Large Language Models (LLMs) present strong general capabilities, and a
...
In order to construct or extend entity-centric and event-centric knowled...
Many-to-many multimodal summarization (M^3S) task aims to generate
summa...
Knowledge distillation (KD) is a promising technique for model compressi...
Multilingual vision-language (V L) pre-training has achieved remarkabl...
Existing neural machine translation (NMT) studies mainly focus on develo...
Recently, the emergence of ChatGPT has attracted wide attention from the...
Zero-shot information extraction (IE) aims to build IE systems from the
...
Neural chat translation (NCT) aims to translate a cross-lingual chat bet...
The goal of multimodal abstractive summarization (MAS) is to produce a
c...
This paper introduces the joint submission of the Beijing Jiaotong Unive...
Translation suggestion (TS) models are used to automatically provide
alt...
Word alignment which aims to extract lexicon translation equivalents bet...
Neural Chat Translation (NCT) aims to translate conversational text into...
Generating adversarial examples for Neural Machine Translation (NMT) wit...
The goal of the cross-lingual summarization (CLS) is to convert a docume...
Token-level adaptive training approaches can alleviate the token imbalan...
Multimodal machine translation and textual chat translation have receive...
Neural Chat Translation (NCT) aims to translate conversational text betw...
Scheduled sampling is widely used to mitigate the exposure bias problem ...
This paper introduces WeChat AI's participation in WMT 2021 shared news
...
Neural chat translation aims to translate bilingual conversational text,...
Zero-resource named entity recognition (NER) severely suffers from data
...
Scheduled sampling is an effective method to alleviate the exposure bias...
Recently, token-level adaptive training has achieved promising improveme...
The success of emotional conversation systems depends on sufficient
perc...
For multiple aspects scenario of aspect-based sentiment analysis (ABSA),...
The vanilla Transformer conducts a fixed number of computations over all...
The aspect-based sentiment analysis (ABSA) task remains to be a long-sta...
Aspect-based sentiment analysis (ABSA) mainly involves three subtasks: a...
The Sentence-State LSTM (S-LSTM) is a powerful and high efficient graph
...
Spoken Language Understanding (SLU) mainly involves two tasks, intent
de...
Aspect based sentiment analysis (ABSA) aims to identify the sentiment
po...
Current state-of-the-art systems for sequence labeling are typically bas...