Tombstones are historically and culturally rich artifacts, encapsulating individual lives, community memory, historical narratives and artistic expression. Yet, many tombstones today face significant preservation challenges, including physical erosion, vandalism, environmental degradation, and political shifts. In this paper, we introduce a novel multi-modal framework for tombstone digitization, aiming to improve the interpretation, organization and retrieval of tombstone content. Our approach leverages vision-language models (VLMs) to translate tombstone images into structured Tombstone Meaning Representations (TMRs), capturing both image and text information. To further enrich semantic parsing, we incorporate retrieval-augmented generation (RAG) to integrate externally dependent elements such as toponyms, occupation codes, and ontological concepts. Compared to traditional OCR-based pipelines, our method improves parsing accuracy from an F1 score of 36.1 to 89.5. Furthermore, we evaluate the model's robustness across diverse linguistic and cultural inscriptions, and simulate physical degradation through image fusion to assess performance under noisy or damaged conditions. Our work represents the first attempt to formalize tombstone understanding using large vision-language models, presenting implications for heritage preservation. The code and supplementary materials are available at: https://github.com/LastDance500/Tombstone-Parsing.

Abstract Current open-domain neural semantics parsers show impressive performance. However, closer inspection of the symbolic meaning representations they produce reveals significant weaknesses: Sometimes they tend to merely copy character sequences from the source text to form symbolic concepts, defaulting to the most frequent word sense based in the training distribution. By leveraging the hierarchical structure of a lexical ontology, we introduce a novel compositional symbolic representation for concepts based on their position in the taxonomical hierarchy. This representation provides richer semantic information and enhances interpretability. We introduce a neural “taxonomical” semantic parser to utilize this new representation system of predicates, and compare it with a standard neural semantic parser trained on the traditional meaning representation format, employing a novel challenge set and evaluation metric for evaluation. Our experimental findings demonstrate that the taxonomical model, trained on much richer and complex meaning representations, is slightly subordinate in performance to the traditional model using the standard metrics for evaluation, but outperforms it when dealing with out-of-vocabulary concepts. We further show through neural model probing that training on a taxonomic representation enhances the model’s ability to learn the taxonomical hierarchy. This finding is encouraging for research in computational semantics that aims to combine data-driven distributional meanings with knowledge-based symbolic representations.

Discourse Representation Theory (DRT) distinguishes itself from other semantic representation frameworks by its ability to model complex semantic and discourse phenomena through structural nesting and variable binding.While seq2seq models hold the state of the art on DRT parsing, their accuracy degrades with the complexity of the sentence, and they sometimes struggle to produce well-formed DRT representations.We introduce the AMS parser, a compositional, neurosymbolic semantic parser for DRT.It rests on a novel mechanism for predicting quantifier scope.We show that the AMS parser reliably produces well-formed outputs and performs well on DRT parsing, especially on complex sentences.1

Simone Tedeschi, Johan Bos, Thierry Declerck, Jan Hajič, Daniel Hershcovich, Eduard Hovy, Alexander Koller, Simon Krek, Steven Schockaert, Rico Sennrich, Ekaterina Shutova, Roberto Navigli. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2023.

Even though many recent semantic parsers are based on deep learning methods, we should not forget that rule-based alternatives might offer advantages over neural approaches with respect to transparency, portability, and explainability. Taking advantage of existing off-the-shelf Universal Dependency parsers, we present a method that maps a syntactic dependency tree to a formal meaning representation based on Discourse Representation Theory. Rather than using lambda calculus to manage variable bindings, our approach is novel in that it consists of using a series of graph transformations. The resulting UD semantic parser shows good performance for English, German, Italian and Dutch, with F-scores over 75%, outperforming a neural semantic parser for the lower-resourced languages. Unlike neural semantic parsers, our UD semantic parser does not hallucinate output, is relatively easy to port to other languages, and is completely transparent.

This paper describes the continuation of a project that aims at establishing an interoperable annotation schema for quantification phenomena as part of the ISO suite of standards for semantic annotation, known as the Semantic Annotation Framework. After a break, caused by the Covid-19 pandemic, the project was relaunched in early 2022 with a second working draft of an annotation scheme, which is discussed in this paper. Keywords: semantic annotation, quantification, interoperability, annotation schema, ISO standard

Abstract We consider the task of crosslingual semantic parsing in the style of Discourse Representation Theory (DRT) where knowledge from annotated corpora in a resource-rich language is transferred via bitext to guide learning in other languages. We introduce Universal Discourse Representation Theory (UDRT), a variant of DRT that explicitly anchors semantic representations to tokens in the linguistic input. We develop a semantic parsing framework based on the Transformer architecture and utilize it to obtain semantic resources in multiple languages following two learning schemes. The Many-to-One approach translates non-English text to English, and then runs a relatively accurate English parser on the translated text, while the One-to-Many approach translates gold standard English to non-English text and trains multiple parsers (one per language) on the translations. Experimental results on the Parallel Meaning Bank show that our proposal outperforms strong baselines by a wide margin and can be used to construct (silver-standard) meaning banks for 99 languages.

We combine character-level and contextual language model representations to improve performance on Discourse Representation Structure parsing.Character representations can easily be added in a sequence-to-sequence model in either one encoder or as a fully separate encoder, with improvements that are robust to different language models, languages and data sets.For English, these improvements are larger than adding individual sources of linguistic information or adding non-contextual embeddings.A new method of analysis based on semantic tags demonstrates that the character-level representations improve performance across a subset of selected semantic phenomena.

Given the limited size of existing idiom corpora, we aim to enable progress in automatic idiom processing and linguistic analysis by creating the largest-to-date corpus of idioms for English. Using a fixed idiom list, automatic pre-extraction, and a strictly controlled crowdsourced annotation procedure, we show that it is feasible to build a high-quality corpus comprising more than 50K instances, an order of a magnitude larger than previous resources. Crucial ingredients of crowdsourcing were the selection of crowdworkers, clear and comprehensive instructions, and an interface that breaks down the task in small, manageable steps. Analysis of the resulting corpus revealed strong effects of genre on idiom distribution, providing new evidence for existing theories on what influences idiom usage. The corpus also contains rich metadata, and is made publicly available.

We investigate the effects of multi-task learning using the recently introduced task of semantic tagging.We employ semantic tagging as an auxiliary task for three different NLP tasks: part-of-speech tagging, Universal Dependency parsing, and Natural Language Inference.We compare full neural network sharing, partial neural network sharing, and what we term the learning what to share setting where negative transfer between tasks is less likely.Our findings show considerable improvements for all tasks, particularly in the learning what to share setting, which shows consistent gains across all tasks.

Neural methods have had several recent successes in semantic parsing, though they have yet to face the challenge of producing meaning representations based on formal semantics. We present a sequence-to-sequence neural semantic parser that is able to produce Discourse Representation Structures (DRSs) for English sentences with high accuracy, outperforming traditional DRS parsers. To facilitate the learning of the output, we represent DRSs as a sequence of flat clauses and introduce a method to verify that produced DRSs are well-formed and interpretable. We compare models using characters and words as input and see (somewhat surprisingly) that the former performs better than the latter. We show that eliminating variable names from the output using De Bruijn indices increases parser performance. Adding silver training data boosts performance even further.

We propose a novel semantic tagging task, semtagging, tailored for the purpose of multilingual semantic parsing, and present the first tagger using deep residual networks (ResNets). Our tagger uses both word and character representations, and includes a novel residual bypass architecture. We evaluate the tagset both intrinsically on the new task of semantic tagging, as well as on Part-of-Speech (POS) tagging. Our system, consisting of a ResNet and an auxiliary loss function predicting our semantic tags, significantly outperforms prior results on English Universal Dependencies POS tagging (95.71% accuracy on UD v1.2 and 95.67% accuracy on UD v1.3).

We propose a method for learning semantic CCG parsers by projecting annotations via a parallel corpus. The method opens an avenue towards cheaply creating multilingual semantic parsers mapping open-domain text to formal meaning representations. A first cross-lingually learned Dutch (from English) semantic parser obtains f-scores ranging from 42.99% to 69.22% depending on the level of label informativity taken into account, compared to 58.40% to 78.88% for the underlying source-language system. These are promising numbers compared to state-of-the-art semantic parsing in open domains.

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.

Ellie Pavlick, Johan Bos, Malvina Nissim, Charley Beller, Benjamin Van Durme, Chris Callison-Burch. Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2015.

Tokenization is widely regarded as a solved problem due to the high accuracy that rulebased tokenizers achieve.But rule-based tokenizers are hard to maintain and their rules language specific.We show that highaccuracy word and sentence segmentation can be achieved by using supervised sequence labeling on the character level combined with unsupervised feature learning.We evaluated our method on three languages and obtained error rates of 0.27 ‰ (English), 0.35 ‰ (Dutch) and 0.76 ‰ (Italian) for our best models.

To make legal texts machine processable, the texts may be represented as linked documents, semantically tagged text, or translated to formal representations that can be automatically reasoned with. The paper considers the latter, which is key to testing consistency of laws, drawing inferences, and providing explanations relative to input. To translate laws to a form that can be reasoned with by a computer, sentences must be parsed and formally represented. The paper presents the state-of-the-art in automatic translation of law to a machine readable formal representation, provides corpora, outlines some key problems, and proposes tasks to address the problems.

Rayner Manny, Ann Hockey Beth, Bouillon Pierrette, Putting Linguistics into Speech Recognition. The Regulus Grammar Compiler. With contributions by Nikos Chatzichrisafis, Marianne Santaholma & Marianne Starlander. Foreword by Aravind K. Joshi. Appeared in the series CSLI Studies in Computational Linguistics (series edited by Ann Copestake). Stanford, California, CSLI. ISBN 1-57586-526-2 (paperback), xiv+305 pages. Price: US$25.00, £17.99. - Volume 14 Issue 1

Computational aspects of Van der Sandt's binding and accommodation theory (BAT) for presupposition projection and anaphora resolution are presented and discussed in this article. BAT is reformulated to meet requirements for computational implementation, which include operations on discourse representation structures (renaming and merging), the representation of presuppositions (allowing for selective binding and determining free and bound variables), and a formulation of the acceptability constraints imposed by BAT. An efficient presupposition resolution algorithm is presented, and several further improvements such as preferences for binding and accommodation are discussed and integrated in this algorithm. Finally, innovative use of first-order theorem provers to carry out consistency checking of discourse representations is investigated.

Godot is a mobile robot platform that serves as a testbed for the interface between a sophisticated low-level robot navigation and a symbolic high-level spoken dialogue system. The interesting feature of this combined system is that information flows in two directions: (1) the navigation system. supplies landmark; information from the cognitive map used for the interpretation of the user's utterances in the dialogue system; and (2) the semantic content of utterances analysed by the dialogue system are used to adjust probabilities about the robot's position in the navigation system.

Systems for spoken-language understanding can use prosodic information on the speech recognition side as well as the linguistic processing side. In the former case, prosody improves recognition accuracy and speed. In the latter case, it contributes to the computation of meaning. Interfacing prosodic processing to language analysis has so far been mainly concerned with speeding up the parsing process. The actual integration of prosodic information into the semantic part of a language understanding system, or into the transfer part of a translation system, has mostly been left aside. We describe how prosody has been used in the syntactic-semantic and transfer modules of the Verbmobil spoken dialogue translation system. On the syntactic-semantic side, prosody is currently used for the solution of three different problems: insertion of clause boundaries, selection of sentence mood (declarative, question, etc), and assignment of semantic focus. On the transfer side, the prosodic information...