Ido Dagan

5 paper cards in Mova's library · 2007–2020

Ido Dagan wrote 5 of the papers Mova reads, in 2007–2020, most of them on Semantic role labeling, Part-of-speech tagging; often with Luke Zettlemoyer, Ayal Klein, Daniela Stepanov.

The profile is the library's match of the name; two people with one name are not always told apart.

Papers

Controlled Crowdsourcing for High-Quality QA-SRL Annotation (2020)
The paper shows that the crowdsourced QA-SRL data of 2018 has low coverage, with an estimated recall in the low 70s, and proposes a controlled protocol to fix it.
QANom: Question-Answer driven SRL for Nominalizations (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.
Crowdsourcing Question-Answer Meaning Representations (2018)
A QAMR represents a sentence's predicate-argument structure as a set of free-form wh-question / answer-span pairs about all its content words, not only verbs («How old is Pierre Vinken? – 61 years old», «What will he join the board as? – nonexecutive director»).
Automatic Thesaurus Construction for Modern Hebrew (2018)
The authors build corpus-based thesauri for Modern Hebrew, a morphologically rich language where taggers and parsers are weak.
Semantic Inference at the Lexical-Syntactic Level for Textual Entailment Recognition (2007)
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…