Alongside its literal meaning, text also carries implicit social signals: information that is used by the reader to assign the author of the text a specific identity or make assumptions about the author’s character. The reader creates a mental image of the author which influences the interpretation of the presented information. This is especially relevant for argumentative text, where the credibility of the information might depend on who provides it. We therefore focus on the question: How do readers of an argument imagine its author? Using the ContArgA corpus, we study arguments annotated for convincingness and perceived author properties (level of education and Big Five personality traits). We find that annotators perceive an author to be similar to themselves when they agree with the stance of the argument. We also find that the envisioned personality traits and education level of the author are statistically significantly correlated with the argument’s convincingness. We conduct experiments with four generative LLMs and a RoBERTa-based regression model showing that LLMs do not replicate the annotators judgments. Argument convincingness can however provide a useful signal for modeling perceived author personality when it is explicitly used during training.

Emotions that somebody develops based on an argument do not only depend on the argument itself - they are also influenced by a subjective evaluation of the argument’s potential impact on the self. For instance, an argument to ban plastic bottles might cause fear of losing a job for a bottle industry worker, which lowers the convincingness – presumably independent of its content. While binary emotionality of arguments has been studied, such cognitive appraisal models have only been proposed in other subtasks of emotion analysis, but not in the context of arguments and their convincingness. To fill this research gap, we propose the Contextualized Argument Appraisal Framework to model the interplay between the sender, receiver, and argument. We adapt established appraisal models from psychology to argument mining, including argument pleasantness, familiarity, response urgency, and expected effort, as well as convincingness variables. To evaluate the framework and pave the way for computational modeling, we develop a novel role-playing-based annotation setup, mimicking real-world exposure to arguments. Participants disclose their emotion, explain the main cause, the argument appraisal, and the perceived convincingness. To consider the subjective nature of such annotations, we also collect demographic data and personality traits of both the participants and ask them to disclose the same variables for their perception of the argument sender. The analysis of the resulting corpus of 4000 annotations reveals that convincingness is positively correlated with positive emotions (e.g., trust) and negatively correlated with negative emotions (e.g., anger). The appraisal variables particularly point to the importance of the annotator’s familiarity with the argument.

The convincingness of an argument does not only depend on its structure (logos), the person who makes the argument (ethos), but also on the emotion that it causes in the recipient (pathos). While the overall intensity and categorical values of emotions in arguments have received considerable attention in the research community, we argue that the emotion an argument evokes in a recipient is subjective. It depends on the recipient’s goals, standards, prior knowledge, and stance. Appraisal theories lend themselves as a link between the subjective cognitive assessment of events and emotions. They have been used in event-centric emotion analysis, but their suitability for assessing argument convincingness remains unexplored. In this paper, we evaluate whether appraisal theories are suitable for emotion analysis in arguments by considering subjective cognitive evaluations of the importance and impact of an argument on its receiver. Based on the annotations in the recently published ContArgA corpus, we perform zero-shot prompting experiments to evaluate the importance of gold-annotated and predicted emotions and appraisals for the assessment of the subjective convincingness labels. We find that, while categorical emotion information does improve convincingness prediction, the improvement is more pronounced with appraisals. This work presents the first systematic comparison between emotion models for convincingness prediction, demonstrating the advantage of appraisals, providing insights for theoretical and practical applications in computational argumentation.

Emotion annotation in text is a challenging task that often yields low inter-annotator agreement. Missing context, differences in world knowledge and extra-linguistic factors such as the author’s identity influence how emotions are perceived. When the text does not provide sufficient information, details about the author may help resolve ambiguity. We test the hypothesis that providing annotators with demographic information reduces disagreement in emotion annotation. We compare one group of annotators who sees each text alongside demographic information about its author, with a group who sees only the text. We find in our study with 500 annotators and 250 texts that displaying demographic information about the author of the text does not improve agreement between annotators, nor does it improve agreement with the gold label. The only exception are cases where the emotion polarity (positive or negative) is unclear. We also find that annotators perform overall better at identifying the correct emotion label when it aligns with gender stereotypes. Zero-shot prompting experiments with large language models do resemble the human annotation experimental results. Our findings suggest that providing demographic information is not a straightforward remedy for ambiguity in emotion annotation and careful consideration is needed when incorporating such data.

Demographics and cultural background of annotators influence the labels they assign in text annotation – for instance, an elderly woman might find it offensive to read a message addressed to a “bro”, but a male teenager might find it appropriate. It is therefore important to acknowledge label variations to not under-represent members of a society. Two research directions developed out of this observation in the context of using large language models (LLM) for data annotations, namely (1) studying biases and inherent knowledge of LLMs and (2) injecting diversity in the output by manipulating the prompt with demographic information. We combine these two strands of research and ask the question to which demographics an LLM resorts to when no demographics is given. To answer this question, we evaluate which attributes of human annotators LLMs inherently mimic. Furthermore, we compare non-demographic conditioned prompts and placebo-conditioned prompts (e.g., “you are an annotator who lives in house number 5”) to demographics-conditioned prompts (“You are a 45 year old man and an expert on politeness annotation. How do you rate instance”). We study these questions for politeness and offensiveness annotations on the POPQUORN data set, a corpus created in a controlled manner to investigate human label variations based on demographics which has not been used for LLM-based analyses so far. We observe notable influences related to gender, race, and age in demographic prompting, which contrasts with previous studies that found no such effects.

We examine LMs’ competence of directional predicate entailments by supervised fine-tuning with prompts. Our analysis shows that contrary to their apparent success on standard NLI, LMs show limited ability to learn such directional inference; moreover, existing datasets fail to test directionality, and/or are infested by artefacts that can be learnt as proxy for entailments, yielding over-optimistic results. In response, we present BoOQA (Boolean Open QA), a robust multi-lingual evaluation benchmark for directional predicate entailments, extrinsic to existing training sets. On BoOQA, we establish baselines and show evidence of existing LM-prompting models being incompetent directional entailment learners, in contrast to entailment graphs, however limited by sparsity.

Predicate entailment detection is a crucial task for question-answering from text, where previous work has explored unsupervised learning of entailment graphs from typed open relation triples. In this paper, we present the first pipeline for building Chinese entailment graphs, which involves a novel high-recall open relation extraction (ORE) method and the first Chinese fine-grained entity typing dataset under the FIGER type ontology. Through experiments on the Levy-Holt dataset, we verify the strength of our Chinese entailment graph, and reveal the cross-lingual complementarity: on the parallel Levy-Holt dataset, an ensemble of Chinese and English entailment graphs outperforms both monolingual graphs, and raises unsupervised SOTA by 4.7 AUC points.

The training of NLP models often requires large amounts of labelled training data, which makes it difficult to expand existing models to new languages. While zero-shot cross-lingual transfer relies on multilingual word embeddings to apply a model trained on one language to another, Yarowski and Ngai (2001) propose the method of annotation projection to generate training data without manual annotation. This method was successfully used for the tasks of named entity recognition and coarse-grained entity typing, but we show that it is outperformed by zero-shot cross-lingual transfer when applied to the similar task of fine-grained entity typing. In our study of fine-grained entity typing with the FIGER type ontology for German, we show that annotation projection amplifies the English model’s tendency to underpredict level 2 labels and is beaten by zero-shot cross-lingual transfer on three novel test sets.

Fine-grained entity typing is important to tasks like relation extraction and knowledge base construction. We find however, that fine-grained entity typing systems perform poorly on general entities (e.g. “ex-president”) as compared to named entities (e.g. “Barack Obama”). This is due to a lack of general entities in existing training data sets. We show that this problem can be mitigated by automatically generating training data from WordNets. We use a German WordNet equivalent, GermaNet, to automatically generate training data for German general entity typing. We use this data to supplement named entity data to train a neural fine-grained entity typing system. This leads to a 10% improvement in accuracy of the prediction of level 1 FIGER types for German general entities, while decreasing named entity type prediction accuracy by only 1%.

This paper presents ongoing work on the construction and alignment of predicate entailment graphs in English and German. We extract predicate-argument pairs from large corpora of monolingual English and German news text and construct monolingual paraphrase clusters and entailment graphs. We use an aligned subset of entities to derive the bilingual alignment of entities and relations, and achieve better than baseline results on a translated subset of a predicate entailment data set (Levy and Dagan, 2016) and the German portion of XNLI (Conneau et al., 2018).