The components underpinning PLMs – large weight matrices – were shown to...
Iterative pruning is one of the most effective compression methods for
p...
Controlling chatbot utterance generation with multiple attributes such a...
Compared with ample visual-text pre-training research, few works explore...
Curriculum learning has shown promising improvements in multiple domains...
Abstractive dialogue summarization is to generate a concise and fluent
s...
Mental disease detection (MDD) from social media has suffered from poor
...
Natural Language Inference Generation task is to generate a text hypothe...
Depression is a prominent health challenge to the world, and early risk
...
News recommendation for anonymous readers is a useful but challenging ta...
Current text-image approaches (e.g., CLIP) typically adopt dual-encoder
...
Previous dialogue summarization techniques adapt large language models
p...
Informational bias is widely present in news articles. It refers to prov...
Automated audio captioning aims at generating textual descriptions for a...
Audio tagging aims at predicting sound events occurred in a recording.
T...
Product descriptions on e-commerce websites often suffer from missing
im...
Recent work has indicated that many natural language understanding and
r...
Interpersonal language style shifting in dialogues is an interesting and...
Multi-turn response selection is a task designed for developing dialogue...
Matching question-answer relations between two turns in conversations is...
Few-shot relation classification describes a circumstance where a model ...
Text style transfer aims to paraphrase a sentence in one style into anot...
In this paper, we propose a novel configurable framework to automaticall...
A gradient boosting decision tree (GBDT), which aggregates a collection ...
One of the ultimate goals of e-commerce platforms is to satisfy various
...
Secure online transaction is an essential task for e-commerce platforms....
Previous work on cross-lingual sequence labeling tasks either requires
p...
Understanding latent user needs beneath shopping behaviors is critical t...
This paper targets to a novel but practical recommendation problem named...
We propose a framework to automatically generate descriptive comments fo...
This paper studies the problem of automatically extracting a short title...
Slot filling is a critical task in natural language understanding (NLU) ...
Verbs play an important role in the understanding of natural language te...
LocatedNear relation describes two typically co-located objects, which i...
The Apache Spark stack has enabled fast large-scale data processing. Des...
LAGE is a systematic framework developed in Java. The motivation of LAGE...