Learning to Control the Specificity in Neural Response Generation (P18-1)

Copied to clipboard

Challenge: Existing generative conversational models tend to favor general and trivial responses which appear frequently.
Approach: They propose a controlled response generation mechanism to handle different utterance-response relationships in terms of specificity.
Outcome: The proposed model outperforms state-of-the-art models under automatic and human evaluations.

Similar Papers

Consistent Response Generation with Controlled Specificity (2020.findings-emnlp)

Copied to clipboard

Challenge: Existing methods to generate fluent responses generate inconsistent responses . we use a sequence-to-sequence model to generate specific responses based on a co-occurrence degree .
Approach: They propose a method to control the specificity of responses while maintaining the consistency with the utterances.
Outcome: The proposed method produces highly consistent responses in open-domain dialogues . it can generate fluent responses while maintaining the consistency with the utterances compared to the conventional model .
Linguistically-Informed Specificity and Semantic Plausibility for Dialogue Generation (N19-1)

Copied to clipboard

Challenge: Past work has focused on word frequency-based approaches to improving specificity, such as penalizing responses with only common words.
Approach: They propose to rerank a sequence-to-sequence model to improve the informativeness, reasonableness, and grammatically of responses by using externally-trained classifiers targeting each of these factors.
Outcome: The proposed model improves the informativeness, reasonableness, and grammatically of responses.
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.
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.
Don’t Change Me! User-Controllable Selective Paraphrase Generation (2021.eacl-main)

Copied to clipboard

Challenge: a new technique allows paraphrase generation to be user-controlled . a user looking for cheap hotels in New York would not find the other answer helpful .
Approach: They propose a method that provides a user with explicit tags that can be placed around any arbitrary segment of text to mean "don't change me!" they propose allowing user-controllable paraphrase generation by fine-tuning model that exhibits this behavior .
Outcome: The proposed technique is language agnostic and tested in English and Chinese.
Explicit Use of Topicality in Dialogue Response Generation (2022.naacl-srw)

Copied to clipboard

Challenge: Existing chat dialogue systems only implicitly consider the topic given the context, but not explicitly.
Approach: They propose a dialogue system that responds appropriately following the topic by selecting the entity with the highest “topicality” they define the entity as a noun or compound nouns, and topicality as the degree of speaker awareness directed toward each entity in the dialogue context.
Outcome: The proposed system can follow the topic more than existing systems that only consider the context .
Adaptive Parameterization for Neural Dialogue Generation (D19-1)

Copied to clipboard

Challenge: Existing models of open-domain dialogue generate responses based on sequence-to-sequence paradigms.
Approach: They propose an Adaptive Neural Dialogue generation model which manages various conversations with conversation-specific parameterization.
Outcome: The proposed model performs better on a large-scale conversational dataset.
An Auto-Encoder Matching Model for Learning Utterance-Level Semantic Dependency in Dialogue Generation (D18-1)

Copied to clipboard

Challenge: Experimental results show that our model can generate semantically coherent responses compared to baseline models.
Approach: They propose an Auto-Encoder Matching model to learn utterance-level semantic dependency . their model contains two auto-encoders and one mapping module .
Outcome: Experimental results show that the proposed model can generate high coherence and fluency compared to baseline models.
Speculative Sampling in Variational Autoencoders for Dialogue Response Generation (2021.findings-emnlp)

Copied to clipboard

Challenge: Existing studies have tried to improve variational models but they fail to learn proper mappings.
Approach: They propose to use a variable-based sampling technique to find the most probable one from redundantly sampled latent variables to tie up the variable with a given response.
Outcome: The proposed method is effective in response generation with massive dialogue data constructed from Twitter posts.
DIRECT: Direct and Indirect Responses in Conversational Text Corpus (2021.findings-emnlp)

Copied to clipboard

Challenge: Neural conversation models have been able to generate fluent responses through training on a dialogue corpus, but they lack the ability to reveal the implied intentions of users.
Approach: They propose to train neural conversation models on a dialogue corpus that provides pragmatic paraphrases to advance techniques for natural language understanding in dialogue systems.
Outcome: The proposed corpus provides 71,498 pairs of indirect–direct utterance pairs accompanied by a multi-turn dialogue history extracted from the MultiWoZ dataset.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations