Search Results for author:
Found 20 papers, 2 papers with code
Learning to Generate Examples for Semantic Processing Tasks
Experiments in low resource settings show that augmenting the training material with the proposed strategy systematically improves the results on text classification and natural language inference tasks by up to 10% accuracy, outperforming existing DA approaches.
Generating Diverse Q&A Benchmarks for RAG Evaluation with DataMorgana
We introduce here DataMorgana, a tool for generating highly customizable and diverse synthetic Q&A benchmarks tailored to RAG applications.
Enhancing Low-Resource LLMs Classification with PEFT and Synthetic Data
Large Language Models (LLMs) operating in 0-shot or few-shot settings achieve competitive results in Text Classification tasks.
The Power of Noise: Redefining Retrieval for RAG Systems
Retrieval-Augmented Generation (RAG) has recently emerged as a method to extend beyond the pre-trained knowledge of Large Language Models by augmenting the original prompt with relevant passages or documents retrieved by an Information Retrieval (IR) system.
Evaluation Metrics of Language Generation Models for Synthetic Traffic Generation Tasks
Experiments on three tasks, i. e., Shopping Utterance Generation, Product Question Generation and Query Auto Completion, demonstrate that our metrics are effective for evaluating STG tasks, and improve the agreement with human judgement up to 20% with respect to common NLG metrics.
Faithful Low-Resource Data-to-Text Generation through Cycle Training
Cycle training uses two models which are inverses of each other: one that generates text from structured data, and one which generates the structured data from natural language text.
Preventing Catastrophic Forgetting in Continual Learning of New Natural Language Tasks
In this paper, we approach the problem of incrementally expanding MTL models' capability to solve new tasks over time by distilling the knowledge of an already trained model on n tasks into a new one for solving n+1 tasks.
Learning to Solve NLP Tasks in an Incremental Number of Languages
In real scenarios, a multilingual model trained to solve NLP tasks on a set of languages can be required to support new languages over time.
VoiSeR: A New Benchmark for Voice-Based Search Refinement
This common user intent is usually available through a {``}filter-by{''} interface on online shopping websites, but is challenging to support naturally via voice, as the intent of refinements must be interpreted in the context of the original search, the initial results, and the available product catalogue facets.
Global Thread-Level Inference for Comment Classification in Community Question Answering
Community question answering, a recent evolution of question answering in the Web context, allows a user to quickly consult the opinion of a number of people on a particular topic, thus taking advantage of the wisdom of the crowd.
KeLP at SemEval-2017 Task 3: Learning Pairwise Patterns in Community Question Answering
This paper describes the KeLP system participating in the SemEval-2017 community Question Answering (cQA) task.
Deep Learning in Semantic Kernel Spaces
Kernel methods enable the direct usage of structured representations of textual data during language learning and inference tasks.
