Search Results for author: Jochen L. Leidner

Found 8 papers, 1 papers with code

Control in Hybrid Chatbots

no code implementations20 Nov 2023 Thomas Rüdel, Jochen L. Leidner

Customer data typically is held in database systems, which can be seen as rule-based knowledge base, whereas businesses increasingly want to benefit from the capabilities of large, pre-trained language models.

Chatbot Hallucination

Data-to-Value: An Evaluation-First Methodology for Natural Language Projects

no code implementations19 Jan 2022 Jochen L. Leidner

Big data, i. e. collecting, storing and processing of data at scale, has recently been possible due to the arrival of clusters of commodity computers powered by application-level distributed parallel operating systems like HDFS/Hadoop/Spark, and such infrastructures have revolutionized data mining at scale.

Detecting ESG topics using domain-specific language models and data augmentation approaches

no code implementations16 Oct 2020 Tim Nugent, Nicole Stelea, Jochen L. Leidner

Despite recent advances in deep learning-based language modelling, many natural language processing (NLP) tasks in the financial domain remain challenging due to the paucity of appropriately labelled data.

Data Augmentation Language Modelling

Topic Grouper: An Agglomerative Clustering Approach to Topic Modeling

1 code implementation13 Apr 2019 Daniel Pfeifer, Jochen L. Leidner

In this context, the fact that each word belongs to exactly one topic is not a major limitation; in some scenarios this can even be a genuine advantage, e. g.~a related shopping basket analysis may aid in optimizing groupings of articles in sales catalogs.

Clustering

attr2vec: Jointly Learning Word and Contextual Attribute Embeddings with Factorization Machines

no code implementations NAACL 2018 Fabio Petroni, Vassilis Plachouras, Timothy Nugent, Jochen L. Leidner

Our experimental results on a text classification task demonstrate that using attr2vec to jointly learn embeddings for words and Part-of-Speech (POS) tags improves results compared to learning the embeddings independently.

Attribute Dependency Parsing +6

A Comparison of Two Paraphrase Models for Taxonomy Augmentation

no code implementations NAACL 2018 Vassilis Plachouras, Fabio Petroni, Timothy Nugent, Jochen L. Leidner

Our results show that paraphrasing is a viable method to enrich a taxonomy with more terms, and that Moses consistently outperforms the sequence-to-sequence neural model.

Document Classification Machine Translation +3

Ethical by Design: Ethics Best Practices for Natural Language Processing

no code implementations WS 2017 Jochen L. Leidner, Vassilis Plachouras

While a number of previous works exist that discuss ethical issues, in particular around big data and machine learning, to the authors{'} knowledge this is the first account of NLP and ethics from the perspective of a principled process.

Ethics

Cannot find the paper you are looking for? You can Submit a new open access paper.