[Mova](https://md.mova.elamur.ai/free/en/) · [this page in HTML](https://mova.elamur.ai/free/en/docs/papers/authors/dan-roth/) [home](https://md.mova.elamur.ai/free/en/) / [docs](https://md.mova.elamur.ai/free/en/docs/) / [papers](https://md.mova.elamur.ai/free/en/docs/papers/) / [authors](https://md.mova.elamur.ai/free/en/docs/papers/authors/) / Dan Roth # Dan Roth 10 paper cards in Mova's library · 2004–2020 Dan Roth wrote 10 of the papers Mova reads, in 2004–2020, most of them on [Coreference resolution](https://md.mova.elamur.ai/free/en/docs/papers/topics/coreference-resolution/), [Semantic role labeling](https://md.mova.elamur.ai/free/en/docs/papers/topics/semantic-role-labeling/); often with [Subhro Roy](https://md.mova.elamur.ai/free/en/docs/papers/authors/subhro-roy/), [Ezra Daya](https://md.mova.elamur.ai/free/en/docs/papers/authors/ezra-daya/), [Shuly Wintner](https://md.mova.elamur.ai/free/en/docs/papers/authors/shuly-wintner/). [OpenAlex](https://openalex.org/A5023802054) · [ORCID](https://orcid.org/0009-0002-1447-5173) · [**h-index 85**](https://openalex.org/authors/A5023802054) · [31311 citations](https://openalex.org/authors/A5023802054) · [731 works](https://openalex.org/works?filter=author.id:A5023802054) — openalex, 2026-10-18 The profile is the library's match of the name; two people with one name are not always told apart. Elsewhere: [Google Scholar](https://scholar.google.com/citations?view_op=search_authors&mauthors=Dan+Roth) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Dan+Roth) · [dblp](https://dblp.org/search?q=Dan+Roth) · [ACL Anthology](https://aclanthology.org/search/?q=Dan+Roth) · [ORCID](https://orcid.org/orcid-search/search?searchQuery=Dan+Roth) Topics: [Coreference resolution](https://md.mova.elamur.ai/free/en/docs/papers/topics/coreference-resolution/) 1 · [Semantic role labeling](https://md.mova.elamur.ai/free/en/docs/papers/topics/semantic-role-labeling/) 1 ## Ideas Mova took (1) From the ideas ledger: an idea tried, kept or queued, or measured with no gain, and what it gave. - **kept** — Keep events in non-real modes out of «what happened» answers: negated frames (neg), conditional ones (cond) and the unrealised complements proposed in white-2016-universal-decompositional-semantics-universal-dependencies I1 do not answer «What did the lion… *([TORQUE: A Reading Comprehension Dataset of Temporal…](https://md.mova.elamur.ai/free/en/docs/papers/ning-2020-torque-reading-comprehension-dataset-temporal/) · an «if» clause is irrealis for the student (PRAG_OFF=cond-irrealis): 7702/2200→7704/2206 (35db4e3f7))* ## Papers 1. **[TORQUE: A Reading Comprehension Dataset of Temporal Ordering Questions](https://md.mova.elamur.ai/free/en/docs/papers/ning-2020-torque-reading-comprehension-dataset-temporal/)** *(2020)* `1 idea kept` TORQUE asks temporal relations as reading-comprehension questions instead of labelling event pairs with Allen-style relations. 2. **["I'd rather just go to bed": Understanding Indirect Answers](https://md.mova.elamur.ai/free/en/docs/papers/louis-2020-i-d-rather-just-go/)** *(2020)* 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. 3. **[QANom: Question-Answer driven SRL for Nominalizations](https://md.mova.elamur.ai/free/en/docs/papers/klein-2020-qanom-question-answer-driven-srl/)** *(2020)* 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. 4. **[Looking Beyond the Surface: A Challenge Set for Reading Comprehension over Multiple Sentences](https://md.mova.elamur.ai/free/en/docs/papers/khashabi-2018-looking-beyond-surface-challenge-set/)** *(2018)* MultiRC has about 6,000 verified multi-sentence questions (9,872 collected) on 871 paragraphs from seven domains, fiction (Gutenberg, MCTest children's stories, movie plots) being the largest. 5. **[Mapping to Declarative Knowledge for Word Problem Solving](https://md.mova.elamur.ai/free/en/docs/papers/roy-2018-mapping-declarative-knowledge-word-problem/)** *(2018)* Instead of learning each arithmetic operation directly from text, this solver first picks a mathematical concept for every operation in the expression tree and then a specific declarative rule under that concept, which fixes the operation. 6. **[A Distributional and Orthographic Aggregation Model for English Derivational Morphology](https://md.mova.elamur.ai/free/en/docs/papers/deutsch-2018-distributional-orthographic-aggregation-model-english/)** *(2018)* The task is derived word generation: given a root word and a transformation (for example "someone who runs" from "run" by AGENT), produce the derived word ("runner"). 7. **[Unit Dependency Graph and its Application to Arithmetic Word Problem Solving](https://md.mova.elamur.ai/free/en/docs/papers/roy-2017-unit-dependency-graph-arithmetic/)** *(2017)* `measured` The paper adds explicit reasoning about units of measure to an arithmetic word-problem solver. It introduces the Unit Dependency Graph (UDG): one node per quantity plus one for the question, where a node can be marked as a rate ("40 miles per hour", or implicitly "each student has 3 books") with a numerator and a… 8. **[Solving General Arithmetic Word Problems](https://md.mova.elamur.ai/free/en/docs/papers/roy-2015-solving-general-arithmetic-word-problems/)** *(2015)* `measured` The paper solves multi-step arithmetic word problems without predefined equation templates by representing the answer as an expression tree in which each number from the text is used at most once. 9. **[Identifying Semitic Roots: Machine Learning with Linguistic Constraints](https://md.mova.elamur.ai/free/en/docs/papers/cl-2008-daya-identifying-semitic-roots-machine-learning/)** *(2008)* 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. 10. **[Learning Hebrew Roots: Machine Learning with Linguistic Constraints](https://md.mova.elamur.ai/free/en/docs/papers/aclbulk-2004-daya-learning-hebrew-roots-machine-learning/)** *(2004)* 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. ## Co-authors (23) - [Subhro Roy](https://md.mova.elamur.ai/free/en/docs/papers/authors/subhro-roy/) ×3 - [Ezra Daya](https://md.mova.elamur.ai/free/en/docs/papers/authors/ezra-daya/) ×2 - [Shuly Wintner](https://md.mova.elamur.ai/free/en/docs/papers/authors/shuly-wintner/) ×2 - [Annie Louis](https://md.mova.elamur.ai/free/en/docs/papers/authors/annie-louis/) - [Ayal Klein](https://md.mova.elamur.ai/free/en/docs/papers/authors/ayal-klein/) - Daniel Deutsch - [Daniel Khashabi](https://md.mova.elamur.ai/free/en/docs/papers/authors/daniel-khashabi/) - [Daniela Stepanov](https://md.mova.elamur.ai/free/en/docs/papers/authors/daniela-stepanov/) - Filip Radlinski - Hangfeng He - Hao Wu - [Ido Dagan](https://md.mova.elamur.ai/free/en/docs/papers/authors/ido-dagan/) - John Hewitt - [Jonathan Mamou](https://md.mova.elamur.ai/free/en/docs/papers/authors/jonathan-mamou/) - [Luke Zettlemoyer](https://md.mova.elamur.ai/free/en/docs/papers/authors/luke-zettlemoyer/) - [Matt Gardner](https://md.mova.elamur.ai/free/en/docs/papers/authors/matt-gardner/) - Michael Roth - [Nanyun Peng](https://md.mova.elamur.ai/free/en/docs/papers/authors/nanyun-peng/) - [Qiang Ning](https://md.mova.elamur.ai/free/en/docs/papers/authors/qiang-ning/) - Rujun Han - Shyam Upadhyay - Snigdha Chaturvedi - [Valentina Pyatkin](https://md.mova.elamur.ai/free/en/docs/papers/authors/valentina-pyatkin/) - [← previous Dan Klein](https://md.mova.elamur.ai/free/en/docs/papers/authors/dan-klein/) - [next → Dan Turner](https://md.mova.elamur.ai/free/en/docs/papers/authors/dan-turner/) - [↑ back to Authors](https://md.mova.elamur.ai/free/en/docs/papers/authors/)