We present EASE, a novel method for learning sentence embeddings via contrastive learning between sentences and their related entities.
We present a multilingual bag-of-entities model that effectively boosts the performance of zero-shot cross-lingual text classification by extending a multilingual pre-trained language model (e. g., M-BERT).
We train a multilingual language model with 24 languages with entity representations and show the model consistently outperforms word-based pretrained models in various cross-lingual transfer tasks.
Ranked #1 on Cross-Lingual Question Answering on XQuAD (Average F1 metric, using extra training data)
Most state-of-the-art open-domain question answering systems use a neural retrieval model to encode passages into continuous vectors and extract them from a knowledge source.
Ranked #2 on Open-Domain Question Answering on TQA
no code implementations • 1 Jan 2021 • 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 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 Schlichtkrull, Sonal Gupta, Yashar Mehdad, Wen-tau Yih
We review the EfficientQA competition from NeurIPS 2020.
In this paper, we propose new pretrained contextualized representations of words and entities based on the bidirectional transformer.
Ranked #1 on Question Answering on TACRED
This study proposes a Neural Attentive Bag-of-Entities model, which is a neural network model that performs text classification using entities in a knowledge base.
Ranked #2 on Text Classification on R8
We propose a global entity disambiguation (ED) model based on BERT.
Ranked #1 on Entity Disambiguation on WNED-WIKI
The embeddings of entities in a large knowledge base (e. g., Wikipedia) are highly beneficial for solving various natural language tasks that involve real world knowledge.
We propose human-in-the-loop adversarial generation, where human authors are guided to break models.
In this paper, we describe TextEnt, a neural network model that learns distributed representations of entities and documents directly from a knowledge base (KB).
Ranked #1 on Entity Typing on Freebase FIGER
In this chapter, we describe our question answering system, which was the winning system at the Human-Computer Question Answering (HCQA) Competition at the Thirty-first Annual Conference on Neural Information Processing Systems (NIPS).
We present Segment-level Neural CRF, which combines neural networks with a linear chain CRF for segment-level sequence modeling tasks such as named entity recognition (NER) and syntactic chunking.
Given a text in the KB, we train our proposed model to predict entities that are relevant to the text.
Ranked #2 on Entity Disambiguation on TAC2010
The KB graph model learns the relatedness of entities using the link structure of the KB, whereas the anchor context model aims to align vectors such that similar words and entities occur close to one another in the vector space by leveraging KB anchors and their context words.
Ranked #4 on Entity Disambiguation on TAC2010