Search Results - "Schütze, Hinrich"

Position Information in Transformers: An Overview by Dufter, Philipp, Schmitt, Martin, Schütze, Hinrich

“…Transformers are arguably the main workhorse in recent natural language processing research. By definition, a Transformer is invariant with respect to…”
Get full text

Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLP by Schick, Timo, Udupa, Sahana, Schütze, Hinrich

“…⚠ This paper contains prompts and model outputs that are offensive in nature. When trained on large, unfiltered crawls from the Internet, language models pick…”
Get full text

AutoExtend: Combining Word Embeddings with Semantic Resources by Rothe, Sascha, Schütze, Hinrich

“…We present , a system that combines word embeddings with semantic resources by learning embeddings for non-word objects like synsets and entities and learning…”
Get full text

Bi-directional recurrent neural network with ranking loss for spoken language understanding by Ngoc Thang Vu, Gupta, Pankaj, Adel, Heike, Schutze, Hinrich

“…This paper presents our latest investigation of recurrent neural networks for the slot filling task of spoken language understanding. We implement a…”
Get full text

Explaining pretrained language models' understanding of linguistic structures using construction grammar by Weissweiler, Leonie, Hofmann, Valentin, Köksal, Abdullatif, Schütze, Hinrich

“…Construction Grammar (CxG) is a paradigm from cognitive linguistics emphasizing the connection between syntax and semantics. Rather than rules that operate on…”
Get full text

Statistical Models for Unsupervised, Semi-Supervised, and Supervised Transliteration Mining by Sajjad, Hassan, Schmid, Helmut, Fraser, Alexander, Schütze, Hinrich

“…We present a generative model that efficiently mines transliteration pairs in a consistent fashion in three different settings: unsupervised, semi-supervised,…”
Get full text

Exploring the relationship between intonation and the lexicon: Evidence for lexicalised storage of intonation by Schweitzer, Katrin, Walsh, Michael, Calhoun, Sasha, Schütze, Hinrich, Möbius, Bernd, Schweitzer, Antje, Dogil, Grzegorz

“…•Prosodic features are shown to depend on distributional properties at the word level.•Increasing frequency of word-accent pairs results in greater accent…”
Get full text

Measuring and Improving Consistency in Pretrained Language Models by Elazar, Yanai, Kassner, Nora, Ravfogel, Shauli, Ravichander, Abhilasha, Hovy, Eduard, Schütze, Hinrich, Goldberg, Yoav

“…of a model—that is, the invariance of its behavior under meaning-preserving alternations in its input—is a highly desirable property in natural language…”
Get full text

Placing language in an integrated understanding system: Next steps toward human-level performance in neural language models by McClelland, James L., Hill, Felix, Rudolph, Maja, Baldridge, Jason, Schütze, Hinrich

“…Language is crucial for human intelligence, but what exactly is its role? We take language to be a part of a system for understanding and communicating about…”
Get full text

Creating an online dictionary of abbreviations from MEDLINE by Chang, Jeffrey T, Schütze, Hinrich, Altman, Russ B

“…The growth of the biomedical literature presents special challenges for both human readers and automatic algorithms. One such challenge derives from the common…”
Get full text

ABCNN: Attention-Based Convolutional Neural Network for Modeling Sentence Pairs by Yin, Wenpeng, Schütze, Hinrich, Xiang, Bing, Zhou, Bowen

“…How to model a pair of sentences is a critical issue in many NLP tasks such as answer selection (AS), paraphrase identification (PI) and textual entailment…”
Get full text

Erratum: “ABCNN: Attention-Based Convolutional Neural Network for Modeling Sentence Pairs” by Yin, Wenpeng, Schütze, Hinrich, Xiang, Bing, Zhou, Bowen

“…In this erratum, we correct the lack of proper attribution of two quotations…”
Get full text

GAPSCORE: finding gene and protein names one word at a time by Chang, Jeffrey T., Schütze, Hinrich, Altman, Russ B.

“…Motivation: New high-throughput technologies have accelerated the accumulation of knowledge about genes and proteins. However, much knowledge is still stored…”
Get full text

Syllable frequency effects in a context-sensitive segment production model by Wade, Travis, Dogil, Grzegorz, Schütze, Hinrich, Walsh, Michael, Möbius, Bernd

“…In this study we describe a new model of how phonetic knowledge guides speech production. In the Context Sequence model, target acoustic patterns are…”
Get full text

A cooccurrence-based thesaurus and two applications to information retrieval by Schütze, Hinrich, Pedersen, Jan O.

“…This paper presents a new method for computing a thesaurus from a text corpus. Each word is represented as a vector in a multi-dimensional space that captures…”
Get full text

True Few-Shot Learning with Prompts—A Real-World Perspective by Schick, Timo, Schütze, Hinrich

“…Prompt-based approaches excel at few-shot learning. However, Perez et al. ( ) recently cast doubt on their performance as they had difficulty getting good…”
Get full text

Corpus-Level Fine-Grained Entity Typing by Yaghoobzadeh, Yadollah, Adel, Heike, Schuetze, Hinrich

“…Extracting information about entities remains an important research area. This paper addresses the problem of corpus-level entity typing, i.e., inferring from…”
Get full text

Type-aware Convolutional Neural Networks for Slot Filling by Adel, Heike, Schuetze, Hinrich

“…The slot filling task aims at extracting answers for queries about entities from text, such as "Who founded Apple". In this paper, we focus on the relation…”
Get full text

Attentive Convolution: Equipping CNNs with RNN-style Attention Mechanisms by Yin, Wenpeng, Schütze, Hinrich

“…In NLP, convolutional neural networks (CNNs) have benefited less than recurrent neural networks (RNNs) from attention mechanisms. We hypothesize that this is…”
Get full text

Joint Semantic Synthesis and Morphological Analysis of the Derived Word by Cotterell, Ryan, Schütze, Hinrich

“…Much like sentences are composed of words, words themselves are composed of smaller units. For example, the English word can be analyzed as + + . However, this…”
Get full text