As a core cognitive skill that enables the transferability of information across domains, analogical reasoning has been extensively studied for both humans and computational models. However, while cognitive theories of analogy often focus on narratives and study the distinction between surface, relational, and system similarities, existing work in natural language processing has a narrower focus as far as relational analogies between word pairs. This gap brings a natural question: can state-of-the-art large language models (LLMs) detect system analogies between narratives? To gain insight into this question and extend word-based relational analogies to relational system analogies, we devise a comprehensive computational framework that operationalizes dominant theories of analogy, using narrative elements to create surface and system mappings. Leveraging the interplay between these mappings, we create a binary task and benchmark for Analogical Reasoning on Narratives (ARN), covering four categories of far (cross-domain)/near (within-domain) analogies and disanalogies. We show that while all LLMs can largely recognize near analogies, even the largest ones struggle with far analogies in a zero-shot setting, with GPT4.0 scoring below random. Guiding the models through solved examples and Chain-of-Thought reasoning enhances their analogical reasoning ability. Yet, since even in the few-shot setting, the best model only performs halfway between random and humans, ARN opens exciting directions for computational analogical reasoners.

In this paper, we present the outcome of a structural linguistic analysis performed on a referentially grounded FrameNet dataset. In this dataset, multiple Dutch events are referenced by multiple co-referential Dutch news texts. Mentions in those documents are annotated with respect to their referential grounding (i.e., links to structured Wikidata), and their conceptual representation (i.e., frames). Provided with each document’s temporal reporting distance, we selected documents for two events - the Utrecht shooting and MH17 - and performed an analysis in which we tracked the events’ participants over time in both their focalization (number of mentions) and their framing (distribution of frame element labels). This way, we use the carefully collected and annotated data to schematize shifts in focalization and perspectivization of the participants as a result of the constantly developing narrative surrounding the events. This novel type of linguistic research involves reference to the real-world referents and takes into account storytelling in news streams.

This paper discusses the re-usibility of existing approaches, tools and automatic techniques for the annotation and detection of events in a challenging variant of centuries old Dutch written in the archives of the Dutch East India Company. We describe our annotation process and provide a thorough analysis of different versions of manually annotated data and the first automatic results from two fine-tuned Language Models. Through the analysis of this complete process, the paper studies two things: to what extent we can use NLP theories and tasks formulated for modern English to formulate an annotation task for Early Modern Dutch and to what extent we can use NLP models and tools built for modern Dutch (and other languages) on Early Modern Dutch. We believe these analyses give us insight into how to deal with the large variation language showcases in describing events, and how this variation may differ accross domains. We release the annotation guidelines, annotated data, and code.

In this paper, we investigate automatic detection of subtle semantic shifts between social communities of different political convictions in Dutch and English. We perform a methodological study comparing methods using static and contextualized language models. We investigate the impact of specializing contextualized models through fine-tuning on target corpora, word sense disambiguation and sentiment. We furthermore propose a new approach using masked token prediction, that relies on behavioral information, specifically the most probable substitutions, instead of geometrical comparison of representations. Our results show that methods using static models and our masked token prediction method can detect differences in connotation of politically loaded terms, whereas methods that rely on measuring the distance between contextualized representations are not providing clear signals, even in synthetic scenarios of extreme shifts.

Bias elimination and recent probing studies attempt to remove specific information from embedding spaces. Here it is important to remove as much of the target information as possible, while preserving any other information present. INLP is a popular recent method which removes specific information through iterative nullspace projections.Multiple iterations, however, increase the risk that information other than the target is negatively affected.We introduce two methods that find a single targeted projection: Mean Projection (MP, more efficient) and Tukey Median Projection (TMP, with theoretical guarantees). Our comparison between MP and INLP shows that (1) one MP projection removes linear separability based on the target and (2) MP has less impact on the overall space.Further analysis shows that applying random projections after MP leads to the same overall effects on the embedding space as the multiple projections of INLP. Applying one targeted (MP) projection hence is methodologically cleaner than applying multiple (INLP) projections that introduce random effects.

Topological Data Analysis (TDA) focuses on the inherent shape of (spatial) data. As such, it may provide useful methods to explore spatial representations of linguistic data (embeddings) which have become central in NLP. In this paper we aim to introduce TDA to researchers in language technology. We use TDA to represent document structure as so-called story trees. Story trees are hierarchical representations created from semantic vector representations of sentences via persistent homology. They can be used to identify and clearly visualize prominent components of a story line. We showcase their potential by using story trees to create extractive summaries for news stories.

Computational linguistic research on language change through distributional semantic (DS) models has inspired researchers from fields such as philosophy and literary studies, who use these methods for the exploration and comparison of comparatively small datasets traditionally analyzed by close reading. Research on methods for small data is still in early stages and it is not clear which methods achieve the best results. We investigate the possibilities and limitations of using distributional semantic models for analyzing philosophical data by means of a realistic use-case. We provide a ground truth for evaluation created by philosophy experts and a blueprint for using DS models in a sound methodological setup. We compare three methods for creating specialized models from small datasets. Though the models do not perform well enough to directly support philosophers yet, we find that models designed for small data yield promising directions for future work.

Semantic annotation tasks contain ambiguity and vagueness and require varying degrees of world knowledge. Disagreement is an important indication of these phenomena. Most traditional evaluation methods, however, critically hinge upon the notion of inter-annotator agreement. While alternative frameworks have been proposed, they do not move beyond agreement as the most important indicator of quality. Critically, evaluations usually do not distinguish between instances in which agreement is expected and instances in which disagreement is not only valid but desired because it captures the linguistic and cognitive phenomena in the data. We attempt to overcome these limitations using the example of a dataset that provides semantic representations for diagnostic experiments on language models. Ambiguity, vagueness, and difficulty are not only highly relevant for this use-case, but also play an important role in other types of semantic annotation tasks. We establish an additional, agreement-independent quality metric based on answer-coherence and evaluate it in comparison to existing metrics. We compare against a gold standard and evaluate on expected disagreement. Despite generally low agreement, annotations follow expected behavior and have high accuracy when selected based on coherence. We show that combining different quality metrics enables a more comprehensive evaluation than relying exclusively on agreement.

What do powerful models of word mean- ing created from distributional data (e.g. Word2vec (Mikolov et al., 2013) BERT (Devlin et al., 2019) and ELMO (Peters et al., 2018)) represent? What causes words to be similar in the semantic space? What type of information is lacking? This thesis proposal presents a framework for investigating the information encoded in distributional semantic models. Several analysis methods have been suggested, but they have been shown to be limited and are not well understood. This approach pairs observations made on actual corpora with insights obtained from data manipulation experiments. The expected outcome is a better understanding of (1) the semantic information we can infer purely based on linguistic co-occurrence patterns and (2) the potential of distributional semantic models to pick up linguistic evidence.

This paper proposes a framework for investigating which types of semantic properties are represented by distributional data. The core of our framework consists of relations between concepts and properties. We provide hypotheses on which properties are reflected in distributional data or not based on the type of relation. We outline strategies for creating a dataset of positive and negative examples for various semantic properties, which cannot easily be separated on the basis of general similarity (e.g. fly: seagull, penguin). This way, a distributional model can only distinguish between positive and negative examples through evidence for a target property. Once completed, this dataset can be used to test our hypotheses and work towards data-derived interpretable representations.

Studying conceptual change using embedding models has become increasingly popular in the Digital Humanities community while critical observations about them have received less attention. This paper investigates what the impact of known pitfalls can be on the conclusions drawn in a digital humanities study through the use case of “Racism”. In addition, we suggest an approach for modeling a complex concept in terms of words and relations representative of the conceptual system. Our results show that different models created from the same data yield different results, but also indicate that using different model architectures, comparing different corpora and comparing to control words and relations can help to identify which results are solid and which may be due to artefact. We propose guidelines to conduct similar studies, but also note that more work is needed to fully understand how we can distinguish artefacts from actual conceptual changes.

This paper presents an approach for investigating the nature of semantic information captured by word embeddings. We propose a method that extends an existing human-elicited semantic property dataset with gold negative examples using crowd judgments. Our experimental approach tests the ability of supervised classifiers to identify semantic features in word embedding vectors and compares this to a feature-identification method based on full vector cosine similarity. The idea behind this method is that properties identified by classifiers, but not through full vector comparison are captured by embeddings. Properties that cannot be identified by either method are not. Our results provide an initial indication that semantic properties relevant for the way entities interact (e.g. dangerous) are captured, while perceptual information (e.g. colors) is not represented. We conclude that, though preliminary, these results show that our method is suitable for identifying which properties are captured by embeddings.

This paper presents the two systems submitted by the meaning space team in Task 10 of the SemEval competition 2018 entitled Capturing discriminative attributes. The systems consist of combinations of approaches exploiting explicitly encoded knowledge about concepts in WordNet and information encoded in distributional semantic vectors. Rather than aiming for high performance, we explore which kind of semantic knowledge is best captured by different methods. The results indicate that WordNet glosses on different levels of the hierarchy capture many attributes relevant for this task. In combination with exploiting word embedding similarities, this source of information yielded our best results. Our best performing system ranked 5th out of 13 final ranks. Our analysis yields insights into the different kinds of attributes represented by different sources of knowledge.