Ido Dagan · page 2
Papers
- Integrating Deep Linguistic Features in Factuality Prediction over Unified Datasets (2017 · 62 citations)
Factuality prediction asks how strongly a source, usually the author, commits to a predicate being true, possible or false. - Attribute First, then Generate: Locally-attributable Grounded Text Generation (2024 · 48 citations)
Attributed generation tries to curb LLM hallucinations by attaching citations to outputs. However, existing systems usually cite whole documents or paragraphs, so checking a claim still means reading a lot of irrelevant text. The authors define a stricter task, Locally-attributable Grounded Text Generation. In it… - WEC: Deriving a Large-scale Cross-document Event Coreference dataset from Wikipedia (2021 · 47 citations)
Cross-document event coreference means grouping mentions from different texts that point to the same real-world event. - Paraphrasing vs Coreferring: Two Sides of the Same Coin (2020 · 47 citations)
Predicate paraphrase acquisition and cross-document event coreference resolution both deal with the same difficulty: different predicates can describe one event. - QANom: Question-Answer driven SRL for Nominalizations (2020 · 41 citations)
QANom extends QA-SRL from verbs to nouns derived from verbs: a noun like proof or increase is questioned with its verb's question templates («What has someone proved?», «Why did something increase?») and answered with spans of the sentence. - Semantic Inference at the Lexical-Syntactic Level for Textual Entailment Recognition (2007 · 39 citations)
The paper proposes a proof system for textual entailment that works directly on dependency trees. Entailment rules, manual or acquired from WordNet and from DIRT-style paraphrase data, rewrite the text tree step by step towards the hypothesis, and a cost function measures the remaining distance when no full proof is… - Realistic Evaluation Principles for Cross-document Coreference Resolution (2021 · 31 citations)
Cross-document (CD) coreference resolution links mentions of the same entity or event across separate texts. - BIUTEE: A Modular Open-Source System for Recognizing Textual Entailment (2012 · 31 citations)
BIUTEE tackles a practical barrier in Recognizing Textual Entailment (RTE): building a full inference system from scratch takes a lot of work, and the few public systems (EDITS, NutCracker) could use only narrow kinds of knowledge. - A Probabilistic Setting and Lexical Coocurrence Model for Textual Entailment (2005 · 23 citations)
Glickman and Dagan argue that textual entailment is often uncertain rather than all-or-nothing, so they treat it probabilistically. - Design Choices for Crowdsourcing Implicit Discourse Relations: Revealing the Biases Introduced by Task Design (2023 · 19 citations)
Crowdsourced annotations can be skewed by how the task is phrased, not only by who annotates or by the label scheme. - Multi-Level Alignments As An Extensible Representation Basis for Textual Entailment Algorithms (2015 · 17 citations)
Building Textual Entailment (TE) systems is expensive. Shared platforms already standardize preprocessing, annotation types and knowledge resources, but the algorithms themselves stay monolithic and hard to extend or port to new languages. The authors propose multi-level alignment as a common intermediate layer.… - Cross-document Event Coreference Search: Task, Dataset and Modeling (2022 · 15 citations)
Cross-document event coreference systems have usually been asked to link every coreferent mention within a fixed and fairly small document set. - Design Choices in Crowdsourcing Discourse Relation Annotations: The Effect of Worker Selection and Training (2022 · 11 citations)
Getting lay crowdworkers to label implicit discourse relations is difficult. The task depends on interpretation, and PDTB 3.0 distinguishes 36 sense types that novices cannot realistically master. This paper asks how recruiting and preparing workers affects label quality, measured as agreement between worker labels… - LAQuer: Localized Attribution Queries in Content-grounded Generation (2025 · 8 citations)
Content-grounded generators, such as RAG systems, often produce claims that their sources do not support, so users have to check them. - Localizing Factual Inconsistencies in Attributable Text Generation (2026 · 7 citations)
LLM outputs that should be grounded in a reference document, such as summaries, open-book answers or cited responses, still contain hallucinations. - Automatic Thesaurus Construction for Modern Hebrew (2018 · 2 citations)
The authors build corpus-based thesauri for Modern Hebrew, a morphologically rich language where taggers and parsers are weak.
This page in Markdown → https://md.research.elamur.ai/free/en/authors/ido-dagan/page/2/