Apple sponsored the annual conference of North American Chapter of the Association for Computational Linguistics (NAACL). The conference took place virtually from June 6 to 11.
Conference Accepted Papers
Combined Resolution of Ellipses and Anaphora in Dialogues
Andy Tseng, Jiarui Lu, Dhivya Piraviperumal, Joel Moniz, Shruti Bhargava, Lin Li, Hong Yu
Noise-robust Named Entity Understanding for Virtual Assistants
Atish Kothari, Deepak Muralidharan, Jason Williams, Joel Moniz, Justine Kao, Lin Li, Sida Gao, Stephen Pulman, Vivek Kaul, Xiao Yang
On the Transferability of Minimal Prediction Preserving Inputs in Question Answering
Shayne Longpre, Yi Lu, Chris DuBois
Open Domain Question Answering Goes Conversational via Question Rewriting
Raviteja Anantha, Svitlana Vakulenko, Michael Tu, Shayne Longpre, Stephen Pulman, Srinivas (Vasu) Chappidi
Affinity Events
Apple sponsored a social at Black in AI which took place on June 6, a social which took place QUEER in AI on June 6 and 7, and a social at LatinX in AI which took place on June 7 and 10.
Learn more about Apple’s company-wide efforts in inclusion and diversity
Related readings and updates.
Can Open Domain Question Answering Models Answer Visual Knowledge Questions?
The task of Outside Knowledge Visual Question Answering (OKVQA) requires an automatic system to answer natural language questions about pictures and images using external knowledge. We observe that many visual questions, which contain deictic referential phrases referring to entities in the image, can be rewritten as "non-grounded" questions and can be answered by existing text-based question answering systems. This allows for the reuse of…
See paper detailsMKQA: A Linguistically Diverse Benchmark for Multilingual Open Domain Question Answering
Progress in cross-lingual modeling depends on challenging, realistic, and diverse evaluation sets. We introduce Multilingual Knowledge Questions and Answers (MKQA), an open-domain question answering evaluation set comprising 10k question-answer pairs aligned across 26 typologically diverse languages (260k question-answer pairs in total). The goal of this dataset is to provide a challenging benchmark for question answering quality across a wide…
See paper details
Discover opportunities in Machine Learning.
Our research in machine learning breaks new ground every day.