A Syntactically Constrained Bidirectional-Asynchronous Approach for Emotional Conversation Generation (D18-1)
Copied to clipboard
| Challenge: | Existing neural language models generate generic responses with poor logic and no emotion. |
| Approach: | They propose a syntactically constrained bidirectional-asynchronous approach for emotional conversation generation using pre-generated emotion keywords and topic keywords. |
| Outcome: | The proposed approach improves the diversity of responses and boosts logic and emotion compared with baselines. |
Similar Papers
Automatic Dialogue Generation with Expressed Emotions (N18-2)
Copied to clipboard
| Challenge: | a growing interest in neural dialogue generation systems is focusing on generating human-like responses based on past utterances . despite efforts, few consider putting restrictions on the response itself . authors present three models that concatenate the desired emotion with the source input . |
| Approach: | They propose three models that concatenate the desired emotion with the source input or push the emotion in the decoder. |
| Outcome: | The proposed model is more efficient than the previous models, but it lacks the emotion vector. |
Modelling Context Emotions using Multi-task Learning for Emotion Controlled Dialog Generation (2021.eacl-main)
Copied to clipboard
| Challenge: | Recent research has tackled this task using neural generative methods by augmenting emotion classes with the input sequences. |
| Approach: | They propose to use a self-attention based encoder and a decoder with dot product attention mechanism to generate a viable response with a specified emotion. |
| Outcome: | The proposed model outperforms baselines on automatic evaluation measures such as F1 and BLEU scores, thus resulting in more fluent and adequate responses. |
Constructing Emotional Consensus and Utilizing Unpaired Data for Empathetic Dialogue Generation (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing models for dialogue empathy focus on the emotion flow in one direction, from context to response. |
| Approach: | They propose a dual-generative model to construct emotional consensus and use unpaired data to produce pseudo paired empathetic samples. |
| Outcome: | The proposed model outperforms baseline models in producing coherent and empathetic responses. |
MojiTalk: Generating Emotional Responses at Scale (P18-1)
Copied to clipboard
| Challenge: | Existing studies on emotion-generating systems focus on small sets of labeled datasets. |
| Approach: | They propose to leverage Twitter data that are naturally labeled with emojis to generate emotional responses. |
| Outcome: | The proposed models can generate high-quality conversation responses in accordance with designated emotions. |
Generating More Interesting Responses in Neural Conversation Models with Distributional Constraints (D18-1)
Copied to clipboard
| Challenge: | Neural conversation models tend to generate safe, generic responses for most inputs . this is due to the limitations of likelihood-based decoding objectives in generation tasks with diverse outputs, such as conversation. |
| Approach: | They propose a distributional constraint approach that incorporates side information into the generated responses. |
| Outcome: | The proposed approach generates responses that are less generic without sacrificing plausibility. |
Affect-Driven Dialog Generation (N19-1)
Copied to clipboard
| Challenge: | Existing systems for end-to-end dialog generation focus on response quality without explicit control over affective content of the responses. |
| Approach: | They propose an affect-driven dialog system which generates emotional responses using a continuous representation of emotions. |
| Outcome: | The proposed system outperforms existing systems in terms of BLEU score and response diversity, and qualitative measures. |
Mixed Feelings: Natural Text Generation with Variable, Coexistent Affective Categories (P18-3)
Copied to clipboard
| Challenge: | a recent study has shown that language models which can generate emotional sentences are limited to one affective category out of a few. |
| Approach: | a new research proposal proposes a language model which can produce multiple emotions simultaneously. authors propose to use a long-term memory language model to allow for variation in multiple emotions. |
| Outcome: | a new language model allows for variation in multiple emotions simultaneously . the proposed model is based on a model of long-term memory . |
Empathetic and Emotionally Positive Conversation Systems with an Emotion-specific Query-Response Memory (2022.findings-emnlp)
Copied to clipboard
Zhiliang Tian, Yinliang Wang, Yiping Song, Chi Zhang, Dongkyu Lee, Yingxiu Zhao, Dongsheng Li, Nevin L. Zhang
| Challenge: | Existing emotional conversation systems output responses according to either a given emotion or the user’s emotion reflected in the input queries. |
| Approach: | They propose to generate empathetic responses catering to the user’s emotions while leading the conversation to be emotionally positive by abstracting the conversation corpus and extracting the different responding strategies for different users’ emotions and conversational topics into a memory. |
| Outcome: | The proposed model surpasses the baseline methods in appropriateness, diversity, and generating emotionally positive responses. |
Generating Responses with a Specific Emotion in Dialog (P19-1)
Copied to clipboard
| Challenge: | EmoDS can express emotions in both ways, but it is difficult to scale to large datasets. |
| Approach: | They propose an emotional dialog system that can express emotions in both ways . they use strong emotional words and neutral words to increase the intensity of emotions . |
| Outcome: | The proposed system performs better than baselines in BLEU, diversity and quality of emotional expression. |
Coherence Modeling of Asynchronous Conversations: A Neural Entity Grid Approach (P18-1)
Copied to clipboard
| Challenge: | Existing coherence models are not able to distinguish coherent discourses from incoherent ones. |
| Approach: | They propose a novel coherence model for written asynchronous conversations . they propose to lexicalize the model's entity transitions and extend it to asynchron conversations based on conversational structure . |
| Outcome: | The proposed model outperforms existing models on coherence assessment and thread reconstruction tasks. |