paper-with-me

Papers

AMR Parsing as Graph Prediction with Latent Alignment

2018-05-14 · ACL 2018 7 · Chunchuan Lyu, Ivan Titov

Abstract meaning representations (AMRs) are broad-coverage sentence-level semantic representations. AMRs represent sentences as rooted labeled directed acyclic graphs. AMR parsing is challenging partly due to the lack of annotated alignments between nodes in the graphs and words in the corresponding sentences. We introduce a neural parser which treats alignments as latent variables within a joint probabilistic model of concepts, relations and alignments. As exact inference requires marginalizing over alignments and is infeasible, we use the variational auto-encoding framework and a continuous relaxation of the discrete alignments. We show that joint modeling is preferable to using a pipeline of align and parse. The parser achieves the best reported results on the standard benchmark (74.4% on LDC2016E25).

📄 PDF Abstract BibTeX arXiv:1805.05286

Code (2)

ChunchuanLv/AMR_AS_GRAPH_PREDICTION 공식 구현 pytorch
josefigueroa168/NLP-project

Tasks

AMR ParsingPredictionSentence

Similar Papers 제목 키워드 기반

Revisiting Structured Sentiment Analysis as Latent Dependency Graph Parsing

2024-07-05 · Chengjie Zhou, Bobo Li, Hao Fei, Fei Li 외

Structured Sentiment Analysis (SSA) was cast as a problem of bi-lexical dependency graph parsing by prior studies. Multiple formulations have been proposed to construct the graph, which share several intrinsic drawbacks:…

Dependency Parsingglobal-optimizationRelation PredictionSentiment Analysis

A Differentiable Relaxation of Graph Segmentation and Alignment for AMR Parsing

2020-10-23 · EMNLP 2021 11 · Chunchuan Lyu, Shay B. Cohen, Ivan Titov

Abstract Meaning Representations (AMR) are a broad-coverage semantic formalism which represents sentence meaning as a directed acyclic graph. To train most AMR parsers, one needs to segment the graph into subgraphs and a…

AMR ParsingSegmentationSentence

AMR Parsing with Action-Pointer Transformer

2021-04-29 · NAACL 2021 4 · Jiawei Zhou, Tahira Naseem, Ramón Fernandez Astudillo, Radu Florian

Abstract Meaning Representation parsing is a sentence-to-graph prediction task where target nodes are not explicitly aligned to sentence tokens. However, since graph nodes are semantically based on one or more sentence t…

Abstract Meaning RepresentationAMR ParsingHard AttentionInductive Bias+1

Learning Semantic Parsers from Denotations with Latent Structured Alignments and Abstract Programs

2019-09-09 · IJCNLP 2019 11 · Bailin Wang, Ivan Titov, Mirella Lapata

Semantic parsing aims to map natural language utterances onto machine interpretable meaning representations, aka programs whose execution against a real-world environment produces a denotation. Weakly-supervised semantic…

Inductive BiasSemantic Parsing

Generic Axiomatization of Families of Noncrossing Graphs in Dependency Parsing

2017-06-11 · Anssi Yli-Jyrä, Carlos Gómez-Rodríguez

We present a simple encoding for unlabeled noncrossing graphs and show how its latent counterpart helps us to represent several families of directed and undirected graphs used in syntactic and semantic parsing of natural…

Dependency ParsingSemantic Parsing