Papers by Emilio Monti
In Factuality: Efficient Integration of Relevant Facts for Visual Question Answering (2021.acl-short)
Copied to clipboard
| Challenge: | Current Visual Question Answering (VQA) models are trained on labelled data that may be insufficient to learn complex knowledge representations. |
| Approach: | They propose a method to integrate external knowledge into a visual pre-trained model by integrating facts extracted from a knowledge base. |
| Outcome: | The proposed method outperforms baseline models on the KVQA dataset benchmark by 19% and shows that it is weaker than previous models. |
One Semantic Parser to Parse Them All: Sequence to Sequence Multi-Task Learning on Semantic Parsing Datasets (2021.starsem-1)
Copied to clipboard
| Challenge: | Existing semantic parsing datasets lack a single standard for meaning representations . lack of a standard led to the creation of plethora of datasets requiring expert annotators . |
| Approach: | They propose to use multi-task learning to unify different datasets and train a single model for them. |
| Outcome: | The proposed architectures yield better parsing accuracies and composition generalization than single-task models. |
Multilingual Neural Semantic Parsing for Low-Resourced Languages (2021.starsem-1)
Copied to clipboard
| Challenge: | a large amount of training data is needed to understand multilingual semantic parsing models. |
| Approach: | They propose to use machine translation to bootstrap multilingual training data from English data. |
| Outcome: | The proposed model outperforms existing models on human-written sentences and the state-of-the-art models on the public NLMaps dataset. |
MASSIVE Multilingual Abstract Meaning Representation: A Dataset and Baselines for Hallucination Detection (2024.starsem-1)
Copied to clipboard
| Challenge: | Abstract Meaning Representation (AMR) is a semantic formalism that captures the core meaning of an utterance. |
| Approach: | They propose to use AMR to map meanings of 1,685 utterances to 50+ languages to build a dataset 20 times larger than existing resources. |
| Outcome: | The proposed dataset covers more languages, has more utterances, and has localized or translated entities for each language. |
Enhancing Contextual Understanding in Large Language Models through Contrastive Decoding (2024.naacl-long)
Copied to clipboard
| Challenge: | Large language models lack contextual knowledge, resulting in text with factual inconsistencies or contextually unfaithful content. |
| Approach: | They propose a method that integrates contrastive decoding with adversarial irrelevant passages as negative samples to enhance robust context grounding during generation. |
| Outcome: | The proposed method improves context grounding during generation without training. |
Semantic Parsing for Conversational Question Answering over Knowledge Graphs (2023.eacl-main)
Copied to clipboard
| Challenge: | Recent years have seen an increasing number of applications aiming to build conversational interfaces based on information retrieval and user recommendation. |
| Approach: | They develop a dataset where user questions are annotated with Sparql parses and system answers correspond to execution results thereof. |
| Outcome: | The proposed parsers can be used to ground questions into queries over definitions in a knowledge graph with large vocabularies. |
Handling Ontology Gaps in Semantic Parsing (2024.starsem-1)
Copied to clipboard
| Challenge: | Existing methods to detect hallucinations in closed-ontology models are limited by ontology gaps. |
| Approach: | They propose a framework for stimulating and analyzing NSP model hallucinations . they propose 'hallucination simulation framework' to detect hallucinosities in presence of ontology gaps . |
| Outcome: | The proposed framework improves the F1-Score and the IQ Pro benchmark datasets. |