Papers by Charles Welch
Mitigating Toxic Degeneration with Empathetic Data: Exploring the Relationship Between Toxicity and Empathy (2022.naacl-main)
Copied to clipboard
| Challenge: | Recent work on controllable text generation has shown promise in successfully altering such text attributes. |
| Approach: | They propose to use empathetic data to reduce the toxicity of generated text by strategically sampling data based on empathy scores. |
| Outcome: | The proposed model significantly reduces the size of fine-tuning data to 7.5-30k samples while making significant improvements over state-of-the-art toxicity mitigation. |
Compositional Demographic Word Embeddings (2020.emnlp-main)
Copied to clipboard
| Challenge: | Word embeddings are usually derived from corpora containing text from many individuals . however, they cannot account for user-specific word preferences, such as using the same word in different ways across contexts. |
| Approach: | They 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. |
| Outcome: | The proposed representations outperform generic representations on two English language tasks. |
Knowledge Enhanced Reflection Generation for Counseling Dialogues (2022.acl-long)
Copied to clipboard
| Challenge: | Using retrieval and generative methods, we generate responses using commonsense and domain knowledge. |
| Approach: | They propose a pipeline that collects domain knowledge through web mining and a model that incorporates knowledge generated by COMET using soft positional encoding and masked self-attention. |
| Outcome: | The proposed pipeline collects domain knowledge through web mining and incorporates knowledge generated by COMET using soft positional encoding and masked self-attention. |
Appraisal Framework for Clinical Empathy: A Novel Application to Breaking Bad News Conversations (2024.lrec-main)
Copied to clipboard
| Challenge: | Empathy is essential in healthcare communication. |
| Approach: | They propose an annotation approach that draws on well-established frameworks for clinical empathy and breaking bad news conversations for considering the dynamic dynamics of discourse relations. |
| Outcome: | The proposed model can be used to train models to detect causal relations involving empathy, a feature of systems that can provide feedback to medical professionals in training. |
Exploring the Value of Personalized Word Embeddings (2020.coling-main)
Copied to clipboard
| Challenge: | a subset of words belonging to specific psycholinguistic categories vary more in their representations across users . combining generic and personalized word embeddings yields the best performance . |
| Approach: | They propose personalized word embeddings and compare their performance to generic ones . they show that personalized word representations can be leveraged for improved performance . |
| Outcome: | The proposed model can be used for authorship attribution. |
Corpus Considerations for Annotator Modeling and Scaling (2024.naacl-long)
Copied to clipboard
| Challenge: | Recent trends in natural language processing and annotation tasks emphasize individual perspectives . annotator models that rely on a single ground truth may disregard valuable minority perspectives omissions . |
| Approach: | They propose a composite embedding approach to investigate annotator modeling techniques . they show that the commonly used user token model consistently outperforms more complex models . |
| Outcome: | The proposed model outperforms more complex models on a given dataset. |
Exploring Self-Identified Counseling Expertise in Online Support Forums (2021.findings-acl)
Copied to clipboard
Allison Lahnala, Yuntian Zhao, Charles Welch, Jonathan K. Kummerfeld, Lawrence C An, Kenneth Resnicow, Rada Mihalcea, Verónica Pérez-Rosas
| Challenge: | Increasing number of people engage in online health forums, making it important to understand the quality of the advice they receive. |
| Approach: | They examine the role of expertise in responses to help-seeking posts . they find that a classifier can distinguish between peer and self-identified mental health professionals' interactions . |
| Outcome: | The findings show that experts' language use differs between groups, and that their comments engage the support-seeker further. |
Unifying Data Perspectivism and Personalization: An Application to Social Norms (2022.emnlp-main)
Copied to clipboard
| Challenge: | Obtaining a single ground truth is not possible or necessary for subjective tasks. |
| Approach: | They propose a set of personalization methods to model annotators and compare their effectiveness for predicting social norms. |
| Outcome: | The proposed model outperforms existing models and compares performance across subsets of social situations that vary by the closeness of the relationship between parties in conflict. |
Improving Low Compute Language Modeling with In-Domain Embedding Initialisation (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to train language models on in-domain data are limited. |
| Approach: | They propose to initialise and freeze in-domain embeddings to provide a useful representation of rare words in English . they find that the standard configuration is not optimal when rare words are present . |
| Outcome: | The proposed approach improves language modeling by providing a useful representation of rare words in English. |
Perspective Taking through Generating Responses to Conflict Situations (2024.findings-acl)
Copied to clipboard
| Challenge: | Language models struggle to understand and explain the beliefs of others, despite improving performance on a wide variety of tasks. |
| Approach: | They propose to modify the social-chem-101 corpus to allow for perspective-taking, the process of conceptualizing the point of view of another person. |
| Outcome: | The proposed models outperform the recent models conditioned on self-disclosures with high similarity to the conflict situation. |
A Critical Reflection and Forward Perspective on Empathy and Natural Language Processing (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Empathy recognition and empathetic response generation tasks are well-established research directions, but there is little clarity on what empathy is and how it is being operationalized. |
| Approach: | They argue that current directions will benefit from a clear conceptualization that includes operationalizing cognitive empathy components. |
| Outcome: | The proposed framework will help to define and operationalize empathy in natural language processing. |
World Knowledge for Abstract Meaning Representation Parsing (L18-1)
Copied to clipboard
| Challenge: | Abstract Meaning Representation (AMR) parsers are based on annotated graphs, but there is still room for improvement . |
| Approach: | They examine the role played by world knowledge in parsing errors in a state-of-the-art parser . they examine the effects of different types of world knowledge on parsers . |
| Outcome: | The proposed model improves on multiple fine-grained metrics, including a 6% increase in named entity F-score, and provides insight into the potential of world knowledge for future work in Abstract Meaning Representation parsing. |
Examining the Utility of Self-disclosure Types for Modeling Annotators of Social Norms (2026.findings-eacl)
Copied to clipboard
| Challenge: | Recent work has explored the use of personal information in the form of persona sentences to improve modeling of individual characteristics and prediction of annotator labels for subjective tasks. |
| Approach: | They categorize self-disclosures and use them to build annotator models for predicting judgments of social norms by analyzing comments from original post. |
| Outcome: | The proposed model improves the model and its ability to predict annotator labels. |
Leveraging Similar Users for Personalized Language Modeling with Limited Data (2022.acl-long)
Copied to clipboard
| Challenge: | Recent work suggests that personalized models are more accurate for individual users than one-size-fits-all solutions. |
| Approach: | They propose a model trained on users that are similar to a new user to find similarity between new and existing users. |
| Outcome: | The proposed model can predict what a user will write when they join a platform and not enough text is available. |
The Practical Impacts of Theoretical Constructs on Empathy Modeling (2025.emnlp-main)
Copied to clipboard
| Challenge: | Empathy operationalizations in NLP are varied, with some having specific behaviors and properties, while others are more abstract. |
| Approach: | They analyze the transfer performance of empathy models adapted to empathy tasks with different theoretical groundings and characterize them as direct, abstract, or adjacent. |
| Outcome: | The proposed models show that they are more transferable than other models. |