Empathy is essential in healthcare communication. We introduce an annotation approach that draws on well-established frameworks for clinical empathy and breaking bad news (BBN) conversations for considering the interactive dynamics of discourse relations. We construct Empathy in BBNs, a span-relation task dataset of simulated BBN conversations in German, using our annotation scheme, in collaboration with a large medical school to support research on educational tools for medical didactics. The annotation is based on 1) Pounds (2011)’s appraisal framework for clinical empathy, which is grounded in systemic functional linguistics, and 2) the SPIKES protocol for breaking bad news (Baile et al., 2000), commonly taught in medical didactics training. This approach presents novel opportunities to study clinical empathic behavior and enables the training of models to detect causal relations involving empathy, a highly desirable feature of systems that can provide feedback to medical professionals in training. We present illustrative examples, discuss applications of the annotation scheme, and insights we can draw from the framework.

Recent trends in natural language processing research and annotation tasks affirm a paradigm shift from the traditional reliance on a single ground truth to a focus on individual perspectives, particularly in subjective tasks. In scenarios where annotation tasks are meant to encompass diversity, models that solely rely on the majority class labels may inadvertently disregard valuable minority perspectives. This oversight could result in the omission of crucial information and, in a broader context, risk disrupting the balance within larger ecosystems. As the landscape of annotator modeling unfolds with diverse representation techniques, it becomes imperative to investigate their effectiveness with the fine-grained features of the datasets in view. This study systematically explores various annotator modeling techniques and compares their performance across seven corpora. From our findings, we show that the commonly used user token model consistently outperforms more complex models. We introduce a composite embedding approach and show distinct differences in which model performs best as a function of the agreement with a given dataset. Our findings shed light on the relationship between corpus statistics and annotator modeling performance, which informs future work on corpus construction and perspectivist NLP.

With growing interest in the use of large language models, it is becoming increasingly important to understand whose views they express. These models tend to generate output that conforms to majority opinion and are not representative of diverse views. As a step toward building models that can take differing views into consideration, we build a novel corpus of social judgements. We crowdsourced annotations of a subset of the Commonsense Norm Bank that contained numbers in the situation descriptions and asked annotators to replace the number with a range defined by a start and end value that, in their view, correspond to the given verdict. Our corpus contains unaggregated annotations and annotator demographics. We describe our annotation process for social judgements and will release our dataset to support future work on numerical reasoning and perspectivist approaches to natural language processing.

Research on psychological risk factors for suicide has developed for decades. However, combining explainable theory with modern data-driven language model approaches is non-trivial. In this study, we propose and evaluate methods for identifying language patterns aligned with theories of suicide risk by combining theory-driven suicidal archetypes with language model-based and relative entropy-based approaches. Archetypes are based on prototypical statements that evince risk of suicidality while relative entropy considers the ratio of how unusual both a risk-familiar and unfamiliar model find the statements. While both approaches independently performed similarly, we find that combining the two significantly improved the performance in the shared task evaluations, yielding our combined system submission with a BERTScore Recall of 0.906. Consistent with the literature, we find that titles are highly informative as suicide risk evidence, despite the brevity. We conclude that a combination of theory- and data-driven methods are needed in the mental health space and can outperform more modern prompt-based methods.

The potential of medical domain dialogue agents lies in their ability to provide patients with faster information access while enabling medical specialists to concentrate on critical tasks. However, the integration of large-language models (LLMs) into these agents presents certain limitations that may result in serious consequences. This paper investigates the challenges and risks of using GPT-3-based models for medical question-answering (MedQA). We perform several evaluations contextualized in terms of standard medical principles. We provide a procedure for manually designing patient queries to stress-test high-risk limitations of LLMs in MedQA systems. Our analysis reveals that LLMs fail to respond adequately to these queries, generating erroneous medical information, unsafe recommendations, and content that may be considered offensive.

Recent language models have been improved by the addition of external memory. Nearest neighbor language models retrieve similar contexts to assist in word prediction. The addition of locality levels allows a model to learn how to weight neighbors based on their relative location to the current text in source documents, and have been shown to further improve model performance. Nearest neighbor models have been explored for controllable generation but have not examined the use of locality levels. We present a novel approach for this purpose and evaluate it using automatic and human evaluation on politeness, formality, supportiveness, and toxicity textual data. We find that our model is successfully able to control style and provides a better fluency-style trade-off than previous work

This research contributes to the task of predicting empathy and personality traits within dialogue, an important aspect of natural language processing, as part of our experimental work for the WASSA 2023 Empathy and Emotion Shared Task. For predicting empathy, emotion polarity, and emotion intensity on turns within a dialogue, we employ adapters trained on social media interactions labeled with empathy ratings in a stacked composition with the target task adapters. Furthermore, we embed demographic information to predict Interpersonal Reactivity Index (IRI) subscales and Big Five Personality Traits utilizing BERT-based models. The results from our study provide valuable insights, contributing to advancements in understanding human behavior and interaction through text. Our team ranked 2nd on the personality and empathy prediction tasks, 4th on the interpersonal reactivity index, and 6th on the conversational task.

We build a system that leverages adapters, a light weight and efficient method for leveraging large language models to perform the task Em- pathy and Distress prediction tasks for WASSA 2022. In our experiments, we find that stacking our empathy and distress adapters on a pre-trained emotion lassification adapter performs best compared to full fine-tuning approaches and emotion feature concatenation. We make our experimental code publicly available

Personalized language models are designed and trained to capture language patterns specific to individual users. This makes them more accurate at predicting what a user will write. However, when a new user joins a platform and not enough text is available, it is harder to build effective personalized language models. We propose a solution for this problem, using a model trained on users that are similar to a new user. In this paper, we explore strategies for finding the similarity between new users and existing ones and methods for using the data from existing users who are a good match. We further explore the trade-off between available data for new users and how well their language can be modeled.

In this paper, we study the effect of commonsense and domain knowledge while generating responses in counseling conversations using retrieval and generative methods for knowledge integration. We propose a pipeline that collects domain knowledge through web mining, and show that retrieval from both domain-specific and commonsense knowledge bases improves the quality of generated responses. We also present a model that incorporates knowledge generated by COMET using soft positional encoding and masked self-attention. We show that both retrieved and COMET-generated knowledge improve the system’s performance as measured by automatic metrics and also by human evaluation. Lastly, we present a comparative study on the types of knowledge encoded by our system showing that causal and intentional relationships benefit the generation task more than other types of commonsense relations.

Recent language modeling performance has been greatly improved by the use of external memory. This memory encodes the context so that similar contexts can be recalled during decoding. This similarity depends on how the model learns to encode context, which can be altered to include other attributes, such as style. We construct and evaluate an architecture for this purpose, using corpora annotated for politeness, formality, and toxicity. Through extensive experiments and human evaluation we demonstrate the potential of our method to generate text while controlling style. We find that style-specific datastores improve generation performance, though results vary greatly across styles, and the effect of pretraining data and specific styles should be explored in future work.

We review the state of research on empathy in natural language processing and identify the following issues: (1) empathy definitions are absent or abstract, which (2) leads to low construct validity and reproducibility. Moreover, (3) emotional empathy is overemphasized, skewing our focus to a narrow subset of simplified tasks. We believe these issues hinder research progress and argue that current directions will benefit from a clear conceptualization that includes operationalizing cognitive empathy components. Our main objectives are to provide insight and guidance on empathy conceptualization for NLP research objectives and to encourage researchers to pursue the overlooked opportunities in this area, highly relevant, e.g., for clinical and educational sectors.

Large pre-trained neural language models have supported the effectiveness of many NLP tasks, yet are still prone to generating toxic language hindering the safety of their use. Using empathetic data, we improve over recent work on controllable text generation that aims to reduce the toxicity of generated text. We find we are able to dramatically reduce the size of fine-tuning data to 7.5-30k samples while at the same time making significant improvements over state-of-the-art toxicity mitigation of up to 3.4% absolute reduction (26% relative) from the original work on 2.3m samples, by strategically sampling data based on empathy scores. We observe that the degree of improvements is subject to specific communication components of empathy. In particular, the more cognitive components of empathy significantly beat the original dataset in almost all experiments, while emotional empathy was tied to less improvement and even underperforming random samples of the original data. This is a particularly implicative insight for NLP work concerning empathy as until recently the research and resources built for it have exclusively considered empathy as an emotional concept.

Studies on interpersonal conflict have a long history and contain many suggestions for conflict typology. We use this as the basis of a novel annotation scheme and release a new dataset of situations and conflict aspect annotations. We then build a classifier to predict whether someone will perceive the actions of one individual as right or wrong in a given situation. Our analyses include conflict aspects, but also generated clusters, which are human validated, and show differences in conflict content based on the relationship of participants to the author. Our findings have important implications for understanding conflict and social norms.

Instead of using a single ground truth for language processing tasks, several recent studies have examined how to represent and predict the labels of the set of annotators. However, often little or no information about annotators is known, or the set of annotators is small. In this work, we examine a corpus of social media posts about conflict from a set of 13k annotators and 210k judgements of social norms. We provide a novel experimental setup that applies personalization methods to the modeling of annotators and compare their effectiveness for predicting the perception of social norms. We further provide an analysis of performance across subsets of social situations that vary by the closeness of the relationship between parties in conflict, and assess where personalization helps the most.

We introduce a counseling dialogue system that seeks to assist counselors while they are learning and refining their counseling skills. The system generates counselors’reflections – i.e., responses that reflect back on what the client has said given the dialogue history. Our method builds upon the new generative pretrained transformer architecture and enhances it with context augmentation techniques inspired by traditional strategies used during counselor training. Through a set of comparative experiments, we show that the system that incorporates these strategies performs better in the reflection generation task than a system that is just fine-tuned with counseling conversations. To confirm our findings, we present a human evaluation study that shows that our system generates naturally-looking reflections that are also stylistically and grammatically correct.

In this paper, we introduce personalized word embeddings, and examine their value for language modeling. We compare the performance of our proposed prediction model when using personalized versus generic word representations, and study how these representations can be leveraged for improved performance. We provide insight into what types of words can be more accurately predicted when building personalized models. Our results show that a subset of words belonging to specific psycholinguistic categories tend to vary more in their representations across users and that combining generic and personalized word embeddings yields the best performance, with a 4.7% relative reduction in perplexity. Additionally, we show that a language model using personalized word embeddings can be effectively used for authorship attribution.

The ongoing COVID-19 pandemic has raised concerns for many regarding personal and public health implications, financial security and economic stability. Alongside many other unprecedented challenges, there are increasing concerns over social isolation and mental health. We introduce Expressive Interviewing – an interview-style conversational system that draws on ideas from motivational interviewing and expressive writing. Expressive Interviewing seeks to encourage users to express their thoughts and feelings through writing by asking them questions about how COVID-19 has impacted their lives. We present relevant aspects of the system’s design and implementation as well as quantitative and qualitative analyses of user interactions with the system. In addition, we conduct a comparative evaluation with a general purpose dialogue system for mental health that shows our system potential in helping users to cope with COVID-19 issues.

Word embeddings are usually derived from corpora containing text from many individuals, thus leading to general purpose representations rather than individually personalized representations. While personalized embeddings can be useful to improve language model performance and other language processing tasks, they can only be computed for people with a large amount of longitudinal data, which is not the case for new users. We propose a new form of personalized word embeddings that use demographic-specific word representations derived compositionally from full or partial demographic information for a user (i.e., gender, age, location, religion). We show that the resulting demographic-aware word representations outperform generic word representations on two tasks for English: language modeling and word associations. We further explore the trade-off between the number of available attributes and their relative effectiveness and discuss the ethical implications of using them.

Many NLP applications, such as biomedical data and technical support, have 10-100 million tokens of in-domain data and limited computational resources for learning from it. How should we train a language model in this scenario? Most language modeling research considers either a small dataset with a closed vocabulary (like the standard 1 million token Penn Treebank), or the whole web with byte-pair encoding. We show that for our target setting in English, initialising and freezing input embeddings using in-domain data can improve language model performance by providing a useful representation of rare words, and this pattern holds across several different domains. In the process, we show that the standard convention of tying input and output embeddings does not improve perplexity when initializing with embeddings trained on in-domain data.

We address the task of targeted sentiment as a means of understanding the sentiment that students hold toward courses and instructors, as expressed by students in their comments. We introduce a new dataset consisting of student comments annotated for targeted sentiment and describe a system that can both identify the courses and instructors mentioned in student comments, as well as label the students’ sentiment toward those entities. Through several comparative evaluations, we show that our system outperforms previous work on a similar task.