim, Lilach Eden, Yoav Kantor, Ido Dagan

Step-by-Step: Separating Planning from Realization in Neural Data-to-Text Generation (N19-1)

Challenge:	Various annotation tasks require a complex hierarchical structure over nodes, where each node is a cluster of items.
Approach:	They propose an open source tool that incrementally constructs clusters and hierarchy simultaneously over any type of text.
Outcome:	The proposed approach significantly reduces annotation time and guarantees transitivity at the cluster and hierarchy levels.

Copied to clipboard

Amit Moryossef, Yoav Goldberg, Ido Dagan

The Power of Summary-Source Alignments (2024.findings-acl)

Challenge:	Modern neural generation systems conflate these two steps into a single end-to-end differentiable system.
Approach:	They propose to split the generation process into a symbolic text-planning stage that is faithful to the input, followed by a neural generation stage that focuses only on realization.
Outcome:	The proposed method improves reliability and adequacy while maintaining fluent output.

Copied to clipboard

Ori Ernst, Ori Shapira, Aviv Slobodkin, Sharon Adar, Mohit Bansal, Jacob Goldberger, Ran Levy, Ido Dagan

CDˆ2CR: Co-reference resolution across documents and domains (2021.eacl-main)

Challenge:	Multi-document summarization (MDS) is a challenging task, often decomposed to subtasks of salience and redundancy detection, followed by text generation.
Approach:	They propose to extend the summary-source alignment framework by applying it at the more fine-grained proposition span level and annotating alignment manually in a multi-document setup.
Outcome:	The proposed framework can yield several datasets for at least six different tasks.

Copied to clipboard

James Ravenscroft, Amanda Clare, Arie Cattan, Ido Dagan, Maria Liakata

SetExpander: End-to-end Term Set Expansion Based on Multi-Context Term Embeddings (C18-2)

Challenge:	Current models for cross-document co-reference resolution assume that all documents are of the same type or fall under the same theme.
Approach:	They propose a task for cross-document cross-domain co-reference resolution (CD2CR) task aims to identify links between entities across heterogeneous document types.
Outcome:	The proposed task outperforms current state-of-the-art models on CD2CR in cross-domain, cross-document setting.

Copied to clipboard

Jonathan Mamou, Oren Pereg, Moshe Wasserblat, Ido Dagan, Yoav Goldberg, Alon Eirew, Yael Green, Shira Guskin, Peter Izsak, Daniel Korat

Semantic Text Processing

Challenge:	SetExpander is a corpus-based system for expanding a seed set of terms into a more complete set of words belonging to the same semantic class.
Approach:	They propose to use a corpus-based system for expanding a seed set of terms into a more complete set of words that belong to the same semantic class.
Outcome:	The proposed system can expand a seed set of terms, validate it, re-expand the expanded set and store it, thus simplifying the extraction of domain-specific fine-grained semantic classes.

iFacetSum: Coreference-based Interactive Faceted Summarization for Multi-Document Exploration (2021.emnlp-demo)

Copied to clipboard

Eran Hirsch, Alon Eirew, Ori Shapira, Avi Caciularu, Arie Cattan, Ori Ernst, Ramakanth Pasunuru, Hadar Ronen, Mohit Bansal, Ido Dagan

Realistic Evaluation Principles for Cross-document Coreference Resolution (2021.starsem-1)

Challenge:	iFS provides a faceted navigation scheme that provides abstractive summaries for the user’s selections.
Approach:	They propose a web application that integrates interactive summarization and faceted search to provide a faceted navigation scheme that yields abstractive summaries for the user's selections.
Outcome:	The proposed system provides a comprehensive overview as well as particular details regard-ing subtopics of interest.

Copied to clipboard

Arie Cattan, Alon Eirew, Gabriel Stanovsky, Mandar Joshi, Ido Dagan

Efficient Data Generation for Source-grounded Information-seeking Dialogs: A Use Case for Meeting Transcripts (2024.findings-emnlp)

Challenge:	Using permissive evaluation protocols, cross-document coreference resolution models produce inflated results.
Approach:	They propose to decouple evaluation of mention detection from coreference linking . they argue that models should not exploit the synthetic topic structure of the standard ECB+ dataset .
Outcome:	The proposed evaluation principles yield lower results than previous lenient evaluation methods.

Copied to clipboard

Lotem Golany, Filippo Galgani, Maya Mamo, Nimrod Parasol, Omer Vandsburger, Nadav Bar, Ido Dagan

Dialogue Systems & Conversational Agents

Challenge:	Existing methods for automating data generation with Large Language Models (LLMs) are difficult, and we propose a semi-automatic approach to generate dialogs with attributions.
Approach:	They propose a semi-automatic approach to generate dialog queries and responses with Large Language Models followed by human verification and identification of attribution spans.
Outcome:	The proposed approach improves the quality of the response generation and attribution quality of MISeD datasets while reducing time and effort.

Attribute First, then Generate: Locally-attributable Grounded Text Generation (2024.acl-long)

Copied to clipboard

Aviv Slobodkin, Eran Hirsch, Arie Cattan, Tal Schuster, Ido Dagan

OpenAsp: A Benchmark for Multi-document Open Aspect-based Summarization (2023.emnlp-main)

Challenge:	Recent efforts to address hallucinations in Large Language Models have focused on attributed text generation, which supplements generated texts with citations of supporting sources for post-generation fact-checking and corrections.
Approach:	They propose a locally-attributable text generation approach prioritizing concise attributions by identifying relevant source segments and conditioning the generation process on them.
Outcome:	The proposed method yields more concise citations than baselines and significantly reduces time required for fact verification by human assessors.

Copied to clipboard

Shmuel Amar, Liat Schiff, Ori Ernst, Asi Shefer, Ori Shapira, Ido Dagan

Summarization

Challenge:	Existing models focus on a limited set of predefined aspects, resulting in a lack of realistic open aspect setting.
Approach:	They propose a benchmark for multi-document open aspect-based summarization using an annotation protocol.
Outcome:	The proposed benchmark satisfies the needs of users in real-world scenarios.

Paraphrasing vs Coreferring: Two Sides of the Same Coin (2020.findings-emnlp)

Copied to clipboard

Yehudit Meged, Avi Caciularu, Vered Shwartz, Ido Dagan