activity
20152022
most citedStudying the Wikipedia Hyperlink Graph for Relatedness and Disambiguation

19 citations · 27 across the 7 of their papers we have counts for

collaborators

12 papers

cs.CL2022

Noisy Channel for Automatic Text Simplification

Oscar M Cumbicus-Pineda, Iker Gutiérrez-Fandiño, Itziar Gonzalez-Dios +1

In this paper we present a simple re-ranking method for Automatic Sentence Simplification based on the noisy channel scheme. Instead of directly computing the best simplification g…

cs.CL20222 cited

Documenting Geographically and Contextually Diverse Data Sources: The BigScience Catalogue of Language Data and Resources

Angelina McMillan-Major, Zaid Alyafeai, Stella Biderman +15

In recent years, large-scale data collection efforts have prioritized the amount of data collected in order to improve the modeling capabilities of large language models. This prio…

cs.AI20214 cited

Inferring spatial relations from textual descriptions of images

Aitzol Elu, Gorka Azkune, Oier Lopez de Lacalle +3

Generating an image from its textual description requires both a certain level of language understanding and common sense knowledge about the spatial relations of the physical enti…

cs.CL2020

Improving Conversational Question Answering Systems after Deployment using Feedback-Weighted Learning

Jon Ander Campos, Kyunghyun Cho, Arantxa Otegi +3

The interaction of conversational systems with users poses an exciting opportunity for improving them after deployment, but little evidence has been provided of its feasibility. In…

cs.AI2020

Spot The Bot: A Robust and Efficient Framework for the Evaluation of Conversational Dialogue Systems

Jan Deriu, Don Tuggener, Pius von Däniken +6

The lack of time-efficient and reliable evaluation methods hamper the development of conversational dialogue systems (chatbots). Evaluations requiring humans to converse with chatb…

cs.CL2020

DoQA -- Accessing Domain-Specific FAQs via Conversational QA

Jon Ander Campos, Arantxa Otegi, Aitor Soroa +3

The goal of this work is to build conversational Question Answering (QA) interfaces for the large body of domain-specific information available in FAQ sites. We present DoQA, a dat…