Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userLevi Graph AMR Parser using Heterogeneous Attention
LEVI Graph AMR Parser باستخدام اهتمام غير متجانس
256
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
إلى جانب رزق BiAffine، تم تكييف المحولات بفعالية مع تحويل الرسائل النصية وحققت أداء حالة من الفن على تحليل عمرو.ومع ذلك، فإن العديد من الأعمال السابقة تعتمد على فك تشفير BiAffine لأي منهما أو كلا من القوس والملصقات على الرغم من أن معظم الميزات المستخدمة من قبل وحدة فك الترميز قد تتعلم من قبل المحول بالفعل.تقدم هذه الورقة نهجا جديدا لتحليل عمرو من خلال الجمع بين البيانات غير المتجانسة (الرموز والمفاهيم والملصقات) كإدخال واحد إلى محول لتعلم الانتباه، واستخدام مصفوفات الاهتمام فقط من المحول للتنبؤ بجميع العناصر في الرسوم البيانية AMR (المفاهيم، الأقواس،تسميات).على الرغم من أن نماذجنا تستخدم معلمات أقل بكثير من محلل الرسم البياني للحالة السابقة، فإنها تظهر دقة مماثلة أو أفضل على عمرو 2.0 و 3.0.
Coupled with biaffine decoders, transformers have been effectively adapted to text-to-graph transduction and achieved state-of-the-art performance on AMR parsing. Many prior works, however, rely on the biaffine decoder for either or both arc and label predictions although most features used by the decoder may be learned by the transformer already. This paper presents a novel approach to AMR parsing by combining heterogeneous data (tokens, concepts, labels) as one input to a transformer to learn attention, and use only attention matrices from the transformer to predict all elements in AMR graphs (concepts, arcs, labels). Although our models use significantly fewer parameters than the previous state-of-the-art graph parser, they show similar or better accuracy on AMR 2.0 and 3.0.
References used
https://aclanthology.org/
rate research
Read More
To capture the semantic graph structure from raw text, most existing summarization approaches are built on GNNs with a pre-trained model. However, these methods suffer from cumbersome procedures and inefficient computations for long-text documents. T
o mitigate these issues, this paper proposes HetFormer, a Transformer-based pre-trained model with multi-granularity sparse attentions for long-text extractive summarization. Specifically, we model different types of semantic nodes in raw text as a potential heterogeneous graph and directly learn heterogeneous relationships (edges) among nodes by Transformer. Extensive experiments on both single- and multi-document summarization tasks show that HetFormer achieves state-of-the-art performance in Rouge F1 while using less memory and fewer parameters.
Abstract Several metrics have been proposed for assessing the similarity of (abstract) meaning representations (AMRs), but little is known about how they relate to human similarity ratings. Moreover, the current metrics have complementary strengths a
nd weaknesses: Some emphasize speed, while others make the alignment of graph structures explicit, at the price of a costly alignment step. In this work we propose new Weisfeiler-Leman AMR similarity metrics that unify the strengths of previous metrics, while mitigating their weaknesses. Specifically, our new metrics are able to match contextualized substructures and induce n:m alignments between their nodes. Furthermore, we introduce a Benchmark for AMR Metrics based on Overt Objectives (Bamboo), the first benchmark to support empirical assessment of graph-based MR similarity metrics. Bamboo maximizes the interpretability of results by defining multiple overt objectives that range from sentence similarity objectives to stress tests that probe a metric's robustness against meaning-altering and meaning- preserving graph transformations. We show the benefits of Bamboo by profiling previous metrics and our own metrics. Results indicate that our novel metrics may serve as a strong baseline for future work.
AMR (Abstract Meaning Representation) and EDS (Elementary Dependency Structures) are two popular meaning representations in NLP/NLU. AMR is more abstract and conceptual, while EDS is more low level, closer to the lexical structures of the given sente
nces. It is thus not surprising that EDS parsing is easier than AMR parsing. In this work, we consider using information from EDS parsing to help improve the performance of AMR parsing. We adopt a transition-based parser and propose to add EDS graphs as additional semantic features using a graph encoder composed of LSTM layer and GCN layer. Our experimental results show that the additional information from EDS parsing indeed gives a boost to the performance of the base AMR parser used in our experiments.
External syntactic and semantic information has been largely ignored by existing neural coreference resolution models. In this paper, we present a heterogeneous graph-based model to incorporate syntactic and semantic structures of sentences. The prop
osed graph contains a syntactic sub-graph where tokens are connected based on a dependency tree, and a semantic sub-graph that contains arguments and predicates as nodes and semantic role labels as edges. By applying a graph attention network, we can obtain syntactically and semantically augmented word representation, which can be integrated using an attentive integration layer and gating mechanism. Experiments on the OntoNotes 5.0 benchmark show the effectiveness of our proposed model.
We present our contribution to the IWPT 2021 shared task on parsing into enhanced Universal Dependencies. Our main system component is a hybrid tree-graph parser that integrates (a) predictions of spanning trees for the enhanced graphs with (b) addit
ional graph edges not present in the spanning trees. We also adopt a finetuning strategy where we first train a language-generic parser on the concatenation of data from all available languages, and then, in a second step, finetune on each individual language separately. Additionally, we develop our own complete set of pre-processing modules relevant to the shared task, including tokenization, sentence segmentation, and multiword token expansion, based on pre-trained XLM-R models and our own pre-training of character-level language models. Our submission reaches a macro-average ELAS of 89.24 on the test set. It ranks top among all teams, with a margin of more than 2 absolute ELAS over the next best-performing submission, and best score on 16 out of 17 languages.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
