Amir Zeldes · page 2
Papers
- GUM-SAGE: A Novel Dataset and Approach for Graded Entity Salience Prediction (2025 · 7 citations)
Salience is defined operationally: an entity is as salient as the number of one-sentence summaries of the document (out of five) that mention it, giving a 0–5 score for every named and unnamed entity of GUM's 213 documents in 12 genres. - Are UD Treebanks Getting More Consistent? A Report Card for English UD (2023 · 7 citations)
The paper checks whether the two largest English UD treebanks, EWT and GUM, which have different origins and conversion histories, are converging, and whether it makes sense to train joint models on them. - GUMSum: Multi-Genre Data and Evaluation for English Abstractive Summarization (2023 · 7 citations)
Neural summarizers write fluent text. They still invent facts, do poorly outside news, and are trained on "found" datasets like XSum and CNN/DM, where many reference texts are not real summaries. Liu and Zeldes address this with GUMSum, a small, carefully built evaluation set. It adds a one-sentence summary to each… - A Neural Approach to Discourse Relation Signal Detection (2020 · 7 citations)
Discourse relations such as CONDITION, CONCESSION or CAUSE are often marked by connectives. Corpus-wide frequency or PMI counts give each word type a single score. They cannot tell whether a given occurrence of "and" or "to" actually carries a relation, and they cannot flag words that point the wrong way. Zeldes and… - Anatomy of OntoGUM—Adapting GUM to the OntoNotes Scheme to Evaluate Robustness of SOTA Coreference Algorithms (2021 · 6 citations)
GUM annotates more coreference than OntoNotes, so the authors convert it automatically to the OntoNotes scheme, using GUM's gold UD trees, in a fixed order of steps: remove bridging and cataphora (an expletive or cataphoric pronoun becomes a singleton), contract verbal mentions to the verb, merge appositions into one… - A Characterwise Windowed Approach to Hebrew Morphological Segmentation (2018 · 6 citations)
Zeldes treats Hebrew segmentation as pure splitting: for every character of a space-delimited token he decides whether a boundary follows, with no morphological analysis. - The DISRPT 2025 Shared Task on Elementary Discourse Unit Segmentation, Connective Detection, and Relation Classification (2025 · 5 citations)
DISRPT 2025 is the fourth edition of a shared task on discourse analysis that spans several annotation frameworks. - Subjectivity in the Annotation of Bridging Anaphora (2025 · 4 citations)
The paper studies where human judgment enters bridging annotation, and why agreement is low. It is a pilot on the test set of the GUM corpus: 26 documents, about 26k tokens, in 16 genres, each annotated by two people. The authors separate three decisions: recognising the bridging anaphor, choosing its antecedent, and… - Universal Anaphora: The First Three Years (2024 · 4 citations)
Coreference work in NLP has long revolved around OntoNotes. That corpus centres on identity coreference in a limited set of genres and leaves out singletons, expletives and many harder phenomena. Universal Anaphora (UA) began in 2020 and is modelled on Universal Dependencies. It aims to coordinate research on… - GUMBridge: A Corpus for Varieties of Bridging Anaphora (2026 · 3 citations)
GUMBridge is a new English corpus of referential bridging anaphora. It is built on the GUM corpus and covers 24 genres, written and spoken. Bridging is defined with information status: an entity is accessible on first mention because of a relation to an earlier, non-identical entity. Each bridging instance gets one… - Sentence-level Feedback Generation for English Language Learners: Does Data Augmentation Help? (2023 · 3 citations)
The paper addresses feedback comment generation (GenChal 2022: FCG). Given a learner's English sentence and the span containing a preposition error, the system must write a short explanation of what is wrong and how to fix it, not just correct it. The authors fine-tune T5-Large, marking the error span with delimiter… - Unifying the Scope of Bridging Anaphora Types in English: Bridging Annotations in ARRAU and GUM (2024 · 2 citations)
The two largest English bridging resources define bridging differently. GUM/GENTLE (16 + 8 genres, 1.9k bridging links) treat it as information status: a first mention that is interpretable only through a non-identical earlier entity, with one antecedent. ARRAU (news part 229k tokens, 3.7k links) treats it as a set… - Not Worth Mentioning? A Pilot Study on Salient Proposition Annotation (2026 · 1 citation)
Extractive summarization assumes that some propositions in a text matter more than others. Yet there has been little effort to define proposition salience in a measurable, graded way for real data. The authors carry over a summary-based method from Salient Entity Extraction (SEE): a unit's salience is the number of… - Building UD Cairo for Old English in the Classroom (2025 · 1 citation)
The paper builds an Old English treebank of the 20 UD Cairo sentences, which illustrate the constructions of the world's languages, as a classroom exercise in historical linguistics. - Overview of AMALGUM – Large Silver Quality Annotations across English Genres (2021 · 1 citation)
Discourse-oriented research faces a gap. Huge web corpora carry only shallow annotation and have unclear makeup, while richly annotated corpora tend to be small. AMALGUM (A Machine-Annotated Lookalike of GUM) is meant to sit between the two. The authors used the gold GUM corpus (130K tokens, eight genres) as a… - DM Doppelgangers: Implicit Connectives as eRST Signals (2026)
RST-style hierarchical discourse annotation and PDTB-style shallow annotation have mostly been studied separately. - LLMBridge: An LLM Pipeline for End-to-end Referential Bridging Resolution in English (2026)
Bridging is when a new entity is understood through its link to an earlier one, as when "the door" is read as belonging to a house just mentioned. - What's in a Bridge?: A Descriptive, Multi-Genre Analysis of the GUMBridge Corpus for Varieties of Bridging Anaphora (2026)
The paper is a descriptive analysis of the GUMBridge corpus: 5.3k referential bridging instances in 273k tokens across 16 genres (the train, dev and test partitions). - Unpacking Ambiguity: The Interaction of Polysemous Discourse Markers and Non-DM Signals (2025)
Using GUM's eRST layer (16 genres, over 250K tokens, discourse markers plus seven types of non-marker signals: graphical, lexical, morphological, numerical, reference, semantic, syntactic), the paper measures how ambiguous each discourse marker is — the entropy of the relations it signals — and asks whether ambiguous…
This page in Markdown → https://md.research.elamur.ai/free/en/authors/amir-zeldes/page/2/