Matching structure for dual learning

H Fei, S Wu, Y Ren, M Zhang - international conference on …, 2022‏ - proceedings.mlr.press
Many natural language processing (NLP) tasks appear in dual forms, which are generally
solved by dual learning technique that models the dualities between the coupled tasks. In …

Lightgt: A light graph transformer for multimedia recommendation

Y Wei, W Liu, F Liu, X Wang, L Nie… - Proceedings of the 46th …, 2023‏ - dl.acm.org
Multimedia recommendation methods aim to discover the user preference on the multi-
modal information to enhance the collaborative filtering (CF) based recommender system …

Knowledge-enhanced event relation extraction via event ontology prompt

L Zhuang, H Fei, P Hu - Information Fusion, 2023‏ - Elsevier
Identifying temporal and subevent relationships between different events (ie, event relation
extraction) is an important step towards event-centric natural language processing, which …

OneEE: A one-stage framework for fast overlap** and nested event extraction

H Cao, J Li, F Su, F Li, H Fei, S Wu, B Li… - arxiv preprint arxiv …, 2022‏ - arxiv.org
Event extraction (EE) is an essential task of information extraction, which aims to extract
structured event information from unstructured text. Most prior work focuses on extracting flat …

Entity-centered cross-document relation extraction

F Wang, F Li, H Fei, J Li, S Wu, F Su, W Shi, D Ji… - arxiv preprint arxiv …, 2022‏ - arxiv.org
Relation Extraction (RE) is a fundamental task of information extraction, which has attracted
a large amount of research attention. Previous studies focus on extracting the relations …

Learn from syntax: Improving pair-wise aspect and opinion terms extractionwith rich syntactic knowledge

S Wu, H Fei, Y Ren, D Ji, J Li - arxiv preprint arxiv:2105.02520, 2021‏ - arxiv.org
In this paper, we propose to enhance the pair-wise aspect and opinion terms extraction
(PAOTE) task by incorporating rich syntactic knowledge. We first build a syntax fusion …

On the robustness of aspect-based sentiment analysis: Rethinking model, data, and training

H Fei, TS Chua, C Li, D Ji, M Zhang, Y Ren - ACM Transactions on …, 2022‏ - dl.acm.org
Aspect-based sentiment analysis (ABSA) aims at automatically inferring the specific
sentiment polarities toward certain aspects of products or services behind the social media …

Diaasq: A benchmark of conversational aspect-based sentiment quadruple analysis

B Li, H Fei, F Li, Y Wu, J Zhang, S Wu, J Li, Y Liu… - arxiv preprint arxiv …, 2022‏ - arxiv.org
The rapid development of aspect-based sentiment analysis (ABSA) within recent decades
shows great potential for real-world society. The current ABSA works, however, are mostly …

One question answering model for many languages with cross-lingual dense passage retrieval

A Asai, X Yu, J Kasai… - Advances in Neural …, 2021‏ - proceedings.neurips.cc
Abstract We present Cross-lingual Open-Retrieval Answer Generation (CORA), the first
unified many-to-many question answering (QA) model that can answer questions across …

Encoder-decoder based unified semantic role labeling with label-aware syntax

H Fei, F Li, B Li, D Ji - Proceedings of the AAAI conference on artificial …, 2021‏ - ojs.aaai.org
Currently the unified semantic role labeling (SRL) that achieves predicate identification and
argument role labeling in an end-to-end manner has received growing interests. Recent …