In the last five years, there has been a significant focus in Natural Language Processing (NLP) on developing larger Pretrained Language Models (PLMs) and introducing benchmarks such as SuperGLUE and SQuAD to measure their abilities in language understanding, reasoning, and reading comprehension. These PLMs have achieved impressive results on these benchmarks, even surpassing human performance in some cases. This has led to claims of superhuman capabilities and the provocative idea that certain tasks have been solved. In this position paper, we take a critical look at these claims and ask whether PLMs truly have superhuman abilities and what the current benchmarks are really evaluating. We show that these benchmarks have serious limitations affecting the comparison between humans and PLMs and provide recommendations for fairer and more transparent benchmarks.

Pre-trained language models (PLMs) have achieved great success in NLP and have recently been used for tasks in computational semantics. However, these tasks do not fully benefit from PLMs since meaning representations are not explicitly included. We introduce multilingual pre-trained language-meaning models based on Discourse Representation Structures (DRSs), including meaning representations besides natural language texts in the same model, and design a new strategy to reduce the gap between the pre-training and fine-tuning objectives. Since DRSs are language neutral, cross-lingual transfer learning is adopted to further improve the performance of non-English tasks. Automatic evaluation results show that our approach achieves the best performance on both the multilingual DRS parsing and DRS-to-text generation tasks. Correlation analysis between automatic metrics and human judgements on the generation task further validates the effectiveness of our model. Human inspection reveals that out-of-vocabulary tokens are the main cause of erroneous results.

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

Neural semantic parsers have obtained acceptable results in the context of parsing DRSs (Discourse Representation Structures). In particular models with character sequences as input showed remarkable performance for English. But how does this approach perform on languages with a different writing system, like Chinese, a language with a large vocabulary of characters? Does rule-based tokenisation of the input help, and which granularity is preferred: characters, or words? The results are promising. Even with DRSs based on English, good results for Chinese are obtained. Tokenisation offers a small advantage for English, but not for Chinese. Overall, characters are preferred as input, both for English and Chinese.

We present an end-to-end neural approach to generate English sentences from formal meaning representations, Discourse Representation Structures (DRSs). We use a rather standard bi-LSTM sequence-to-sequence model, work with a linearized DRS input representation, and evaluate character-level and word-level decoders. We obtain very encouraging results in terms of reference-based automatic metrics such as BLEU. But because such metrics only evaluate the surface level of generated output, we develop a new metric, ROSE, that targets specific semantic phenomena. We do this with five DRS generation challenge sets focusing on tense, grammatical number, polarity, named entities and quantities. The aim of these challenge sets is to assess the neural generator’s systematicity and generalization to unseen inputs.

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.

The 2020 Shared Task at the Conference for Computational Language Learning (CoNLL) was devoted to Meaning Representation Parsing (MRP) across frameworks and languages. Extending a similar setup from the previous year, five distinct approaches to the representation of sentence meaning in the form of directed graphs were represented in the English training and evaluation data for the task, packaged in a uniform graph abstraction and serialization; for four of these representation frameworks, additional training and evaluation data was provided for one additional language per framework. The task received submissions from eight teams, of which two do not participate in the official ranking because they arrived after the closing deadline or made use of additional training data. All technical information regarding the task, including system submissions, official results, and links to supporting resources and software are available from the task web site at: http://mrp.nlpl.eu

Discourse Representation Theory (DRT) is a formal account for representing the meaning of natural language discourse. Meaning in DRT is modeled via a Discourse Representation Structure (DRS), a meaning representation with a model-theoretic interpretation, which is usually depicted as nested boxes. In contrast, a directed labeled graph is a common data structure used to encode semantics of natural language texts. The paper describes the procedure of dressing up DRSs as directed labeled graphs to include DRT as a new framework in the 2020 shared task on Cross-Framework and Cross-Lingual Meaning Representation Parsing. Since one of the goals of the shared task is to encourage unified models for several semantic graph frameworks, the conversion procedure was biased towards making the DRT graph framework somewhat similar to other graph-based meaning representation frameworks.

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.

The AMR (Abstract Meaning Representation) formalism for representing meaning of natural language sentences puts emphasis on predicate-argument structure and was not designed to deal with scope and quantifiers. By extending AMR with indices for contexts and formulating constraints on these contexts, a formalism is derived that makes correct predictions for inferences involving negation and bound variables. The attractive core predicate-argument structure of AMR is preserved. The resulting framework is similar to the meaning representations of Discourse Representation Theory employed in the Parallel Meaning Bank.

Large crowdsourced datasets are widely used for training and evaluating neural models on natural language inference (NLI). Despite these efforts, neural models have a hard time capturing logical inferences, including those licensed by phrase replacements, so-called monotonicity reasoning. Since no large dataset has been developed for monotonicity reasoning, it is still unclear whether the main obstacle is the size of datasets or the model architectures themselves. To investigate this issue, we introduce a new dataset, called HELP, for handling entailments with lexical and logical phenomena. We add it to training data for the state-of-the-art neural models and evaluate them on test sets for monotonicity phenomena. The results showed that our data augmentation improved the overall accuracy. We also find that the improvement is better on monotonicity inferences with lexical replacements than on downward inferences with disjunction and modification. This suggests that some types of inferences can be improved by our data augmentation while others are immune to it.

Recently, sequence-to-sequence models have achieved impressive performance on a number of semantic parsing tasks. However, they often do not exploit available linguistic resources, while these, when employed correctly, are likely to increase performance even further. Research in neural machine translation has shown that employing this information has a lot of potential, especially when using a multi-encoder setup. We employ a range of semantic and syntactic resources to improve performance for the task of Discourse Representation Structure Parsing. We show that (i) linguistic features can be beneficial for neural semantic parsing and (ii) the best method of adding these features is by using multiple encoders.

The paper presents the IWCS 2019 shared task on semantic parsing where the goal is to produce Discourse Representation Structures (DRSs) for English sentences. DRSs originate from Discourse Representation Theory and represent scoped meaning representations that capture the semantics of negation, modals, quantification, and presupposition triggers. Additionally, concepts and event-participants in DRSs are described with WordNet synsets and the thematic roles from VerbNet. To measure similarity between two DRSs, they are represented in a clausal form, i.e. as a set of tuples. Participant systems were expected to produce DRSs in this clausal form. Taking into account the rich lexical information, explicit scope marking, a high number of shared variables among clauses, and highly-constrained format of valid DRSs, all these makes the DRS parsing a challenging NLP task. The results of the shared task displayed improvements over the existing state-of-the-art parser.

Meaning banking—creating a semantically annotated corpus for the purpose of semantic parsing or generation—is a challenging task. It is quite simple to come up with a complex meaning representation, but it is hard to design a simple meaning representation that captures many nuances of meaning. This paper lists some lessons learned in nearly ten years of meaning annotation during the development of the Groningen Meaning Bank (Bos et al., 2017) and the Parallel Meaning Bank (Abzianidze et al., 2017). The paper’s format is rather unconventional: there is no explicit related work, no methodology section, no results, and no discussion (and the current snippet is not an abstract but actually an introductory preface). Instead, its structure is inspired by work of Traum (2000) and Bender (2013). The list starts with a brief overview of the existing meaning banks (Section 1) and the rest of the items are roughly divided into three groups: corpus collection (Section 2 and 3, annotation methods (Section 4–11), and design of meaning representations (Section 12–30). We hope this overview will give inspiration and guidance in creating improved meaning banks in the future

We present the first open-source graphical annotation tool for combinatory categorial grammar (CCG), and the first set of detailed guidelines for syntactic annotation with CCG, for four languages: English, German, Italian, and Dutch. We also release a parallel pilot CCG treebank based on these guidelines, with 4x100 adjudicated sentences, 10K single-annotator fully corrected sentences, and 82K single-annotator partially corrected sentences.

Monotonicity reasoning is one of the important reasoning skills for any intelligent natural language inference (NLI) model in that it requires the ability to capture the interaction between lexical and syntactic structures. Since no test set has been developed for monotonicity reasoning with wide coverage, it is still unclear whether neural models can perform monotonicity reasoning in a proper way. To investigate this issue, we introduce the Monotonicity Entailment Dataset (MED). Performance by state-of-the-art NLI models on the new test set is substantially worse, under 55%, especially on downward reasoning. In addition, analysis using a monotonicity-driven data augmentation method showed that these models might be limited in their generalization ability in upward and downward reasoning.

Disambiguation of potentially idiomatic expressions involves determining the sense of a potentially idiomatic expression in a given context, e.g. determining that make hay in ‘Investment banks made hay while takeovers shone.’ is used in a figurative sense. This enables automatic interpretation of idiomatic expressions, which is important for applications like machine translation and sentiment analysis. In this work, we present an unsupervised approach for English that makes use of literalisations of idiom senses to improve disambiguation, which is based on the lexical cohesion graph-based method by Sporleder and Li (2009). Experimental results show that, while literalisation carries novel information, its performance falls short of that of state-of-the-art unsupervised methods.

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 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.

The Parallel Meaning Bank is a corpus of translations annotated with shared, formal meaning representations comprising over 11 million words divided over four languages (English, German, Italian, and Dutch). Our approach is based on cross-lingual projection: automatically produced (and manually corrected) semantic annotations for English sentences are mapped onto their word-aligned translations, assuming that the translations are meaning-preserving. The semantic annotation consists of five main steps: (i) segmentation of the text in sentences and lexical items; (ii) syntactic parsing with Combinatory Categorial Grammar; (iii) universal semantic tagging; (iv) symbolization; and (v) compositional semantic analysis based on Discourse Representation Theory. These steps are performed using statistical models trained in a semi-supervised manner. The employed annotation models are all language-neutral. Our first results are promising.

In this talk I will discuss the analysis of several semantic phenomena that need meaning representations that can describe attributes of propositional contexts. I will do this in a version of Discourse Representation Theory, using a universal semantic tagset developed as part of a project that aims to produce a large meaning bank (a semantically-annotated corpus) for four languages (English, Dutch, German and Italian).

We evaluate a semantic parser based on a character-based sequence-to-sequence model in the context of the SemEval-2017 shared task on semantic parsing for AMRs. With data augmentation, super characters, and POS-tagging we gain major improvements in performance compared to a baseline character-level model. Although we improve on previous character-based neural semantic parsing models, the overall accuracy is still lower than a state-of-the-art AMR parser. An ensemble combining our neural semantic parser with an existing, traditional parser, yields a small gain in performance.

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.

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).

From a purely theoretical point of view, it makes sense to approach recognizing textual entailment (RTE) with the help of logic. After all, entailment matters are all about logic. In practice, only few RTE systems follow the bumpy road from words to logic. This is probably because it requires a combination of robust, deep semantic analysis and logical inference—and why develop something with this complexity if you perhaps can get away with something simpler? In this article, with the help of an RTE system based on Combinatory Categorial Grammar, Discourse Representation Theory, and first-order theorem proving, we make an empirical assessment of the logic-based approach. High precision paired with low recall is a key characteristic of this system. The bottleneck in achieving high recall is the lack of a systematic way to produce relevant background knowledge. There is a place for logic in RTE, but it is (still) overshadowed by the knowledge acquisition problem.

What would be a good method to provide a large collection of semantically annotated texts with formal, deep semantics rather than shallow? We argue that a bootstrapping approach comprising state-of-the-art NLP tools for parsing and semantic interpretation, in combination with a wiki-like interface for collaborative annotation of experts, and a game with a purpose for crowdsourcing, are the starting ingredients for fulfilling this enterprise. The result is a semantic resource that anyone can edit and that integrates various phenomena, including predicate-argument structure, scope, tense, thematic roles, rhetorical relations and presuppositions, into a single semantic formalism: Discourse Representation Theory. Taking texts rather than sentences as the units of annotation results in deep semantic representations that incorporate discourse structure and dependencies. To manage the various (possibly conflicting) annotations provided by experts and non-experts, we introduce a method that stores ``Bits of Wisdom'' in a database as stand-off annotations.

What’s the best way to assess the performance of a semantic component in an NLP system? Tradition in NLP evaluation tells us that comparing output against a gold standard is a good idea. To define a gold standard, one first needs to decide on the representation language, and in many cases a first-order language seems a good compromise between expressive power and efficiency. Secondly, one needs to decide how to represent the various semantic phenomena, in particular the depth of analysis of quantification, plurals, eventualities, thematic roles, scope, anaphora, presupposition, ellipsis, comparatives, superlatives, tense, aspect, and time-expressions. Hence it will be hard to come up with an annotation scheme unless one permits different level of semantic granularity. The alternative is a theory-neutral black-box type evaluation where we just look at how systems react on various inputs. For this approach, we can consider the well-known task of recognising textual entailment, or the lesser-known task of textual model checking. The disadvantage of black-box methods is that it is difficult to come up with natural data that cover specific semantic phenomena.