Search Results for author:
Found 6 papers, 4 papers with code
The Cross-lingual Conversation Summarization Challenge
We propose the shared task of cross-lingual conversation summarization, \emph{ConvSumX Challenge}, opening new avenues for researchers to investigate solutions that integrate conversation summarization and machine translation.
Abstractive Dialogue Summarization
Cross-Lingual Abstractive Summarization
+3
Graph Pre-training for AMR Parsing and Generation
To our knowledge, we are the first to consider pre-training on semantic graphs.
Ranked #1 on
AMR-to-Text Generation
on LDC2017T10
(using extra training data)
Semantic Representation for Dialogue Modeling
Although neural models have achieved competitive results in dialogue systems, they have shown limited ability in representing core semantics, such as ignoring important entities.
Ranked #4 on
Dialog Relation Extraction
on DialogRE
Online Back-Parsing for AMR-to-Text Generation
AMR-to-text generation aims to recover a text containing the same meaning as an input AMR graph.
Ranked #7 on
AMR-to-Text Generation
on LDC2017T10
Investigating Typed Syntactic Dependencies for Targeted Sentiment Classification Using Graph Attention Neural Network
Targeted sentiment classification predicts the sentiment polarity on given target mentions in input texts.
Ranked #1 on
Aspect-Based Sentiment Analysis
on MAMS
Duality Regularization for Unsupervised Bilingual Lexicon Induction
Unsupervised bilingual lexicon induction naturally exhibits duality, which results from symmetry in back-translation.
