--- title: "Dan Roth — papers, page 2 — Elamur Research" description: "Dan Roth, Oracle: 64 papers on Elamur Research (2002–2026), h-index 84 — affiliations, topics, co-authors and who cites them in our library." canonical: "https://research.elamur.ai/free/en/authors/dan-roth/page/2/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/dan-roth/page/2/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / [Dan Roth](https://md.research.elamur.ai/free/en/authors/dan-roth/) / page 2 # Dan Roth · page 2 64 papers in our library · 2002–2026 · page 2 of 3 [The profile, affiliations and co-authors →](https://md.research.elamur.ai/free/en/authors/dan-roth/) ## Papers The most cited first (OpenAlex and our library). [← prev](https://md.research.elamur.ai/free/en/authors/dan-roth/) [1](https://md.research.elamur.ai/free/en/authors/dan-roth/) **2** [3](https://md.research.elamur.ai/free/en/authors/dan-roth/page/3/) [next →](https://md.research.elamur.ai/free/en/authors/dan-roth/page/3/) 26. **[Zero-shot Event Extraction via Transfer Learning: Challenges and Insights](https://md.research.elamur.ai/free/en/papers/lyu-2021-zero-shot-event-extraction-transfer/)** *(2021 · 128 citations)* Event extraction (EE) usually depends on costly supervised annotation tied to a fixed event ontology. This paper tests whether EE can be done with no event training data at all. The authors reuse off-the-shelf pretrained models built for other tasks. Trigger detection is posed as Textual Entailment or Yes/No QA… 27. **[Grammar Error Correction in Morphologically Rich Languages: The Case of Russian](https://md.research.elamur.ai/free/en/papers/rozovskaya-2019-grammar-error-correction-morphologically-rich/)** *(2019 · 126 citations)* Research on grammar error correction (GEC) has focused almost entirely on English, where systems rely on tens of millions of words of annotated learner text. 28. **[Solving Hard Coreference Problems](https://md.research.elamur.ai/free/en/papers/peng-2015-solving-hard-coreference-problems/)** *(2015 · 118 citations)* Coreference systems still struggle with pronouns, especially in Winograd-style sentences. In these, gender and number agreement offer no help, and picking the right antecedent depends on world knowledge. Peng, Khashabi and Roth propose Predicate Schemas, a knowledge representation organized around predicates: 29. **[A Statistical Analysis of Summarization Evaluation Metrics Using Resampling Methods](https://md.research.elamur.ai/free/en/papers/deutsch-2021-statistical-analysis-summarization-evaluation-metrics/)** *(2021 · 117 citations)* Automatic summarization metrics are usually judged by how well their scores correlate with human quality ratings. 30. **[TwoWingOS: A Two-Wing Optimization Strategy for Evidential Claim Verification](https://md.research.elamur.ai/free/en/papers/yin-2018-twowingos-two-wing-optimization-strategy/)** *(2018 · 114 citations)* The paper tackles evidential claim verification: given a claim and a large text collection, a system must find the sentences that support or refute the claim and then decide whether the claim is supported, refuted, or lacks enough information. 31. **[ExpertQA: Expert-Curated Questions and Attributed Answers](https://md.research.elamur.ai/free/en/papers/malaviya-2024-expertqa-expert-curated-questions-attributed/)** *(2024 · 113 citations)* LLMs are increasingly used by specialists, but it is unclear how factual their answers are and how well their citations hold up in specific professional fields, especially high-risk ones like medicine and law. 32. **[“Ask Not What Textual Entailment Can Do for You...”](https://md.research.elamur.ai/free/en/papers/sammons-2010-ask-not-what-textual-entailment/)** *(2010 · 108 citations)* The paper argues that Recognizing Textual Entailment (RTE) should become a shared testbed for the component tasks of NLP, such as NER, coreference and parsing. 33. **[The Illinois-Columbia System in the CoNLL-2014 Shared Task](https://md.research.elamur.ai/free/en/papers/rozovskaya-2014-illinois-columbia-system-conll-2014/)** *(2014 · 94 citations)* This paper presents the Illinois-Columbia entry to the CoNLL-2014 shared task on correcting grammatical mistakes in essays by non-native English writers. 34. **[CogCompTime: A Tool for Understanding Time in Natural Language](https://md.research.elamur.ai/free/en/papers/ning-2018-cogcomptime-tool-understanding-time-natural/)** *(2018 · 93 citations)* CogCompTime is a publicly available system for extracting temporal information from raw English text. It covers two tasks. The first is finding explicit time expressions (Timexes) and converting them to a standard format. The second is recovering the implicit ordering of events through temporal relations (TempRels). 35. **[A Constrained Latent Variable Model for Coreference Resolution](https://md.research.elamur.ai/free/en/papers/chang-2013-constrained-latent-variable-model-coreference/)** *(2013 · 81 citations)* Coreference resolution clusters noun-phrase mentions according to which real-world entity each one denotes. 36. **[Modeling Semantic Relations Expressed by Prepositions](https://md.research.elamur.ai/free/en/papers/srikumar-2013-modeling-semantic-relations-expressed-prepositions/)** *(2013 · 76 citations)* Prepositions are highly ambiguous: one preposition can signal many meanings, and many prepositions can signal the same meaning. 37. **[A Joint Framework for Coreference Resolution and Mention Head Detection](https://md.research.elamur.ai/free/en/papers/peng-2015-joint-framework-coreference-resolution-mention/)** *(2015 · 75 citations)* Coreference systems lose much of their accuracy when they must find mentions in raw text rather than receive gold-annotated ones. 38. **["I'd rather just go to bed": Understanding Indirect Answers](https://md.research.elamur.ai/free/en/papers/louis-2020-i-d-rather-just-go/)** *(2020 · 72 citations)* The paper builds Circa, 34,268 pairs of a polar question and an indirect answer (no yes/no words), in ten everyday scenarios, written and labelled by crowd workers. 39. **[Learning-based Multi-Sieve Co-reference Resolution with Knowledge](https://md.research.elamur.ai/free/en/papers/ratinov-2012-learning-based-multi-sieve-co/)** *(2012 · 72 citations)* The paper tackles co-reference resolution: deciding which mentions in a text point to the same entity. Many errors come from missing world knowledge, such as not knowing that "Kursk" is a submarine and can therefore be called a "vessel." The authors link mentions to Wikipedia pages using an existing context-sensitive… 40. **[A Peek into Token Bias: Large Language Models Are Not Yet Genuine Reasoners](https://md.research.elamur.ai/free/en/papers/jiang-2024-peek-into-token-bias-large/)** *(2024 · 64 citations)* The paper asks whether large language models actually reason logically or mostly react to familiar surface tokens that appear in well-known problem statements. 41. **[Inference Protocols for Coreference Resolution](https://md.research.elamur.ai/free/en/papers/chang-2011-inference-protocols-coreference-resolution/)** *(2011 · 50 citations)* This paper presents Illinois-Coref, the system the University of Illinois submitted to the closed-track competition of CoNLL-2011, a shared task on resolving coreference in OntoNotes-4.0. 42. **[CoCoMIC: Code Completion by Jointly Modeling In-file and Cross-file Context](https://md.research.elamur.ai/free/en/papers/ding-2024-cocomic-code-completion-jointly-modeling/)** *(2024 · 45 citations)* Most code language models complete a file using only the code above the cursor. They ignore definitions elsewhere in the same repository, which matter a great deal in modular projects. Without that information, models invent class methods or call functions with wrong arguments, especially in private, still-developing… 43. **[QANom: Question-Answer driven SRL for Nominalizations](https://md.research.elamur.ai/free/en/papers/klein-2020-qanom-question-answer-driven-srl/)** *(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. 44. **[DeAL: Decoding-time Alignment for Large Language Models](https://md.research.elamur.ai/free/en/papers/huang-2025-deal-decoding-time-alignment-large/)** *(2025 · 36 citations)* The paper argues that alignment learned during training (e.g., RLHF) has two weaknesses. It locks models into a developer's fixed, supposedly universal preferences, and it can be bypassed, for example through jailbreaks. The authors propose DeAL, which moves alignment to inference time. Decoding is treated as an… 45. **[PropSegmEnt: A Large-Scale Corpus for Proposition-Level Segmentation and Entailment Recognition](https://md.research.elamur.ai/free/en/papers/chen-2023-propsegment-large-scale-corpus-proposition/)** *(2023 · 31 citations)* Standard NLI datasets give one entailment label to a whole sentence or paragraph. Most real sentences pack several distinct units of meaning, and each can be true or unsupported independently. A single label therefore hides partial entailment, where only some of a hypothesis is backed by the premise. PropSegmEnt… 46. **[Pairwise Representation Learning for Event Coreference](https://md.research.elamur.ai/free/en/papers/yu-2022-pairwise-representation-learning-event-coreference/)** *(2022 · 31 citations)* Event coreference resolution decides whether two event mentions describe the same real-world event. Earlier systems usually encoded each mention on its own and then classified the pair. As a result, a mention's vector never reflected its counterpart's context, which is a serious gap when the mentions come from… 47. **[Revisiting the Evaluation for Cross Document Event Coreference](https://md.research.elamur.ai/free/en/papers/upadhyay-2016-revisiting-evaluation-cross-document-event/)** *(2016 · 30 citations)* Cross document event coreference (CDEC) asks whether event mentions in different documents describe the same real-world event. 48. **[Identifying Semitic Roots: Machine Learning with Linguistic Constraints](https://md.research.elamur.ai/free/en/papers/daya-2008-identifying-semitic-roots-machine-learning/)** *(2008 · 25 citations)* Semitic words are built from a root (usually three consonants) and a pattern, and the root is hard to recover from unpointed text because of weak paradigms, missing vowels and attached prefixes. 49. **[Improving Generalization in Coreference Resolution via Adversarial Training](https://md.research.elamur.ai/free/en/papers/subramanian-2019-improving-generalization-coreference-resolution-adversarial/)** *(2019 · 23 citations)* Neural coreference resolvers trained on CoNLL-2012 may lean on memorized entity names rather than truly generalizing. 50. **[Learning Hebrew Roots: Machine Learning with Linguistic Constraints](https://md.research.elamur.ai/free/en/papers/daya-2004-learning-hebrew-roots-machine-learning/)** *(2004 · 23 citations)* The root of a Hebrew word (usually three consonants) is hard to find, because vowels are unwritten, particles attach without spaces, and weak roots change their shape. [← prev](https://md.research.elamur.ai/free/en/authors/dan-roth/) [1](https://md.research.elamur.ai/free/en/authors/dan-roth/) **2** [3](https://md.research.elamur.ai/free/en/authors/dan-roth/page/3/) [next →](https://md.research.elamur.ai/free/en/authors/dan-roth/page/3/)