Hinrich Schütze

The Operation Sequence Model—Combining N-Gram-Based and Phrase-Based Statistical Machine Translation

2015 · Computational Linguistics

In this article, we present a novel machine translation model, the Operation Sequence Model (OSM), which combines the benefits of phrase-based and N-gram-based statistical machine translation (SMT) and remedies their drawbacks. The model represents the …

Joint Semantic Synthesis and Morphological Analysis of the Derived Word

2018 · Transactions of the Association for Computational Linguistics

Much like sentences are composed of words, words themselves are composed of smaller units. For example, the English word questionably can be analyzed as question+ able+ ly. However, this structural decomposition of the word does …

End-Task Oriented Textual Entailment via Deep Explorations of Inter-Sentence Interactions

2018 · arXiv (Cornell University)

This work deals with SciTail, a natural entailment challenge derived from a multi-choice question answering problem. The premises and hypotheses in SciTail were generated with no awareness of each other, and did not specifically aim …

Comparing Convolutional Neural Networks to Traditional Models for Slot Filling

2016 · arXiv (Cornell University)

We address relation classification in the context of slot filling, the task of finding and evaluating fillers like "Steve Jobs" for the slot X in "X founded Apple". We propose a convolutional neural network which …

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

2021

When scaled to hundreds of billions of parameters, pretrained language models such as GPT-3 (Brown et al., 2020) achieve remarkable few-shot performance. However, enormous amounts of compute are required for training and applying such big …

Data Centric Domain Adaptation for Historical
\nText with OCR Errors

2021 · Open access LMU (Ludwid Maxmilian's Universitat Munchen)

We propose new methods for in-domain and cross-domain Named Entity Recognition (NER) on historical data for Dutch and French. For the cross-domain case, we address domain shift by integrating unsupervised in-domain data via contextualized string …

BMIKE-53: Investigating Cross-Lingual Knowledge Editing with In-Context Learning

2024 · arXiv (Cornell University)

This paper introduces BMIKE-53, a comprehensive benchmark for cross-lingual in-context knowledge editing (IKE) across 53 languages, unifying three knowledge editing (KE) datasets: zsRE, CounterFact, and WikiFactDiff. Cross-lingual KE, which requires knowledge edited in one language …

Construction-Based Reduction of Translationese for Low-Resource Languages: A Pilot Study on Bavarian

2025

Peiqin Lin, Marion Thaler, Daniela Goschala, Amir Hossein Kargaran, Yihong Liu, André F. T. Martins, Hinrich Schütze. Proceedings of the 7th Workshop on Research in Computational Linguistic Typology and Multilingual NLP. 2025.

On the Entity-Level Alignment in Crosslingual Consistency

2025 · arXiv (Cornell University)

Multilingual large language models (LLMs) are expected to recall factual knowledge consistently across languages. However, the factors that give rise to such crosslingual consistency -- and its frequent failure -- remain poorly understood. In this …

ABCNN: Attention-Based Convolutional Neural Network for Modeling Sentence Pairs

2016 · Transactions of the Association for Computational Linguistics

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 (TE). Most prior work (i) deals with one individual …

Multichannel Variable-Size Convolution for Sentence Classification

2015

We propose MVCNN, a convolution neural network (CNN) architecture for sentence classification. It (i) combines diverse versions of pretrained word embeddings and (ii) extracts features of multigranular phrases with variable-size convolution filters. We also show …

Convolutional Neural Network for Paraphrase Identification

2015

We present a new deep learning architecture Bi-CNN-MI for paraphrase identification (PI). Based on the insight that PI requires comparing two sentences on multiple levels of granularity, we learn multigranular sentence representations using convolutional neural …

Learning Word Meta-Embeddings

2016

Word embeddings -distributed representations of words -in deep learning are beneficial for many tasks in NLP. However, different embedding sets vary greatly in quality and characteristics of the captured information. Instead of relying on a …

Table Filling Multi-Task Recurrent Neural Network for Joint Entity and Relation Extraction

2016 · International Conference on Computational Linguistics

This paper proposes a novel context-aware joint entity and word-level relation extraction approach through semantic composition of words, introducing a Table Filling Multi-Task Recurrent Neural Network (TF-MTRNN) model that reduces the entity recognition and relation …

Comparative Study of CNN and RNN for Natural Language Processing

2017 · arXiv (Cornell University)

Deep neural networks (DNN) have revolutionized the field of natural language processing (NLP). Convolutional neural network (CNN) and recurrent neural network (RNN), the two main types of DNN architectures, are widely explored to handle various …

Neural Relation Extraction within and across Sentence Boundaries

2019

Past work in relation extraction mostly focuses on binary relation between entity pairs within single sentence. Recently, the NLP community has gained interest in relation extraction in entity pairs spanning multiple sentences. In this paper, …

Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLP

2021 · Transactions of the Association for Computational Linguistics

Abstract ⚠ This paper contains prompts and model outputs that are offensive in nature. When trained on large, unfiltered crawls from the Internet, language models pick up and reproduce all kinds of undesirable biases that …

Measuring and Improving Consistency in Pretrained Language Models

2021 · Transactions of the Association for Computational Linguistics

Abstract Consistency 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 processing. In this paper we study the question: Are Pretrained Language …