How Do We Answer Complex Questions: Discourse Structure of Long-form Answers
Fangyuan Xu, Junyi Jessy Li, Eunsol Choi.
About
Long-form answers, consisting of multiple sentences, can provide nuanced and comprehensive answers to a broader set of questions. To better understand this complex and understudied task, we study the functional structure of long-form answers collected from three datasets, ELI5, WebGPT and Natural Questions.
We develop an ontology of six sentence-level functional roles for long-form answers, and annotate 3.9k sentences in 640 answer paragraphs (See figure below for examples of answer paragraphs annotated with sentence-level roles).
We further analyze model-generated answers -- finding that annotators agree less with each other when annotating model-generated answers compared to annotating human-written answers.
![intro figure](src/intro.jpeg)
Citations
If you find our work helpful, please cite us as:
@inproceedings{xu2022lfqadiscourse, title = {How Do We Answer Complex Questions: Discourse Structure of Long-form Answers}, author = {Xu, Fangyuan and Li, Junyi Jessy and Choi, Eunsol}, year = 2022, booktitle = {Proceedings of the Annual Meeting of the Association for Computational Linguistics}, note = {Long paper} }
Contact
For any questions, please contact Fangyuan Xu.