1.1k citations · 1.1k across the 19 of their papers we have counts for
21 papers
Learning When to Retrieve, What to Rewrite, and How to Respond in Conversational QA
Nirmal Roy, Leonardo F. R. Ribeiro, Rexhina Blloshmi +1
Augmenting Large Language Models (LLMs) with information retrieval capabilities (i.e., Retrieval-Augmented Generation (RAG)) has proven beneficial for knowledge-intensive tasks. Ho…
Speechworthy Instruction-tuned Language Models
Hyundong Cho, Nicolaas Jedema, Leonardo F. R. Ribeiro +5
Current instruction-tuned language models are exclusively trained with textual preference data and thus are often not aligned with the unique requirements of other modalities, such…
FANTAstic SEquences and Where to Find Them: Faithful and Efficient API Call Generation through State-tracked Constrained Decoding and Reranking
Zhuoer Wang, Leonardo F. R. Ribeiro, Alexandros Papangelis +6
API call generation is the cornerstone of large language models' tool-using ability that provides access to the larger world. However, existing supervised and in-context learning a…
Measuring Retrieval Complexity in Question Answering Systems
Matteo Gabburo, Nicolaas Paul Jedema, Siddhant Garg +2
In this paper, we investigate which questions are challenging for retrieval-based Question Answering (QA). We (i) propose retrieval complexity (RC), a novel metric conditioned on t…
On the Role of Summary Content Units in Text Summarization Evaluation
Marcel Nawrath, Agnieszka Nowak, Tristan Ratz +13
At the heart of the Pyramid evaluation method for text summarization lie human written summary content units (SCUs). These SCUs are concise sentences that decompose a summary into…
Generating Summaries with Controllable Readability Levels
Leonardo F. R. Ribeiro, Mohit Bansal, Markus Dreyer
Readability refers to how easily a reader can understand a written text. Several factors affect the readability level, such as the complexity of the text, its subject matter, and t…
Learning to Reason over Scene Graphs: A Case Study of Finetuning GPT-2 into a Robot Language Model for Grounded Task Planning
Georgia Chalvatzaki, Ali Younes, Daljeet Nandha +3
Long-horizon task planning is essential for the development of intelligent assistive and service robots. In this work, we investigate the applicability of a smaller class of large…
Incorporating Relevance Feedback for Information-Seeking Retrieval using Few-Shot Document Re-Ranking
Tim Baumgärtner, Leonardo F. R. Ribeiro, Nils Reimers +1
Pairing a lexical retriever with a neural re-ranking model has set state-of-the-art performance on large-scale information retrieval datasets. This pipeline covers scenarios like q…
UKP-SQuARE v2: Explainability and Adversarial Attacks for Trustworthy QA
Rachneet Sachdeva, Haritz Puerto, Tim Baumgärtner +6
Question Answering (QA) systems are increasingly deployed in applications where they support real-world decisions. However, state-of-the-art models rely on deep neural networks, wh…
GEMv2: Multilingual NLG Benchmarking in a Single Line of Code
Sebastian Gehrmann, Abhik Bhattacharjee, Abinaya Mahendiran +74
Evaluation in machine learning is usually informed by past choices, for example which datasets or metrics to use. This standardization enables the comparison on equal footing using…
FactGraph: Evaluating Factuality in Summarization with Semantic Graph Representations
Leonardo F. R. Ribeiro, Mengwen Liu, Iryna Gurevych +2
Despite recent improvements in abstractive summarization, most current approaches generate summaries that are not factually consistent with the source document, severely restrictin…
UKP-SQUARE: An Online Platform for Question Answering Research
Tim Baumgärtner, Kexin Wang, Rachneet Sachdeva +10
Recent advances in NLP and information retrieval have given rise to a diverse set of question answering tasks that are of different formats (e.g., extractive, abstractive), require…
Smelting Gold and Silver for Improved Multilingual AMR-to-Text Generation
Leonardo F. R. Ribeiro, Jonas Pfeiffer, Yue Zhang +1
Recent work on multilingual AMR-to-text generation has exclusively focused on data augmentation strategies that utilize silver AMR. However, this assumes a high quality of generate…
Structural Adapters in Pretrained Language Models for AMR-to-text Generation
Leonardo F. R. Ribeiro, Yue Zhang, Iryna Gurevych
Pretrained language models (PLM) have recently advanced graph-to-text generation, where the input graph is linearized into a sequence and fed into the PLM to obtain its representat…
Investigating Pretrained Language Models for Graph-to-Text Generation
Leonardo F. R. Ribeiro, Martin Schmitt, Hinrich Schütze +1
Graph-to-text generation aims to generate fluent texts from graph-based data. In this paper, we investigate two recently proposed pretrained language models (PLMs) and analyze the…
Modeling Graph Structure via Relative Position for Text Generation from Knowledge Graphs
Martin Schmitt, Leonardo F. R. Ribeiro, Philipp Dufter +2
We present Graformer, a novel Transformer-based encoder-decoder architecture for graph-to-text generation. With our novel graph self-attention, the encoding of a node relies on all…
Common Sense or World Knowledge? Investigating Adapter-Based Knowledge Injection into Pretrained Transformers
Anne Lauscher, Olga Majewska, Leonardo F. R. Ribeiro +3
Following the major success of neural language models (LMs) such as BERT or GPT-2 on a variety of language understanding tasks, recent work focused on injecting (structured) knowle…
Metaphoric Paraphrase Generation
Kevin Stowe, Leonardo Ribeiro, Iryna Gurevych
This work describes the task of metaphoric paraphrase generation, in which we are given a literal sentence and are charged with generating a metaphoric paraphrase. We propose two d…
Modeling Global and Local Node Contexts for Text Generation from Knowledge Graphs
Leonardo F. R. Ribeiro, Yue Zhang, Claire Gardent +1
Recent graph-to-text models generate text from graph-based data using either global or local aggregation to learn node representations. Global node encoding allows explicit communi…
Enhancing AMR-to-Text Generation with Dual Graph Representations
Leonardo F. R. Ribeiro, Claire Gardent, Iryna Gurevych
Generating text from graph-based data, such as Abstract Meaning Representation (AMR), is a challenging task due to the inherent difficulty in how to properly encode the structure o…
struc2vec: Learning Node Representations from Structural Identity
Leonardo F. R. Ribeiro, Pedro H. P. Savarese, Daniel R. Figueiredo
Structural identity is a concept of symmetry in which network nodes are identified according to the network structure and their relationship to other nodes. Structural identity has…