Hinrich Schütze

is this you? claim profile

0 followers

Chair of Computational Linguistics Director, Center for Information and Language Processing

Superbizarre Is Not Superb: Improving BERT's Interpretations of Complex Words with Derivational Morphology

How does the input segmentation of pretrained language models (PLMs) aff...
01/02/2021 ∙ by Valentin Hofmann, et al. ∙ 0 ∙ share

read it
A Closer Look at Few-Shot Crosslingual Transfer: Variance, Benchmarks and Baselines

We present a focused study of few-shot crosslingual transfer, a recently...
12/31/2020 ∙ by Mengjie Zhao, et al. ∙ 9 ∙ share

read it
Few-Shot Text Generation with Pattern-Exploiting Training

Providing pretrained language models with simple task descriptions or pr...
12/22/2020 ∙ by Timo Schick, et al. ∙ 4 ∙ share

read it
Subword Sampling for Low Resource Word Alignment

Annotation projection is an important area in NLP that can greatly contr...
12/21/2020 ∙ by Ehsaneddin Asgari, et al. ∙ 0 ∙ share

read it
Automatically Identifying Words That Can Serve as Labels for Few-Shot Text Classification

A recent approach for few-shot text classification is to convert textual...
10/26/2020 ∙ by Timo Schick, et al. ∙ 9 ∙ share

read it
Dynamic Contextualized Word Embeddings

Static word embeddings that represent words by a single vector cannot ca...
10/23/2020 ∙ by Valentin Hofmann, et al. ∙ 0 ∙ share

read it
Transformers Are Better Than Humans at Identifying Generated Text

Fake information spread via the internet and social media influences pub...
09/28/2020 ∙ by Antonis Maronikolakis, et al. ∙ 0 ∙ share

read it
It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learners

When scaled to hundreds of billions of parameters, pretrained language m...
09/15/2020 ∙ by Timo Schick, et al. ∙ 5 ∙ share

read it
Investigating Pretrained Language Models for Graph-to-Text Generation

Graph-to-text generation, a subtask of data-to-text generation, aims to ...
07/16/2020 ∙ by Leonardo F. R. Ribeiro, et al. ∙ 0 ∙ share

read it
Automatic Domain Adaptation Outperforms Manual Domain Adaptation for Predicting Financial Outcomes

In this paper, we automatically create sentiment dictionaries for predic...
06/25/2020 ∙ by Marina Sedinkina, et al. ∙ 0 ∙ share

read it
Neural Topic Modeling with Continual Lifelong Learning

Lifelong learning has recently attracted attention in building machine l...
06/19/2020 ∙ by Pankaj Gupta, et al. ∙ 0 ∙ share

read it
Explainable and Discourse Topic-aware Neural Language Understanding

Marrying topic models and language models exposes language understanding...
06/18/2020 ∙ by Yatin Chaudhary, et al. ∙ 0 ∙ share

read it
Pre-trained Language Models as Symbolic Reasoners over Knowledge?

How can pre-trained language models (PLMs) learn factual knowledge from ...
06/18/2020 ∙ by Nora Kassner, et al. ∙ 0 ∙ share

read it
Modeling Graph Structure via Relative Position for Better Text Generation from Knowledge Graphs

We present a novel encoder-decoder architecture for graph-to-text genera...
06/16/2020 ∙ by Martin Schmitt, et al. ∙ 0 ∙ share

read it
Unsupervised Embedding-based Detection of Lexical Semantic Changes

This paper describes EmbLexChange, a system introduced by the "Life-Lang...
05/16/2020 ∙ by Ehsaneddin Asgari, et al. ∙ 0 ∙ share

read it
BERT-kNN: Adding a kNN Search Component to Pretrained Language Models for Better QA

Khandelwal et al. (2020) show that a k-nearest-neighbor (kNN) component ...
05/02/2020 ∙ by Nora Kassner, et al. ∙ 0 ∙ share

read it
Generating Derivational Morphology with BERT

Can BERT generate derivationally complex words? We present the first stu...
05/02/2020 ∙ by Valentin Hofmann, et al. ∙ 0 ∙ share

read it
Identifying Necessary Elements for BERT's Multilinguality

It has been shown that multilingual BERT (mBERT) yields high quality mul...
05/01/2020 ∙ by Philipp Dufter, et al. ∙ 0 ∙ share

read it
Masking as an Efficient Alternative to Finetuning for Pretrained Language Models

We present an efficient method of utilizing pretrained language models, ...
04/26/2020 ∙ by Mengjie Zhao, et al. ∙ 0 ∙ share

read it
Quantifying the Contextualization of Word Representations with Semantic Class Probing

Pretrained language models have achieved a new state of the art on many ...
04/25/2020 ∙ by Mengjie Zhao, et al. ∙ 0 ∙ share

read it
SimAlign: High Quality Word Alignments without Parallel Training Data using Static and Contextualized Embeddings

Word alignments are useful for tasks like statistical and neural machine...
04/18/2020 ∙ by Masoud Jalili Sabet, et al. ∙ 0 ∙ share

read it
Inexpensive Domain Adaptation of Pretrained Language Models: A Case Study on Biomedical Named Entity Recognition

Domain adaptation of Pretrained Language Models (PTLMs) is typically ach...
04/07/2020 ∙ by Nina Poerner, et al. ∙ 0 ∙ share

read it
Exploiting Cloze Questions for Few-Shot Text Classification and Natural Language Inference

Some NLP tasks can be solved in a fully unsupervised fashion by providin...
01/21/2020 ∙ by Timo Schick, et al. ∙ 0 ∙ share

read it
Multipurpose Intelligent Process Automation via Conversational Assistant

Intelligent Process Automation (IPA) is an emerging technology with a pr...
01/07/2020 ∙ by Alena Moiseeva, et al. ∙ 9 ∙ share

read it
Extending Machine Language Models toward Human-Level Language Understanding

Language is central to human intelligence. We review recent breakthrough...
12/12/2019 ∙ by James L. McClelland, et al. ∙ 34 ∙ share

read it
Morphological Segmentation Inside-Out

Morphological segmentation has traditionally been modeled with non-hiera...
11/12/2019 ∙ by Ryan Cotterell, et al. ∙ 0 ∙ share

read it
Sentence Meta-Embeddings for Unsupervised Semantic Textual Similarity

We address the task of unsupervised Semantic Textual Similarity (STS) by...
11/09/2019 ∙ by Nina Poerner, et al. ∙ 0 ∙ share

read it
BERT is Not a Knowledge Base (Yet): Factual Knowledge vs. Name-Based Reasoning in Unsupervised QA

The BERT language model (LM) (Devlin et al., 2019) is surprisingly good ...
11/09/2019 ∙ by Nina Poerner, et al. ∙ 0 ∙ share

read it
Negated LAMA: Birds cannot fly

Pretrained language models have achieved remarkable improvements in a br...
11/08/2019 ∙ by Nora Kassner, et al. ∙ 0 ∙ share

read it
BERTRAM: Improved Word Embeddings Have Big Impact on Contextualized Model Performance

Pretraining deep contextualized representations using an unsupervised la...
10/16/2019 ∙ by Timo Schick, et al. ∙ 0 ∙ share

read it
Linguistically Informed Relation Extraction and Neural Architectures for Nested Named Entity Recognition in BioNLP-OST 2019

Named Entity Recognition (NER) and Relation Extraction (RE) are essentia...
10/08/2019 ∙ by Usama Yaseen, et al. ∙ 0 ∙ share

read it
Type-aware Convolutional Neural Networks for Slot Filling

The slot filling task aims at extracting answers for queries about entit...
10/01/2019 ∙ by Heike Adel, et al. ∙ 0 ∙ share

read it
BioNLP-OST 2019 RDoC Tasks: Multi-grain Neural Relevance Ranking Using Topics and Attention Based Query-Document-Sentence Interactions

This paper presents our system details and results of participation in t...
10/01/2019 ∙ by Yatin Chaudhary, et al. ∙ 0 ∙ share

read it
Multi-view and Multi-source Transfers in Neural Topic Modeling with Pretrained Topic and Word Embeddings

Though word embeddings and topics are complementary representations, sev...
09/14/2019 ∙ by Pankaj Gupta, et al. ∙ 0 ∙ share

read it
Multi-view and Multi-source Transfers in Neural Topic Modeling

Though word embeddings and topics are complementary representations, sev...
09/14/2019 ∙ by Pankaj Gupta, et al. ∙ 0 ∙ share

read it
Neural Architectures for Fine-Grained Propaganda Detection in News

This paper describes our system (MIC-CIS) details and results of partici...
09/13/2019 ∙ by Pankaj Gupta, et al. ∙ 0 ∙ share

read it
Morphological Word Embeddings

Linguistic similarity is multi-faceted. For instance, two words may be s...
07/04/2019 ∙ by Ryan Cotterell, et al. ∙ 0 ∙ share

read it
Probing for Semantic Classes: Diagnosing the Meaning Content of Word Embeddings

Word embeddings typically represent different meanings of a word in a si...
06/09/2019 ∙ by Yadollah Yaghoobzadeh, et al. ∙ 0 ∙ share

read it
Generating Multi-Sentence Abstractive Summaries of Interleaved Texts

In multi-participant postings, as in online chat conversations, several ...
06/05/2019 ∙ by Sanjeev Kumar Karn, et al. ∙ 0 ∙ share

read it
SherLIiC: A Typed Event-Focused Lexical Inference Benchmark for Evaluating Natural Language Inference

We present SherLIiC, a testbed for lexical inference in context (LIiC), ...
06/04/2019 ∙ by Martin Schmitt, et al. ∙ 0 ∙ share

read it
Robust Argument Unit Recognition and Classification

Argument mining is generally performed on the sentence-level -- it is as...
04/22/2019 ∙ by Dietrich Trautmann, et al. ∙ 0 ∙ share

read it
Unsupervised Text Generation from Structured Data

This work presents a joint solution to two challenging tasks: text gener...
04/20/2019 ∙ by Martin Schmitt, et al. ∙ 0 ∙ share

read it
Analytical Methods for Interpretable Ultradense Word Embeddings

Word embeddings are useful for a wide variety of tasks, but they lack in...
04/18/2019 ∙ by Philipp Dufter, et al. ∙ 0 ∙ share

read it
Rare Words: A Major Problem for Contextualized Embeddings And How to Fix it by Attentive Mimicking

Pretraining deep neural network architectures with a language modeling o...
04/14/2019 ∙ by Timo Schick, et al. ∙ 0 ∙ share

read it
Attentive Mimicking: Better Word Embeddings by Attending to Informative Contexts

Learning high-quality embeddings for rare words is a hard problem becaus...
04/02/2019 ∙ by Timo Schick, et al. ∙ 0 ∙ share

read it
Learning Semantic Representations for Novel Words: Leveraging Both Form and Context

Word embeddings are a key component of high-performing natural language ...
11/09/2018 ∙ by Timo Schick, et al. ∙ 0 ∙ share

read it
CIS at TAC Cold Start 2015: Neural Networks and Coreference Resolution for Slot Filling

This paper describes the CIS slot filling system for the TAC Cold Start ...
11/06/2018 ∙ by Heike Adel, et al. ∙ 0 ∙ share

read it
A Stronger Baseline for Multilingual Word Embeddings

Levy, Søgaard and Goldberg's (2017) S-ID (sentence ID) method applies wo...
11/01/2018 ∙ by Philipp Dufter, et al. ∙ 0 ∙ share

read it
Aligning Very Small Parallel Corpora Using Cross-Lingual Word Embeddings and a Monogamy Objective

Count-based word alignment methods, such as the IBM models or fast-align...
10/31/2018 ∙ by Nina Poerner, et al. ∙ 0 ∙ share

read it
Multi-Multi-View Learning: Multilingual and Multi-Representation Entity Typing

Knowledge bases (KBs) are paramount in NLP. We employ multiview learning...
10/24/2018 ∙ by Yadollah Yaghoobzadeh, et al. ∙ 0 ∙ share

read it

Hinrich Schütze

Featured Co-authors