paper-with-me

홈 › Papers

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 tokens, implicit alignments can be derived. Transition-based parsers operate over the sentence from left to right, capturing this inductive bias via alignments at the cost of limited expressiveness. In this work, we propose a transition-based system that combines hard-attention over sentences with a target-side action pointer mechanism to decouple source tokens from node representations and address alignments. We model the transitions as well as the pointer mechanism through straightforward modifications within a single Transformer architecture. Parser state and graph structure information are efficiently encoded using attention heads. We show that our action-pointer approach leads to increased expressiveness and attains large gains (+1.6 points) against the best transition-based AMR parser in very similar conditions. While using no graph re-categorization, our single model yields the second best Smatch score on AMR 2.0 (81.8), which is further improved to 83.4 with silver data and ensemble decoding.

📄 PDF Abstract BibTeX arXiv:2104.14674

Code (1)

ibm/graph_ensemble_learning pytorch

Tasks

Abstract Meaning RepresentationAMR ParsingHard AttentionInductive BiasSentence

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 설명 없음
Residual Connection 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Adam 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Similar Papers 제목 키워드 기반

AMR Parsing with Action-Pointer Transformer

2020-11-24 · Anonymous

Abstract Meaning Representation parsing belongs to a category of sentence-to-graph prediction tasks where the target graph is not explicitly linked to the sentence tokens. However, nodes or subgraphs are semantically rel…

Abstract Meaning RepresentationAMR ParsingHard AttentionSentence

Context Transformer with Stacked Pointer Networks for Conversational Question Answering over Knowledge Graphs

2021-03-13 · Joan Plepi, Endri Kacupaj, Kuldeep Singh, Harsh Thakkar 외

Neural semantic parsing approaches have been widely used for Question Answering (QA) systems over knowledge graphs. Such methods provide the flexibility to handle QA datasets with complex queries and a large number of en…

Conversational Question AnsweringKnowledge GraphsLogical ReasoningQuestion Answering+1

Self Attended Stack-Pointer Networks for Learning Long Term Dependencies

2020-12-01 · ICON 2020 12 · Salih Tuc, Burcu Can

We propose a novel deep neural architecture for dependency parsing, which is built upon a Transformer Encoder (Vaswani et al. 2017) and a Stack Pointer Network (Ma et al. 2018). We first encode each sentence using a Tran…

Dependency ParsingSentence

AMR Parsing with Causal Hierarchical Attention and Pointers

2023-10-18 · Chao Lou, Kewei Tu

Translation-based AMR parsers have recently gained popularity due to their simplicity and effectiveness. They predict linearized graphs as free texts, avoiding explicit structure modeling. However, this simplicity neglec…

AMR ParsingDecoderTranslation

Hierarchical Pointer Net Parsing

2019-08-30 · IJCNLP 2019 11 · Linlin Liu, Xiang Lin, Shafiq Joty, Simeng Han 외

Transition-based top-down parsing with pointer networks has achieved state-of-the-art results in multiple parsing tasks, while having a linear time complexity. However, the decoder of these parsers has a sequential struc…

DecoderDiscourse ParsingInductive BiasSentence