AI Paper Atlas

Research map / Large language models / Retrieval and knowledge

On Resolving Ambiguous Anaphoric Expressions in Imperative Discourse

Vasanth Sarathy, Matthias Scheutz

AAAI 2019 · Large language models › Retrieval and knowledge · approach: Explanatory and multiple-choice QA benchmarks

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
combine plausibility, normative and speaker-intent evidence with Dempster's rule instead of plausibility aloneASP + DS resolver · Pass it to mebelief in correct object: m(knife) 0.4, m(tomato) 0.3, m(Theta) 0.3 -> [1.0, 1.0]Improved
add normative and intent evidence for ambiguous 'put it down'ASP + DS resolver · Put it downmass on Theta: m(Theta) = 0.75Improved
change task context from washing dishes to cookingASP + DS resolver · Pass it to meresolved object: knife : [1.0, 1.0] vs tomato : [1.0, 1.0]Mixed
add normative microtheorySpeaker intent only · Pass it to me, cookingmass on single object: 0.5 -> 1.0Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy