We present a family of encodings for sequence labeling dependency parsing, based on the concept of hierarchical bracketing. We prove that the existing 4-bit projective encoding belongs to this family, but it is suboptimal in the number of labels used to encode a tree. We derive an optimal hierarchical bracketing, which minimizes the number of symbols used and encodes projective trees using only 12 distinct labels (vs. 16 for the 4-bit encoding). We also extend optimal hierarchical bracketing to support arbitrary non-projectivity in a more compact way than previous encodings. Our new encodings yield competitive accuracy on a diverse set of treebanks.

We revisit hierarchical bracketing encodings from a practical perspective in the context of dependency graph parsing.The approach encodes graphs as sequences, enabling lineartime parsing with n tagging actions, and still representing reentrancies, cycles, and empty nodes.Compared to existing graph linearizations, this representation substantially reduces the label space while preserving structural information.We evaluate it on a multilingual and multi-formalism benchmark, showing competitive results and consistent improvements over other methods in exact match accuracy.

Event extraction from unstructured text is a critical task in natural language processing, often requiring substantial annotated data. This study presents an approach to document-level event extraction applied to Italian crime news, utilizing large language models (LLMs) with minimal labeled data. Our method leverages zero-shot prompting and in-context learning to effectively extract relevant event information. We address three key challenges: (1) identifying text spans corresponding to event entities, (2) associating related spans dispersed throughout the text with the same entity, and (3) formatting the extracted data into a structured JSON. The findings are promising: LLMs achieve an F1-score of approximately 60% for detecting event-related text spans, demonstrating their potential even in resource-constrained settings. This work represents a significant advancement in utilizing LLMs for tasks traditionally dependent on extensive data, showing that meaningful results are achievable with minimal data annotation. Additionally, the proposed approach outperforms several baselines, confirming its robustness and adaptability to various event extraction scenarios. • Novel use of LLMs for event extraction from Italian news with minimal annotated data. • In-context learning outperforms zero-shot prompting for identifying event spans. • Mixtral achieves top performance in event extraction from Italian crime news. • LLMs outperform QA models, proving robust in data-scarce environments. • In-context learning performance depends on the quality of selected examples.

Various linearizations have been proposed to cast syntactic dependency parsing as sequence labeling.However, these approaches do not support more complex graph-based representations, such as semantic dependencies or enhanced universal dependencies, as they cannot handle reentrancy or cycles.By extending them, we define a range of unbounded and bounded linearizations that can be used to cast graph parsing as a tagging task, enlarging the toolbox of problems that can be solved under this paradigm.Experimental results on semantic dependency and enhanced UD parsing show that with a good choice of encoding, sequencelabeling dependency graph parsers combine high efficiency with accuracies close to the state of the art, in spite of their simplicity.

We introduce an encoding for syntactic parsing as sequence labeling that can represent any projective dependency tree as a sequence of 4-bit labels, one per word.The bits in each word's label represent (1) whether it is a right or left dependent, (2) whether it is the outermost (left/right) dependent of its parent, (3) whether it has any left children and ( 4) whether it has any right children.We show that this provides an injective mapping from trees to labels that can be encoded and decoded in linear time.We then define a 7-bit extension that represents an extra plane of arcs, extending the coverage to almost full non-projectivity (over 99.9% empirical arc coverage).Results on a set of diverse treebanks show that our 7-bit encoding obtains substantial accuracy gains over the previously best-performing sequence labeling encodings.

Alberto Muñoz-Ortiz, David Vilares, Carlos Gómez-Rodríguez. Proceedings of the 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers). 2023.

Treebank selection for parsing evaluation and the spurious effects that might arise from a biased choice have not been explored in detail. This paper studies how evaluating on a single subset of treebanks can lead to weak conclusions. First, we take a few contrasting parsers, and run them on subsets of treebanks proposed in previous work, whose use was justified (or not) on criteria such as typology or data scarcity. Second, we run a large-scale version of this experiment, create vast amounts of random subsets of treebanks, and compare on them many parsers whose scores are available. The results show substantial variability across subsets and that although establishing guidelines for good treebank selection is hard, some inadequate strategies can be easily avoided.

Recent analyses suggest that encoders pretrained for language modeling capture certain morpho-syntactic structure. However, probing frameworks for word vectors still do not report results on standard setups such as constituent and dependency parsing. This paper addresses this problem and does full parsing (on English) relying only on pretraining architectures – and no decoding. We first cast constituent and dependency parsing as sequence tagging. We then use a single feed-forward layer to directly map word vectors to labels that encode a linearized tree. This is used to: (i) see how far we can reach on syntax modelling with just pretrained encoders, and (ii) shed some light about the syntax-sensitivity of different word vectors (by freezing the weights of the pretraining network during training). For evaluation, we use bracketing F1-score and las, and analyze in-depth differences across representations for span lengths and dependency displacements. The overall results surpass existing sequence tagging parsers on the ptb (93.5%) and end-to-end en-ewt ud (78.8%).

We define a mapping from transition-based parsing algorithms that read sentences from left to right to sequence labeling encodings of syntactic trees.This not only establishes a theoretical relation between transition-based parsing and sequence-labeling parsing, but also provides a method to obtain new encodings for fast and simple sequence labeling parsing from the many existing transition-based parsers for different formalisms.Applying it to dependency parsing, we implement sequence labeling versions of four algorithms, showing that they are learnable and obtain comparable performance to existing encodings.

We present a bracketing-based encoding that can be used to represent any 2-planar dependency tree over a sentence of length n as a sequence of n labels, hence providing almost total coverage of crossing arcs in sequence labeling parsing.First, we show that existing bracketing encodings for parsing as labeling can only handle a very mild extension of projective trees.Second, we overcome this limitation by taking into account the well-known property of 2-planarity, which is present in the vast majority of dependency syntactic structures in treebanks, i.e., the arcs of a dependency tree can be split into two planes such that arcs in a given plane do not cross.We take advantage of this property to design a method that balances the brackets and that encodes the arcs belonging to each of those planes, allowing for almost unrestricted non-projectivity (∼ 99.9% coverage) in sequence labeling parsing.The experiments show that our linearizations improve over the accuracy of the original bracketing encoding in highly non-projective treebanks (on average by 0.4 LAS), while achieving a similar speed.Also, they are especially suitable when PoS tags are not used as input parameters to the models.

This paper reduces discontinuous parsing to sequence labeling.It first shows that existing reductions for constituent parsing as labeling do not support discontinuities.Second, it fills this gap and proposes to encode tree discontinuities as nearly ordered permutations of the input sequence.Third, it studies whether such discontinuous representations are learnable.The experiments show that despite the architectural simplicity, under the right representation, the models are fast and accurate.1

We use parsing as sequence labeling as a common framework to learn across constituency and dependency syntactic abstractions.To do so, we cast the problem as multitask learning (MTL).First, we show that adding a parsing paradigm as an auxiliary loss consistently improves the performance on the other paradigm.Secondly, we explore an MTL sequence labeling model that parses both representations, at almost no cost in terms of performance and speed.The results across the board show that on average MTL models with auxiliary losses for constituency parsing outperform singletask ones by 1.05 F1 points, and for dependency parsing by 0.62 UAS points.

We present HEAD-QA, a multi-choice question answering testbed to encourage research on complex reasoning.The questions come from exams to access a specialized position in the Spanish healthcare system, and are challenging even for highly specialized humans.We then consider monolingual (Spanish) and cross-lingual (to English) experiments with information retrieval and neural techniques.We show that: (i) HEAD-QA challenges current methods, and (ii) the results lag well behind human performance, demonstrating its usefulness as a benchmark for future work.

Michalina Strzyz, David Vilares, Carlos Gómez-Rodríguez. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.

We introduce a method to reduce constituent parsing to sequence labeling.For each word w t , it generates a label that encodes: (1) the number of ancestors in the tree that the words w t and w t+1 have in common, and (2) the nonterminal symbol at the lowest common ancestor.We first prove that the proposed encoding function is injective for any tree without unary branches.In practice, the approach is made extensible to all constituency trees by collapsing unary branches.We then use the PTB and CTB treebanks as testbeds and propose a set of fast baselines.We achieve 90.7% F-score on the PTB test set, outperforming the Vinyals et al. (2015) sequence-to-sequence parser.In addition, sacrificing some accuracy, our approach achieves the fastest constituent parsing speeds reported to date on PTB by a wide margin. 1

We explore how to detect people's perspectives that occupy a certain proposition.We propose a Bayesian modelling approach where topics (or propositions) and their associated perspectives (or viewpoints) are modeled as latent variables.Words associated with topics or perspectives follow different generative routes.Based on the extracted perspectives, we can extract the top associated sentences from text to generate a succinct summary which allows a quick glimpse of the main viewpoints in a document.The model is evaluated on debates from the House of Commons of the UK Parliament, revealing perspectives from the debates without the use of labelled data and obtaining better results than previous related solutions under a variety of evaluations.

Objective sentences lack sentiments and, hence, can reduce the accuracy of a sentiment classifier. Traditional methods prior to 2001 used hand-crafted templates to identify subjectivity and did not generalize well for resource-deficient languages such as Spanish. Later works published between 2002 and 2009 proposed the use of deep neural networks to automatically learn a dictionary of features (in the form of convolution kernels) that is portable to new languages. Recently, recurrent neural networks are being used to model alternating subjective and objective sentences within a single review. Such networks are difficult to train for a large vocabulary of words due to the problem of vanishing gradients. Hence, in this paper we consider use of a Lyapunov linear matrix inequality to classify Spanish text as subjective or objective by combining Spanish features and features obtained from the corresponding translated English text. The aligned features for each sentence are next evolved using multiple kernel learning. The proposed Lyapunov deep neural network outperforms baselines by over 10% and the features learned in the hidden layers improve our understanding subjective sentences in Spanish.

Millions of micro texts are published every day on Twitter. Identifying the sentiment present in them can be helpful for measuring the frame of mind of the public, their satisfaction with respect to a product, or their support of a social event. In this context, polarity classification is a subfield of sentiment analysis focused on determining whether the content of a text is objective or subjective, and in the latter case, if it conveys a positive or a negative opinion. Most polarity detection techniques tend to take into account individual terms in the text and even some degree of linguistic knowledge, but they do not usually consider syntactic relations between words. This article explores how relating lexical, syntactic, and psychometric information can be helpful to perform polarity classification on Spanish tweets. We provide an evaluation for both shallow and deep linguistic perspectives. Empirical results show an improved performance of syntactic approaches over pure lexical models when using large training sets to create a classifier, but this tendency is reversed when small training collections are used.

Abstract We describe an opinion mining system which classifies the polarity of Spanish texts. We propose an NLP approach that undertakes pre-processing, tokenisation and POS tagging of texts to then obtain the syntactic structure of sentences by means of a dependency parser. This structure is then used to address three of the most significant linguistic constructions for the purpose in question: intensification, subordinate adversative clauses and negation. We also propose a semi-automatic domain adaptation method to improve the accuracy of our system in specific application domains, by enriching semantic dictionaries using machine learning methods in order to adapt the semantic orientation of their words to a particular field. Experimental results are promising in both general and specific domains.

We describe a system that classifies the polarity of Spanish tweets. We adopt a hybrid approach, which combines machine learning and linguistic knowledge acquired by means of NLP. We use part-of-speech tags, syntactic dependencies and semantic knowledge as features for a supervised classifier. Lexical particularities of the language used in Twitter are taken into account in a pre-processing step. Experimental results improve over those of pure machine learning approaches and confirm the practical utility of the proposal.