Papers by Chaoqun Duan

4 papers
UniRPG: Unified Discrete Reasoning over Table and Text as Program Generation (2022.emnlp-main)

Copied to clipboard

Challenge: Existing methods for question answering using knowledge resources are mixed-of-experts and semantic parsing-based.
Approach: They propose a semantic-parsing-based approach to perform Unified discrete Reasoning over heterogeneous knowledge resources as Program Generation.
Outcome: The proposed approach improves interpretability and scalability over table and text . it achieves promising performance on the TAT-QA dataset without annotation .
MuGER2: Multi-Granularity Evidence Retrieval and Reasoning for Hybrid Question Answering (2022.findings-emnlp)

Copied to clipboard

Challenge: Conventional HQA models retrieve coarse- or fine-grained evidence to reason the answer . however, they neglect a more general scenario requiring reasoning over heterogeneous data to answer a question.
Approach: They propose a multi-granularity evidence retrieval and reasoning approach to answer questions over heterogeneous data using tables and passages linked to table cells.
Outcome: The proposed approach significantly boosts the performance on the HybridQA dataset.
OPERA: Operation-Pivoted Discrete Reasoning over Text (2022.naacl-main)

Copied to clipboard

Challenge: Existing methods to predict logical forms ignore the utilization of symbolic operations and lack reasoning ability and interpretability.
Approach: They propose an operation-pivoted discrete reasoning framework that uses symbolic operations as neural modules to facilitate reasoning ability and interpretability.
Outcome: Extensive experiments on DROP and RACENum datasets show the reasoning ability of OPERA.
LUNA: Learning Slot-Turn Alignment for Dialogue State Tracking (2022.naacl-main)

Copied to clipboard

Challenge: Existing methods exploit the utterances of all dialogue turns to assign value to slots . this can lead to suboptimal results due to information introduced from irrelevant utterrances .
Approach: They propose a SLot-TUrN Alignment enhanced approach to assign slot value . they explicitly align each slot with its most relevant utterance and then predict the corresponding value based on this aligned utteration.
Outcome: The proposed approach achieves state-of-the-art on three multi-domain task-oriented dialogue datasets.

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