Vera Demberg

Rollenwechsel-English: a large-scale semantic role corpus

2018

We present the Rollenwechsel-English (RW-eng) corpus, a large corpus of automatically-labelled semantic frames extracted from the ukWaC corpus and BNC using Propbank roles.RW-eng contains both full-phrase constituents for labelled roles as well as heads identified …

Neural Data-to-Text Generation with LM-based Text Augmentation

2021 · arXiv (Cornell University)

For many new application domains for data-to-text generation, the main obstacle in training neural models consists of a lack of training data. While usually large numbers of instances are available on the data side, often …

A practical perspective on connective generation

2021

In data-driven natural language generation, we typically know what relation should be expressed and need to select a connective to lexicalize it. In the current contribution, we analyse whether a sophisticated connective generation module is …

ChatGPT vs Human-authored Text: Insights into Controllable Text Summarization and Sentence Style Transfer

2023

Large-scale language models, like ChatGPT, have garnered significant media attention and stunned the public with their remarkable capacity for generating coherent text from short natural language prompts. In this paper, we aim to conduct a …

Implicit Discourse Relation Classification For Nigerian Pidgin

2024 · arXiv (Cornell University)

Despite attempts to make Large Language Models multi-lingual, many of the world's languages are still severely under-resourced. This widens the performance gap between NLP and AI applications aimed at well-financed, and those aimed at less-resourced …

RST-LoRA: A Discourse-Aware Low-Rank Adaptation for Long Document Abstractive Summarization

2024

For long document summarization, discourse structure is important to discern the key content of the text and the differences in importance level between sentences.Unfortunately, the integration of rhetorical structure theory (RST) into parameter-efficient fine-tuning strategies …

Human Speech Perception in Noise: Can Large Language Models Paraphrase to Improve It?

2024

Large Language Models (LLMs) can generate text by transferring style attributes like formality resulting in formal or informal text.However, instructing LLMs to generate text that when spoken, is more intelligible in an acoustically difficult environment, …