activity
20172022
most citedBPEmb: Tokenization-free Pre-trained Subword Embeddings in 275 Languages

129 citations · 137 across the 7 of their papers we have counts for

collaborators
Showing cs.CLShow all

10 papers · 1 filter

cs.CL2022

Cross-stitching Text and Knowledge Graph Encoders for Distantly Supervised Relation Extraction

Qin Dai, Benjamin Heinzerling, Kentaro Inui

Bi-encoder architectures for distantly-supervised relation extraction are designed to make use of the complementary information found in text and knowledge graphs (KG). However, cu…

cs.CL20211 cited

Learning to Learn to be Right for the Right Reasons

Pride Kavumba, Benjamin Heinzerling, Ana Brassard +1

Improving model generalization on held-out data is one of the core objectives in commonsense reasoning. Recent work has shown that models trained on the dataset with superficial cu…

cs.CL2020

Language Models as Knowledge Bases: On Entity Representations, Storage Capacity, and Paraphrased Queries

Benjamin Heinzerling, Kentaro Inui

Pretrained language models have been suggested as a possible alternative or complement to structured knowledge bases. However, this emerging LM-as-KB paradigm has so far only been…

cs.CL20195 cited

When Choosing Plausible Alternatives, Clever Hans can be Clever

Pride Kavumba, Naoya Inoue, Benjamin Heinzerling +3

Pretrained language models, such as BERT and RoBERTa, have shown large improvements in the commonsense reasoning benchmark COPA. However, recent work found that many improvements i…

cs.CL2019

Riposte! A Large Corpus of Counter-Arguments

Paul Reisert, Benjamin Heinzerling, Naoya Inoue +2

Constructive feedback is an effective method for improving critical thinking skills. Counter-arguments (CAs), one form of constructive feedback, have been proven to be useful for c…

cs.CL20192 cited

On the Importance of Subword Information for Morphological Tasks in Truly Low-Resource Languages

Yi Zhu, Benjamin Heinzerling, Ivan Vulić +3

Recent work has validated the importance of subword information for word representation learning. Since subwords increase parameter sharing ability in neural models, their value sh…