Papers by Marco Damonte

8 papers
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.
Cross-Lingual Abstract Meaning Representation Parsing (N18-1)

Copied to clipboard

Challenge: Abstract Meaning Representation (AMR) research has focused on English . Qualitative analysis shows that the new parsers overcome structural differences between the languages.
Approach: They propose to use an AMR parser for English and parallel corpora to learn AMR for Italian, Spanish, German and Chinese.
Outcome: The proposed method overcomes structural differences between the target languages and requires no gold standard data.
Practical Semantic Parsing for Spoken Language Understanding (N19-2)

Copied to clipboard

Challenge: Existing systems that can handle a user's utterance are unable to handle Q&A or SLU.
Approach: They build a transfer learning framework for executable semantic parsing . they show it is effective for Q&A and for spoken language understanding .
Outcome: The proposed framework is effective for Q&A and Spoken Language Understanding . it can be learned by exploiting data on other domains, the authors show .
Structural Neural Encoders for AMR-to-text Generation (N19-1)

Copied to clipboard

Challenge: Abstract Meaning Representation (AMR) graphs are graphs, rather than trees, because they contain reentrant nodes with multiple parents.
Approach: They propose to use sequence-to-sequence models that encode AMR graphs into vector representations to generate sentences from AMRs.
Outcome: The proposed model outperforms tree encoders in the AMR-to-text generation task by 24.40 points.
The Role of Reentrancies in Abstract Meaning Representation Parsing (2020.findings-emnlp)

Copied to clipboard

Challenge: Abstract Meaning Representation (AMR) parsers make errors with respect to reentrancies, which complicates AMR parsing and requires specific transitions.
Approach: They propose to categorize the types of errors AMR parsers make with respect to reentrancies and find that correcting these errors provides an in-crease of up to 5% Smatch in parsing perfor- mance and 20% in reen- trancy prediction.
Outcome: The proposed formalism can predict reentrancies with 5% accuracy and 20% accuracy.
Abstract Meaning Representation for Paraphrase Detection (N18-1)

Copied to clipboard

Challenge: Abstract Meaning Representation (AMR) parsing is ideal for paraphrase detection . it abstracts away from the syntactic realization of a sentence, and denotes only its meaning in a canonical form.
Approach: They propose a technique that uses latent semantic analysis to translate sentences into AMR graphs . they show that the technique can be used to detect whether two sentences have the same meaning .
Outcome: The proposed technique significantly advances state-of-the-art paraphrase detection for the Microsoft Research Paraphrase Corpus.
CLASP: Few-Shot Cross-Lingual Data Augmentation for Semantic Parsing (2022.aacl-short)

Copied to clipboard

Challenge: Large Language Models excel at a low-resource level given limited data, but are unsuitable for runtime systems which require low latency.
Approach: They propose a method to augment training data for a model 40x smaller (500M parameters) they use Alexa to generate synthetic data from Alexa 20B to augment the training set .
Outcome: The proposed method improves low-resource SP on two datasets in low-source settings.
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.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations