In this paper, we examine the current state-of-the-art in AMR parsing, which relies on ensemble strategies by merging multiple graph predictions. Our analysis reveals that the present models often violate AMR structural constraints. To address this issue, we develop a validation method, and show how ensemble models can exploit SMATCH metric weaknesses to obtain higher scores, but sometimes result in corrupted graphs. Additionally, we highlight the demanding need to compute the SMATCH score among all possible predictions. To overcome these challenges, we propose two novel ensemble strategies based on Transformer models, improving robustness to structural constraints, while also reducing the computational time. Our methods provide new insights for enhancing AMR parsers and metrics. Our code is available at \href{https://www.github.com/babelscape/AMRs-Assemble}{github.com/babelscape/AMRs-Assemble}.

Translating natural language into Bash Commands is an emerging research field that has gained attention in recent years. Most efforts have focused on producing more accurate translation models. To the best of our knowledge, only two datasets are available, with one based on the other. Both datasets involve scraping through known data sources (through platforms like stack overflow, crowdsourcing, etc.) and hiring experts to validate and correct either the English text or Bash Commands. This paper provides two contributions to research on synthesizing Bash Commands from scratch. First, we describe a state-of-the-art translation model used to generate Bash Commands from the corresponding English text. Second, we introduce a new NL2CMD dataset that is automatically generated, involves minimal human intervention, and is over six times larger than prior datasets. Since the generation pipeline does not rely on existing Bash Commands, the distribution and types of commands can be custom adjusted. We evaluate the performance of ChatGPT on this task and discuss the potential of using it as a data generator. Our empirical results show how the scale and diversity of our dataset can offer unique opportunities for semantic parsing researchers.

Dependency parsing is the basis of many complex pipelines for problems in natural language processing such as machine summarization, machine translation, event extraction, semantic parsing,semantic role labeling(SRL), emotion analysis, dialogue systems and information processing. Thus, any error in dependency parsing could propagate to downstream task and therefore any advance in this field could lead to major improvement in NLP tasks. There are two main approaches to dependency parsing. The first approach is transition based which has incremental local inference and involves using datastructures such as buffer and stack (Nivre 2008),(Buys & Blunsom 2015). This approach has the limitation of resolving relatively short sentences and is a trade-off between speed and accuracy.

Semantic role labeling (SRL) is the process of detecting the predicate-argument structure of each predicate in a sentence. SRL plays a crucial role as a pre-processing step in many NLP applications such as topic and concept extraction, question answering, summarization, machine translation, sentiment analysis, and text mining. Recently, in many languages, unified SRL dragged lots of attention due to its outstanding performance, which is the result of overcoming the error propagation problem. However, regarding the Persian language, all previous works have focused on traditional methods of SRL leading to a drop in accuracy and imposing expensive feature extraction steps in terms of financial resources, time and energy consumption. In this work, we present an end-to-end SRL method that not only eliminates the need for feature extraction but also outperforms existing methods in facing new samples in practical situations. The proposed method does not employ any auxiliary features and shows more than 16 (83.16) percent improvement in accuracy against previous methods in similar circumstances.

In this paper we compare some old formulations of Minimalism, in particular Stabler's computational minimalism, and Chomsky's new formulation of Merge and Minimalism, from the point of view of their mathematical description in terms of Hopf algebras. We show that the newer formulation has a clear advantage purely in terms of the underlying mathematical structure. More precisely, in the case of Stabler's computational minimalism, External Merge can be described in terms of a partially defined operated algebra with binary operation, while Internal Merge determines a system of right-ideal coideals of the Loday-Ronco Hopf algebra and corresponding right-module coalgebra quotients. This mathematical structure shows that Internal and External Merge have significantly different roles in the old formulations of Minimalism, and they are more difficult to reconcile as facets of a single algebraic operation, as desirable linguistically. On the other hand, we show that the newer formulation of Minimalism naturally carries a Hopf algebra structure where Internal and External Merge directly arise from the same operation. We also compare, at the level of algebraic properties, the externalization model of the new Minimalism with proposals for assignments of planar embeddings based on heads of trees.

Previous work has predominantly focused on monolingual English semantic parsing. We, instead, explore the feasibility of Chinese semantic parsing in the absence of labeled data for Chinese meaning representations. We describe the pipeline of automatically collecting the linearized Chinese meaning representation data for sequential-to sequential neural networks. We further propose a test suite designed explicitly for Chinese semantic parsing, which provides fine-grained evaluation for parsing performance, where we aim to study Chinese parsing difficulties. Our experimental results show that the difficulty of Chinese semantic parsing is mainly caused by adverbs. Realizing Chinese parsing through machine translation and an English parser yields slightly lower performance than training a model directly on Chinese data.

Extracting sentiment elements using pre-trained generative models has recently led to large improvements in aspect-based sentiment analysis benchmarks. However, these models always need large-scale computing resources, and they also ignore explicit modeling of structure between sentiment elements. To address these challenges, we propose an opinion tree parsing model, aiming to parse all the sentiment elements from an opinion tree, which is much faster, and can explicitly reveal a more comprehensive and complete aspect-level sentiment structure. In particular, we first introduce a novel context-free opinion grammar to normalize the opinion tree structure. We then employ a neural chart-based opinion tree parser to fully explore the correlations among sentiment elements and parse them into an opinion tree structure. Extensive experiments show the superiority of our proposed model and the capacity of the opinion tree parser with the proposed context-free opinion grammar. More importantly, the results also prove that our model is much faster than previous models.

Visually-situated language is ubiquitous -- sources range from textbooks with diagrams to web pages with images and tables, to mobile apps with buttons and forms. Perhaps due to this diversity, previous work has typically relied on domain-specific recipes with limited sharing of the underlying data, model architectures, and objectives. We present Pix2Struct, a pretrained image-to-text model for purely visual language understanding, which can be finetuned on tasks containing visually-situated language. Pix2Struct is pretrained by learning to parse masked screenshots of web pages into simplified HTML. The web, with its richness of visual elements cleanly reflected in the HTML structure, provides a large source of pretraining data well suited to the diversity of downstream tasks. Intuitively, this objective subsumes common pretraining signals such as OCR, language modeling, image captioning. In addition to the novel pretraining strategy, we introduce a variable-resolution input representation and a more flexible integration of language and vision inputs, where language prompts such as questions are rendered directly on top of the input image. For the first time, we show that a single pretrained model can achieve state-of-the-art results in six out of nine tasks across four domains: documents, illustrations, user interfaces, and natural images.

Symbolic Regression (SR) allows for the discovery of scientific equations from data. To limit the large search space of possible equations, prior knowledge has been expressed in terms of formal grammars that characterize subsets of arbitrary strings. However, there is a mismatch between context-free grammars required to express the set of syntactically correct equations, missing closure properties of the former, and a tree structure of the latter. Our contributions are to (i) compactly express experts' prior beliefs about which equations are more likely to be expected by probabilistic Regular Tree Expressions (pRTE), and (ii) adapt Bayesian inference to make such priors efficiently available for symbolic regression encoded as finite state machines. Our scientific case studies show its effectiveness in soil science to find sorption isotherms and for modeling hyper-elastic materials.

However, Translating natural language queries into SQLs in a seq2seq to produce a correct SQL expression, a parser should not manner has attracted much attention recently. However, only understand the semantics of the input query but also produce compared with abstract-syntactic-tree-based SQL generation, predictions that satisfy the SQL grammar and database seq2seq semantic parsers face much more challenges, including schema restrictions. We experimentally find that with the help poor quality on schematical information prediction and of pre-trained language models, seq2seq models are capable poor semantic coherence between natural language queries of generating legal SQL skeletons, while detailed schematic and SQLs. This paper analyses the above difficulties and information prediction remains a big difficulty for seq2seq proposes a seq2seq-oriented decoding strategy called SR, parsers. To solve this problem, in this paper, we propose which includes a new intermediate representation SSQL and a new intermediate representation called SSQL (Semantic-a reranking method with score re-estimator to solve the above SQL) for seq2seq SQL generation based on standard SQL obstacles respectively.