Papers by Adrià de Gispert
Multi-representation ensembles and delayed SGD updates improve syntax-based NMT (P18-2)
Copied to clipboard
| Challenge: | Existing studies have shown that NMT models trained to generate target syntax exhibit improved sentence structure relative to those trained on plain-text. |
| Approach: | They propose an approach to decoding ensembles of models generating different representations, focusing on models generating syntax. |
| Outcome: | The proposed approach gives state-of-the-art performance on a difficult Japanese-English task. |
Learning to Reason Over Time: Timeline Self-Reflection for Improved Temporal Reasoning in Language Models (2025.acl-long)
Copied to clipboard
| Challenge: | Large Language Models struggle with temporal reasoning, which requires processing time-related information such as event sequencing, durations, and inter-temporal relationships. |
| Approach: | They propose a framework that enhances the temporal reasoning abilities of Large Language Models (LLMs) by combining timeline construction with iterative self-reflection. |
| Outcome: | The proposed framework improves the temporal reasoning abilities of large language models and improves traceability of the inference process. |
RAGferee: Building Contextual Reward Models for Retrieval-Augmented Generation (2025.emnlp-main)
Copied to clipboard
Andrei Catalin Coman, Ionut Teodor Sorodoc, Leonardo F. R. Ribeiro, Bill Byrne, James Henderson, Adrià de Gispert
| Challenge: | Existing Reward Models (RMs) struggle in Retrieval Augmented Generation settings. |
| Approach: | They propose a method that repurposes question-answering datasets into preference pairs that prioritise groundedness over stylistic features. |
| Outcome: | The proposed method surpasses existing RMs trained on larger general corpora with an absolute improvement of +15.5%. |
FocusQA: Open-Domain Question Answering with a Context in Focus (2022.findings-emnlp)
Copied to clipboard
Gianni Barlacchi, Ivano Lauriola, Alessandro Moschitti, Marco Del Tredici, Xiaoyu Shen, Thuy Vu, Bill Byrne, Adrià de Gispert
| Challenge: | a new method for question answering with a context in focus simulates a free interaction with QA systems. |
| Approach: | They introduce question answering with a cotext in focus task that simulates a free interaction with QA systems. |
| Outcome: | The proposed model outperforms state-of-the-art models for question answering with a context in focus up to 21.3% absolute points. |
Neural Machine Translation Decoding with Terminology Constraints (N18-2)
Copied to clipboard
| Challenge: | Constrained neural machine translation systems can provide excellent quality but do not strictly enforce terminology. |
| Approach: | They propose a framework for constrained neural decoding which supports target-side constraints as well as constraints with corresponding aligned input text spans. |
| Outcome: | The proposed framework performs well on multiple translation tasks and motivates the need for constrained decoding with attentions to reduce misplacement and duplication when translating user constraints. |
GaRAGe: A Benchmark with Grounding Annotations for RAG Evaluation (2025.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have shown consistent improvements across many tasks requiring natural language understanding, coding, mathematical or logical reasoning . |
| Approach: | They propose to use GaRAGe to evaluate whether LLMs can identify relevant grounding when generating RAG answers. |
| Outcome: | The proposed model over-summarises rather than ground answers strictly on annotated relevant passages, or deflects when no relevant grounding is available. |
Strong and Efficient Baselines for Open Domain Conversational Question Answering (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Current Open Domain Question Answering (ODQA) approaches to reevaluating baselines for efficiency and effectiveness have been limited due to various limitations. |
| Approach: | They propose and evaluate strong yet simple and efficient baselines by introducing a fast reranking component between the retriever and the reader and performing targeted finetuning steps. |
| Outcome: | The proposed method improves the SotA results while reducing the reader’s latency by 60%. |
Domain Adaptive Inference for Neural Machine Translation (P19-1)
Copied to clipboard
| Challenge: | Neural Machine Translation models are effective when trained on broad domains with large datasets, such as news translation. |
| Approach: | They propose a novel approach for adaptive ensemble weighting for Neural Machine Translation by extending Bayesian Interpolation with source information. |
| Outcome: | The proposed approach improves performance on Spanish-English and English-German tasks without the need for the domain label. |
Controlling Japanese Honorifics in English-to-Japanese Neural Machine Translation (D19-52)
Copied to clipboard
| Challenge: | In the Japanese language different levels of honorific speech are used to convey respect, deference, humility, formality and social distance. |
| Approach: | They propose a method for controlling the level of formality of Japanese output . they use heuristics to identify honorific verb forms to classify Japanese sentences . |
| Outcome: | The proposed model can produce Japanese translations in different honorific speech styles for the same English input sentence. |