activity
20182022
most citedBERT Post-Training for Review Reading Comprehension and Aspect-based Sentiment Analysis

360 citations · 574 across the 22 of their papers we have counts for

collaborators
Showing 2020 · cs.CLShow all

9 papers · 2 filters

cs.CL2020★ 2 cited

Continual Learning in Task-Oriented Dialogue Systems

Andrea Madotto, Zhaojiang Lin, Zhenpeng Zhou +6

Continual learning in task-oriented dialogue systems can allow us to add new domains and functionalities through time without incurring the high cost of a whole system retraining.…

cs.CL2020★ 7 cited

Understanding Pre-trained BERT for Aspect-based Sentiment Analysis

Hu Xu, Lei Shu, Philip S. Yu +1

This paper analyzes the pre-trained hidden representations learned from reviews on BERT for tasks in aspect-based sentiment analysis (ABSA). Our work is motivated by the recent pro…

cs.CL2020

NUANCED: Natural Utterance Annotation for Nuanced Conversation with Estimated Distributions

Zhiyu Chen, Honglei Liu, Hu Xu +3

Existing conversational systems are mostly agent-centric, which assumes the user utterances would closely follow the system ontology (for NLU or dialogue state tracking). However,…

cs.CL2020

Adding Chit-Chat to Enhance Task-Oriented Dialogues

Kai Sun, Seungwhan Moon, Paul Crook +7

Existing dialogue corpora and models are typically designed under two disjoint motives: while task-oriented systems focus on achieving functional goals (e.g., booking hotels), open…

cs.CL2020

A Knowledge-Driven Approach to Classifying Object and Attribute Coreferences in Opinion Mining

Jiahua Chen, Shuai Wang, Sahisnu Mazumder +1

Classifying and resolving coreferences of objects (e.g., product names) and attributes (e.g., product aspects) in opinionated reviews is crucial for improving the opinion mining pe…

cs.CL2020

Controllable Text Generation with Focused Variation

Lei Shu, Alexandros Papangelis, Yi-Chia Wang +5

This work introduces Focused-Variation Network (FVN), a novel model to control language generation. The main problems in previous controlled language generation models range from t…