Papers by Emily Dinan
Queens are Powerful too: Mitigating Gender Bias in Dialogue Generation (2020.emnlp-main)
Copied to clipboard
| Challenge: | Social biases present in data are often directly reflected in the predictions of models trained on that data. |
| Approach: | They analyze gender bias in dialogue data and propose techniques to mitigate it . they use counterfactual data augmentation, targeted data collection, and bias controlled training . |
| Outcome: | The proposed techniques mitigate gender bias by balancing genderedness of generated dialogue utterances. |
Multi-Dimensional Gender Bias Classification (2020.emnlp-main)
Copied to clipboard
| Challenge: | a novel framework decomposes gender bias in text along several pragmatic and semantic dimensions . language is a primary means by which people communicate, express identities and categorize themselves . unwanted gender biases can affect downstream applications, leading to poor user experiences . |
| Approach: | They propose a framework that decomposes gender bias in text along several dimensions . they annotate eight large scale datasets with gender information and collect a benchmark . |
| Outcome: | The proposed framework decomposes gender bias in text along several pragmatic and semantic dimensions. |
Reducing Conversational Agents’ Overconfidence Through Linguistic Calibration (2022.tacl-1)
Copied to clipboard
| Challenge: | Neural generative open-domain english-language dialogue agents are currently unsuitable for applications other than entertainement and research. |
| Approach: | They propose to incorporate metacognitive features into the training of a controllable generation model to improve likelihood of correctness. |
| Outcome: | The proposed model improves likelihood of correctness by incorporating metacognitive features into the training of a controllable generation model. |
Recipes for Building an Open-Domain Chatbot (2021.eacl-main)
Copied to clipboard
Stephen Roller, Emily Dinan, Naman Goyal, Da Ju, Mary Williamson, Yinhan Liu, Jing Xu, Myle Ott, Eric Michael Smith, Y-Lan Boureau, Jason Weston
| Challenge: | Existing work shows that scaling models in the number of parameters and the size of the data they are trained on gives improved results, but other factors are important. |
| Approach: | They propose to build open-domain chatbots that can be scaled to improve their performance . they use a blend of cognitive and cognitive skills to build a model that combines these skills . |
| Outcome: | The proposed models outperform existing approaches in multi-turn dialogue on engagingness and humanness measurements. |
Adversarial NLI: A New Benchmark for Natural Language Understanding (2020.acl-main)
Copied to clipboard
| Challenge: | a new large-scale NLI benchmark dataset is presented to test models on a variety of popular NLIs. |
| Approach: | They propose a large-scale NLI benchmark dataset that is iteratively compared with a human-and-model-in-the-loop procedure. |
| Outcome: | The proposed method can be applied in a never-ending learning scenario, becoming a moving target for NLU, rather than a static benchmark that will quickly saturate. |
Dialogue in the Wild: Learning from a Deployed Role-Playing Game with Humans and Bots (2021.findings-acl)
Copied to clipboard
| Challenge: | prevailing paradigm in natural language processing research is to build a fixed dataset and freeze it, without any ability for the model to interact with humans using language at training time at all. |
| Approach: | They build and deploy a role-playing game where players converse with learning agents situated in an open-domain fantasy world. |
| Outcome: | The proposed game enables human players to learn from human conversations and improves on their models. |
The Dialogue Dodecathlon: Open-Domain Knowledge and Image Grounded Conversational Agents (2020.acl-main)
Copied to clipboard
| Challenge: | a set of 12 tasks that measure if a conversational agent can communicate engagingly with personality and empathy, ask questions, answer questions by utilizing knowledge resources, and perceive and converse about images. |
| Approach: | They propose a set of 12 tasks that measure if a conversational agent can communicate engagingly with personality and empathy . they use large dialogue datasets to multi-task and obtain state-of-the-art results . |
| Outcome: | The proposed model improves over a BERT pre-trained model on large dialogue datasets and provides state-of-the-art results on many of the tasks. |
Learning to Speak and Act in a Fantasy Text Adventure Game (D19-1)
Copied to clipboard
Jack Urbanek, Angela Fan, Siddharth Karamcheti, Saachi Jain, Samuel Humeau, Emily Dinan, Tim Rocktäschel, Douwe Kiela, Arthur Szlam, Jason Weston
| Challenge: | Existing studies on grounded dialogue use only statistical regularities of text data, without explicit understanding of the world that the text describes. |
| Approach: | They propose a large-scale crowdsourced text adventure game as a research platform for studying grounded dialogue. |
| Outcome: | The proposed game allows agents to perceive, emote, and act whilst conducting dialogue with other agents. |
Build it Break it Fix it for Dialogue Safety: Robustness from Adversarial Human Attack (D19-1)
Copied to clipboard
| Challenge: | Detecting offensive language in the context of a dialogue is an increasingly important application of natural language processing. |
| Approach: | They propose to train a model to be robust to such attacks by iterative build it, break it, fix it scheme with humans and models in the loop. |
| Outcome: | The proposed model is significantly more robust to such human attacks than previous systems. |
When Life Gives You Lemons, Make Cherryade: Converting Feedback from Bad Responses into Good Labels (2024.naacl-long)
Copied to clipboard
| Challenge: | Existing dialogue models are primarily trained on human-human conversations . thumb ups/downs and gold corrections are often sparse in real-life deployment settings . |
| Approach: | They propose a framework to make use of binary and free-form textual human feedback. |
| Outcome: | The proposed framework improves the final dialogue model by using model-corrected replies. |
BTS: Harmonizing Specialized Experts into a Generalist LLM (2025.emnlp-main)
Copied to clipboard
Qizhen Zhang, Prajjwal Bhargava, Chloe Bi, Chris X. Cai, Jakob Nicolaus Foerster, Jeremy Fu, Punit Singh Koura, Ruan Silva, Sheng Shen, Emily Dinan, Suchin Gururangan, Mike Lewis
| Challenge: | Branch-Train-Stitch (BTS) is an efficient and flexible training algorithm for combining independently trained large language model (LLM) experts into a single, capable generalist model. |
| Approach: | They propose an efficient and flexible training algorithm for combining large language model (LLM) experts into a single, capable generalist model using lightweight stitch layers. |
| Outcome: | The proposed model can generalize to new domains despite being frozen . it yields the best generalist performance on a variety of downstream tasks, retaining the specialized capabilities of each of the experts. |
AutoReply: Detecting Nonsense in Dialogue with Discriminative Replies (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing models for dialogue detection make many errors in their own messages . a dataset of long dialogues richly grounded in the game state contains many errors . |
| Approach: | They propose to use an annotated dialogue dataset to generate automatic responses for dialogue models. |
| Outcome: | The proposed model outperforms handcrafted replies and performs on par with supervised learning approaches. |
Bot-Adversarial Dialogue for Safe Conversational Agents (2021.naacl-main)
Copied to clipboard
| Challenge: | a new method for evaluating chatbot safety is proposed to mimic human-generated data . a bot-adversarial dialogue model learns undesirable features from this data, a study finds . |
| Approach: | They propose a human-and-model-in-the-loop framework for evaluating toxicity of chatbots . they propose two methods for safe conversational agents by either training on data or ”baking-in” safety to the generative model itself. |
| Outcome: | The proposed methods are safer than existing models while maintaining usability metrics, the authors say . they show that the proposed methods can be used to make safer models with human-model interactions . |
SafetyKit: First Aid for Measuring Safety in Open-domain Conversational Systems (2022.acl-long)
Copied to clipboard
| Challenge: | Several studies discuss the potential harms and benefits of large language models (LLMs) large neural models can replicate and even amplify negative, stereotypical, and derogatory associations in the data. |
| Approach: | They propose to use a first aid kit to assess the safety of conversational AI in various settings . they propose several future directions and discuss ethical considerations . |
| Outcome: | The proposed tools can provide estimates of the relative safety of systems in various settings, but they still have several shortcomings. |
Personalizing Dialogue Agents: I have a dog, do you have pets too? (P18-1)
Copied to clipboard
| Challenge: | chit-chat models lack specificity, do not display a consistent personality and are often not very captivating. |
| Approach: | They propose to train chit-chat models to condition on profile information and profile information about the interlocutors. |
| Outcome: | The proposed model can predict profile information about the interlocutors based on the data . the proposed model is able to generate meaningful responses in a chit-chat setting . |