Papers with Switchboard Dialog

4 papers
Human-like informative conversations: Better acknowledgements using conditional mutual information (2021.naacl-main)

Copied to clipboard

Challenge: Existing chatbots generate responses that are non-specific w.r.t. one of the contexts, typically the conversational history.
Approach: They propose to build a dialogue agent that can weave new factual content into conversations as naturally as humans.
Outcome: The proposed method trades off pmi for pcmi_h and is preferred by humans for overall quality over the Max-PMI baseline 60% of the time.
What Helps Transformers Recognize Conversational Structure? Importance of Context, Punctuation, and Labels in Dialog Act Recognition (2021.tacl-1)

Copied to clipboard

Challenge: Existing punctuation in the transcripts has a massive effect on the models’ performance, and specific label set specificity does not affect dialog act segmentation performance.
Approach: They apply two pre-trained transformer models to a conversation transcript as a sequence of dialog acts and achieve strong results on Switchboard Dialog Act and Meeting Recorder Dialog Act corpora.
Outcome: The proposed models achieve 8.4% and 14.2% error rates on the Switchboard Dialog Act and Meeting Recorder Dialog Act corpora.
Disentangling Indirect Answers to Yes-No Questions in Real Conversations (2022.naacl-main)

Copied to clipboard

Challenge: Existing models with synthetic indirect answers to yes-no questions are not beneficial when working with real conversations.
Approach: They propose to annotate the underlying direct answers to yes-no questions in real conversations.
Outcome: The proposed model outperforms the majority baseline but the task remains a challenge.
The TalkMoves Dataset: K-12 Mathematics Lesson Transcripts Annotated for Teacher and Student Discursive Moves (2022.lrec-1)

Copied to clipboard

Challenge: Currently, classroom recordings are limited due to practical and privacy concerns and sharing is restricted due to limited access to valuable resources and data sets.
Approach: They propose to use the TalkMoves dataset to analyze the nature of teacher and student discourse in K-12 math classrooms.
Outcome: The TalkMoves dataset contains 567 human-annotated K-12 mathematics lesson transcripts derived from video recordings.

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