Abstract Meaning Representation Research Articles

Text summarization based on semantic graphs: an abstract meaning representation graph-to-text deep learning approach

Nowadays, due to the constantly growing amount of textual information, automatic text summarization constitutes an important research area in natural language processing. In this work, we present a novel framework that combines semantic graph representations along with deep learning predictions to generate abstractive summaries of single documents, in an effort to utilize a semantic representation of the unstructured textual content in a machine-readable, structured, and concise manner. The overall framework is based on a well defined methodology for performing semantic graph parsing, graph construction, graph transformations for machine learning models and deep learning predictions. The employed semantic graph representation focuses on using the model of abstract meaning representation. Several combinations of graph construction and graph transformation methods are investigated to specify the most efficient of them for the machine learning models. Additionally, a range of deep learning architectures is examined, including a sequence-to-sequence attentive network, reinforcement learning, transformer-based architectures, and pre-trained neural language models. In this direction, a semantic graph representation of an original text is extracted, and then the present framework formulates the problem as a graph-to-summary learning problem to predict a summary of an original text. To the best of our knowledge, this formulation of graph-to-summary predictions in abstractive text summarization, without other intermediate steps in the machine learning phase, has not been presented in the relevant literature. Another important contribution is an introduction of a measure for assessing the factual consistency of the generated summaries in an effort to provide a qualitative evaluation. To assess the framework, an extensive experimental procedure is presented that uses popular datasets to evaluate key aspects of the proposed approach. The obtained results exhibit promising performance, validating the robustness of the proposed framework.

Assessing the Cross-linguistic Utility of Abstract Meaning Representation

Abstract Semantic representations capture the meaning of a text. Abstract Meaning Representation (AMR), a type of semantic representation, focuses on predicate-argument structure and abstracts away from surface form. Though AMR was developed initially for English, it has now been adapted to a multitude of languages in the form of non-English annotation schemas, cross-lingual text-to-AMR parsing, and AMR-to-(non-English) text generation. We advance prior work on cross-lingual AMR by thoroughly investigating the amount, types, and causes of differences that appear in AMRs of different languages. Further, we compare how AMR captures meaning in cross-lingual pairs versus strings, and show that AMR graphs are able to draw out fine-grained differences between parallel sentences. We explore three primary research questions: (1) What are the types and causes of differences in parallel AMRs? (2) How can we measure the amount of difference between AMR pairs in different languages? (3) Given that AMR structure is affected by language and exhibits cross-lingual differences, how do cross-lingual AMR pairs compare to string-based representations of cross-lingual sentence pairs? We find that the source language itself does have a measurable impact on AMR structure, and that translation divergences and annotator choices also lead to differences in cross-lingual AMR pairs. We explore the implications of this finding throughout our study, concluding that, although AMR is useful to capture meaning across languages, evaluations need to take into account source language influences if they are to paint an accurate picture of system output, and meaning generally.

Generation and Polynomial Parsing of Graph Languages with Non-Structural Reentrancies

Abstract Graph-based semantic representations are popular in natural language processing, where it is often convenient to model linguistic concepts as nodes and relations as edges between them. Several attempts have been made to find a generative device that is sufficiently powerful to describe languages of semantic graphs, while at the same allowing efficient parsing. We contribute to this line of work by introducing graph extension grammar, a variant of the contextual hyperedge replacement grammars proposed by Hoffmann et al. Contextual hyperedge replacement can generate graphs with non-structural reentrancies, a type of node-sharing that is very common in formalisms such as abstract meaning representation, but that context-free types of graph grammars cannot model. To provide our formalism with a way to place reentrancies in a linguistically meaningful way, we endow rules with logical formulas in counting monadic second-order logic. We then present a parsing algorithm and show as our main result that this algorithm runs in polynomial time on graph languages generated by a subclass of our grammars, the so-called local graph extension grammars.

Evolving a Pipeline Approach for Abstract Meaning Representation Parsing Towards Dynamic Neural Networks.

Meaning Representation parsing aims to represent a sentence as a structured, Directed, Acyclic Graph (DAG), in an attempt to extract meaning from text. This paper extends an existing 2-stage pipeline AMR parser with state-of-the-art techniques in dependency parsing. First, Pointer-Generator Networks are used for out-of-vocabulary words in the concept identification stage, with an improved initialization via the use of word-and character-level embeddings. Second, the performance of the Relation Identification module is improved by jointly training the Heads Selection and the Arcs Labeling components. Last, we underline the difficulty of end-to-end training with recurrent modules in a static deep neural network construction approach and explore a dynamic construction implementation, which continuously adapts the computation graph, thus potentially enabling end-to-end training in the proposed pipeline solution.

Document-level relation extraction based on sememe knowledge-enhanced abstract meaning representation and reasoning

Document-level relation extraction is a challenging task in information extraction, as it involves identifying semantic relations between entities that are dispersed throughout a document. Existing graph-based approaches often rely on simplistic methods to construct text graphs, which do not provide enough lexical and semantic information to accurately predict the relations between entity pairs. In this paper, we introduce a document-level relation extraction method called SKAMRR (Sememe Knowledge-enhanced Meaning Representation and Reasoning). First, we generate document-level abstract meaning representation graphs using rules and acquire entity nodes’ features through sufficient information propagation. Next, we construct inference graphs for entity pairs and utilize graph neural networks to obtain their representations for relation classification. Additionally, we propose the global adaptive loss to address the issue of long-tailed data. We conduct extensive experiments on four datasets DocRE, CDR, GDA, and HacRED. Our model achieves competitive results and its performance outperforms previous state-of-the-art methods on four datasets.

Spanish Abstract Meaning Representation: Annotation of a General Corpus


 
 
 Abstract Abstract Meaning Representation (AMR), originally designed for English, has been adapted to a number of languages to facilitate cross-lingual semantic representation and analysis. We build on previous work and present the first sizable, general annotation project for Spanish AMR. We release a detailed set of annotation guidelines and a corpus of 486 gold-annotated sentences spanning multiple genres from an existing, cross-lingual AMR corpus. Our work constitutes the second largest non-English gold AMR corpus to date. Fine-tuning an AMR to-Spanish generation model with our annotations results in a BERTScore improvement of 8.8%, demonstrating initial utility of our work.
 
 

Abstract meaning representation of Turkish

AbstractAbstract meaning representation (AMR) is a graph-based sentence-level meaning representation that has become highly popular in recent years. AMR is a knowledge-based meaning representation heavily relying on frame semantics for linking predicate frames and entity knowledge bases such as DBpedia for linking named entity concepts. Although it is originally designed for English, its adaptation to non-English languages is possible by defining language-specific divergences and representations. This article introduces the first AMR representation framework for Turkish, which poses diverse challenges for AMR due to its typological differences compared to English; agglutinative, free constituent order, morphologically highly rich resulting in fewer word surface forms in sentences. The introduced solutions to these peculiarities are expected to guide the studies for other similar languages and speed up the construction of a cross-lingual universal AMR framework. Besides this main contribution, the article also presents the construction of the first AMR corpus of 700 sentences, the first AMR parser (i.e., a tree-to-graph rule-based AMR parser) used for semi-automatic annotation, and the evaluation of the introduced resources for Turkish.

Dependency Patterns of Complex Sentences and Semantic Disambiguation for Abstract Meaning Representation Parsing

Dependency Patterns of Complex Sentences and Semantic Disambiguation for Abstract Meaning Representation Parsing

Weisfeiler-Leman in the Bamboo: Novel AMR Graph Metrics and a Benchmark for AMR Graph Similarity

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 and 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.

Abstract meaning representation for legal documents: an empirical research on a human-annotated dataset

Abstract meaning representation for legal documents: an empirical research on a human-annotated dataset

Distant context aware text generation from abstract meaning representation

Distant context aware text generation from abstract meaning representation

문장 의미의 그래프 구조 표상을 위한 한국어 추상 의미 표상 가이드라인 및 말뭉치 구축

이 논문은 한국어 Abstract Meaning Representation (AMR; 추상 의미 표상) 가이드라인 1.0을 소개한다. AMR은 통합적인 의미 표상 체계로, 의미 분석(semantic parsing)을 위한 주요 프레임워크 중 하나로 자리매김하고 있다. 한국어 AMR 가이드라인은 현행 AMR 1.2.6을 분석하고 이를 한국어의 특성에 맞게 로컬라이징한 것이다. 한국어 AMR 말뭉치는 자연어 이해 기술의 핵심이 되는 의미 파서의 학습 데이터로 활용될 수 있으며, 기계 독해, 자동 요약 등 다양한 자연어 이해 및 생성 기술에 활용될 수 있다. 현재 가이드라인에 따라 구축된 한국어 AMR 말뭉치는 현재 896 문장으로 10,414 어절 규모이다.

Building a Chinese AMR Bank with Concept and Relation Alignments

Abstract Meaning Representation (AMR) is a meaning representation framework in which the meaning of a full sentence is represented as a single-rooted, acyclic, directed graph. In this article, we describe an on-going project to build a Chinese AMR (CAMR) corpus, which currently includes 10,149 sentences from the newsgroup and weblog portion of the Chinese TreeBank (CTB). We describe the annotation specifications for the CAMR corpus, which follow the annotation principles of English AMR but make adaptations where needed to accommodate the linguistic facts of Chinese. The CAMR specifications also include a systematic treatment of sentence-internal discourse relations. One significant change we have made to the AMR annotation methodology is the inclusion of the alignment between word tokens in the sentence and the concepts/relations in the CAMR annotation to make it easier for automatic parsers to model the correspondence between a sentence and its meaning representation. We develop an annotation tool for CAMR, and the inter-agreement as measured by the Smatch score between the two annotators is 0.83, indicating reliable annotation. We also present some quantitative analysis of the CAMR corpus. 46.71% of the AMRs of the sentences are non-tree graphs. Moreover, the AMR of 88.95% of the sentences has concepts inferred from the context of the sentence but do not correspond to a specific word.

English Semantic Recognition Based on Abstract Meaning Representation and Vector Space Model

With the development and application of computer science and technology innovation, artificial intelligence industry has achieved sharp development, and its technology has been widely used in many fields, such as natural language processing, robot manufacturing, semantic recognition, information system development, etc. In terms of natural language processing, the recognition and understanding of human language based on artificial intelligence has become the focus of research. And as semantic recognition and processing play an important part of natural language processing, they have achieved satisfactory results in the Meaning Representation (AMR) and Vector Space Model (VSM) development and application. Based on this, this paper takes the English recognition as the research object, adopts the scientific research methods such as literature analysis, practice investigation and experimental research, further analyzes English semantic recognition based on AMR and VSM from the aspects of semantic recognition difficulty, principles of AMR and VSM and its application in English recognition, as well as the practical applications. The author hopes to provide references for future research.

Special Thematic Section on Semantic Models for Natural Language Processing (Preface)

Abstract With the availability of large language data online, cross-linked lexical resources (such as BabelNet, Predicate Matrix and UBY) and semantically annotated corpora (SemCor, OntoNotes, etc.), more and more applications in Natural Language Processing (NLP) have started to exploit various semantic models. The semantic models have been created on the base of LSA, clustering, word embeddings, deep learning, neural networks, etc., and abstract logical forms, such as Minimal Recursion Semantics (MRS) or Abstract Meaning Representation (AMR), etc. Additionally, the Linguistic Linked Open Data Cloud has been initiated (LLOD Cloud) which interlinks linguistic data for improving the tasks of NLP. This cloud has been expanding enormously for the last four-five years. It includes corpora, lexicons, thesauri, knowledge bases of various kinds, organized around appropriate ontologies, such as LEMON. The semantic models behind the data organization as well as the representation of the semantic resources themselves are a challenge to the NLP community. The NLP applications that extensively rely on the above discussed models include Machine Translation, Information Extraction, Question Answering, Text Simplification, etc.

From Sentences to Documents: Extending Abstract Meaning Representation for Understanding Documents

Research partially supported by the Spanish Government (grants TIN2015-65100-R; TIN2015-65136-C02-2-R).

Automatic Lossless-Summarization of News Articles with Abstract Meaning Representation

The continuously growing size of the textual content needs a way to be designed to store the information in condensed manner with minimal information loss. Hence, the concept of lossless-summary is introduced which aims to address the problem of dangling anaphoras and incoherency in extractive summaries. A pipeline of operations has been proposed by this work in order to generate lossless-summaries. Co-reference resolution is performed pairwise on the sentences before generating the Abstract Meaning Representation (AMR) of the sentences. An algorithm to merge AMR graphs is developed and finally the text is generated using the merged AMR graphs. CNN/Dailymail dataset of news article is used for evaluations and results obtained shows the potential for lossless-summarization.

Domain Transfer for Deep Natural Language Generation from Abstract Meaning Representations

Stochastic natural language generation systems that are trained from labelled datasets are often domainspecific in their annotation and in their mapping from semantic input representations to lexical-syntactic outputs. As a result, learnt models fail to generalize across domains, heavily restricting their usability beyond single applications. In this article, we focus on the problem of domain adaptation for natural language generation. We show how linguistic knowledge from a source domain, for which labelled data is available, can be adapted to a target domain by reusing training data across domains. As a key to this, we propose to employ abstract meaning representations as a common semantic representation across domains. We model natural language generation as a long short-term memory recurrent neural network encoderdecoder, in which one recurrent neural network learns a latent representation of a semantic input, and a second recurrent neural network learns to decode it to a sequence of words. We show that the learnt representations can be transferred across domains and can be leveraged effectively to improve training on new unseen domains. Experiments in three different domains and with six datasets demonstrate that the lexical-syntactic constructions learnt in one domain can be transferred to new domains and achieve up to 75-100% of the performance of in-domain training. This is based on objective metrics such as BLEU and semantic error rate and a subjective human rating study. Training a policy from prior knowledge from a different domain is consistently better than pure in-domain training by up to 10%.

English Caption Writing Assessment Using Abstract Meaning Representation

English Caption Writing Assessment Using Abstract Meaning Representation

Expressive Power of Abstract Meaning Representations

The syntax of abstract meaning representations (AMRs) can be defined recursively, and a systematic translation to first-order logic (FOL) can be specified, including a proper treatment of negation. AMRs without recurrent variables are in the decidable two-variable fragment of FOL. The current definition of AMRs has limited expressive power for universal quantification (up to one universal quantifier per sentence). A simple extension of the AMR syntax and translation to FOL provides the means to represent projection and scope phenomena.