Search Results for author: Massimiliano Ciaramita

Found 18 papers, 4 papers with code

Ask the Right Questions: Active Question Reformulation with Reinforcement Learning

2 code implementations ICLR 2018 Christian Buck, Jannis Bulian, Massimiliano Ciaramita, Wojciech Gajewski, Andrea Gesmundo, Neil Houlsby, Wei Wang

The agent probes the system with, potentially many, natural language reformulations of an initial question and aggregates the returned evidence to yield the best answer.

Information Retrieval Question Answering +3

Zero-Shot Dual Machine Translation

1 code implementation25 May 2018 Lierni Sestorain, Massimiliano Ciaramita, Christian Buck, Thomas Hofmann

Our method can obtain improvements also on the setting where a small amount of parallel data for the zero-shot language pair is available.

Machine Translation NMT +1

Analyzing Language Learned by an Active Question Answering Agent

no code implementations23 Jan 2018 Christian Buck, Jannis Bulian, Massimiliano Ciaramita, Wojciech Gajewski, Andrea Gesmundo, Neil Houlsby, Wei Wang

We analyze the language learned by an agent trained with reinforcement learning as a component of the ActiveQA system [Buck et al., 2017].

Information Retrieval Question Answering +3

Learning to Coordinate Multiple Reinforcement Learning Agents for Diverse Query Reformulation

no code implementations ICLR 2019 Rodrigo Nogueira, Jannis Bulian, Massimiliano Ciaramita

We propose a method to efficiently learn diverse strategies in reinforcement learning for query reformulation in the tasks of document retrieval and question answering.

Question Answering reinforcement-learning +2

On Identifiability in Transformers

no code implementations ICLR 2020 Gino Brunner, Yang Liu, Damián Pascual, Oliver Richter, Massimiliano Ciaramita, Roger Wattenhofer

We show that, for sequences longer than the attention head dimension, attention weights are not identifiable.

Meta Answering for Machine Reading

no code implementations11 Nov 2019 Benjamin Borschinger, Jordan Boyd-Graber, Christian Buck, Jannis Bulian, Massimiliano Ciaramita, Michelle Chen Huebscher, Wojciech Gajewski, Yannic Kilcher, Rodrigo Nogueira, Lierni Sestorain Saralegu

We investigate a framework for machine reading, inspired by real world information-seeking problems, where a meta question answering system interacts with a black box environment.

Natural Questions Question Answering +1

Multi-agent query reformulation: Challenges and the role of diversity

no code implementations ICLR Workshop drlStructPred 2019 Rodrigo Nogueira, Jannis Bulian, Massimiliano Ciaramita

We investigate methods to efficiently learn diverse strategies in reinforcement learning for a generative structured prediction problem: query reformulation.

Question Answering reinforcement-learning +3

Zero-Shot Retrieval with Search Agents and Hybrid Environments

no code implementations30 Sep 2022 Michelle Chen Huebscher, Christian Buck, Massimiliano Ciaramita, Sascha Rothe

We extend the previous learning to search setup to a hybrid environment, which accepts discrete query refinement operations, after a first-pass retrieval step via a dual encoder.

Retrieval

In-Context Probing: Toward Building Robust Classifiers via Probing Large Language Models

no code implementations23 May 2023 Afra Amini, Massimiliano Ciaramita

However, the effectiveness of in-context learning is dependent on the provided context, and the performance on a downstream task can vary considerably, depending on the instruction.

In-Context Learning

Assessing Large Language Models on Climate Information

no code implementations4 Oct 2023 Jannis Bulian, Mike S. Schäfer, Afra Amini, Heidi Lam, Massimiliano Ciaramita, Ben Gaiarin, Michelle Chen Huebscher, Christian Buck, Niels Mede, Markus Leippold, Nadine Strauss

We evaluate several recent LLMs and conduct a comprehensive analysis of the results, shedding light on both the potential and the limitations of LLMs in the realm of climate communication.

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