C
Chris Alberti
Researcher at Google
Publications - 46
Citations - 5035
Chris Alberti is an academic researcher from Google. The author has contributed to research in topics: Question answering & Computer science. The author has an hindex of 21, co-authored 40 publications receiving 3053 citations. Previous affiliations of Chris Alberti include Georgia Institute of Technology.
Papers
More filters
Journal ArticleDOI
Coreference Resolution through a seq2seq Transition-Based System
TL;DR: The authors presented a text-to-text (seq2seq) paradigm to predict mentions and links jointly, which achieved state-of-the-art performance on the CoNLL-2012 datasets.
Posted Content
Corpora Generation for Grammatical Error Correction
TL;DR: The authors proposed two approaches for generating large parallel datasets for grammatical error correction using publicly available Wikipedia data, one method extracts source-target pairs from Wikipedia edit histories with minimal filtration heuristics, while the second method introduces noise into Wikipedia sentences via round-trip translation through bridge languages.
NeurIPS 2020 EfficientQA Competition: Systems, Analyses and Lessons Learned
Sewon Min,Jordan Boyd-Graber,Chris Alberti,Danqi Chen,Eunsol Choi,Michael Collins,Kelvin Guu,Hannaneh Hajishirzi,Kenton Lee,Jennimaria Palomaki,Colin Raffel,Adam Roberts,Tom Kwiatkowski,Patrick S. H. Lewis,Yuxiang Wu,Heinrich Küttler,Linqing Liu,Pasquale Minervini,Pontus Stenetorp,Sebastian Riedel,Sohee Yang,Minjoon Seo,Gautier Izacard,Fabio Petroni,Lucas Hosseini,Nicola De Cao,Edouard Grave,Ikuya Yamada,Sonse Shimaoka,Masatoshi Suzuki,Shumpei Miyawaki,Shun Sato,Ryo Takahashi,Jun Suzuki,Martin Fajcik,Martin Docekal,Karel Ondrej,Pavel Smrz,Hao Cheng,Yelong Shen,Xiaodong Liu,Pengcheng He,Weizhu Chen,Jianfeng Gao,Barlas Oguz,Xilun Chen,Vladimir Karpukhin,Stan Peshterliev,Dmytro Okhonko,Michael Sejr Schlichtkrull,Sonal Gupta,Yashar Mehdad,Wen-tau Yih +52 more
TL;DR: The EfficientQA competition as discussed by the authors focused on open-domain question answering (QA), where systems take natural language questions as input and return natural language answers, and the aim of the competition was to build systems that can predict correct answers while also satisfying strict on-disk memory budgets.
Posted Content
Data Weighted Training Strategies for Grammatical Error Correction
TL;DR: The authors derive example-level scores on large pretraining data based on a smaller, higher-quality dataset and use delta-log-perplexity, a type of example scoring, into a training schedule for grammatical error correction.
Patent
Methods and systems for identifying competitors using content items including content extensions
Abstract: Systems and methods for identifying competitors using content extensions in content items in content items associated with their content placement campaigns are described. A processor identifies one or more competing entities from auctions in which the first entity places a bid. The competing entities are associated with content items having a first type of content extension that received impressions in at least one identified auction. The processor computes an overlap rate based on a number of auctions in which both a content item having the first type of content extension of the identified competing entity and a content item of the first entity received impressions and a number of auctions in which a content item having the first type of content extension of the identified competing entity received an impression and the first entity competed. The processor ranks the competing entities based on the computed overlap rate.