Search Results for author:
Found 8 papers, 4 papers with code
Don't Half-listen: Capturing Key-part Information in Continual Instruction Tuning
Recent methods try to alleviate the CF problem by modifying models or replaying data, which may only remember the surface-level pattern of instructions and get confused on held-out tasks.
An Extensible Plug-and-Play Method for Multi-Aspect Controllable Text Generation
Recently, multi-aspect controllable text generation that controls the generated text in multiple aspects (e. g., sentiment, topic, and keywords) has attracted increasing attention.
CUGE: A Chinese Language Understanding and Generation Evaluation Benchmark
We argue that for general-purpose language intelligence evaluation, the benchmark itself needs to be comprehensive and systematic.
Transfer Learning for Sequence Generation: from Single-source to Multi-source
Although directly finetuning pretrained models on MSG tasks and concatenating multiple sources into a single long sequence is regarded as a simple method to transfer pretrained models to MSG tasks, we conjecture that the direct finetuning method leads to catastrophic forgetting and solely relying on pretrained self-attention layers to capture cross-source information is not sufficient.
Neural Machine Translation: A Review of Methods, Resources, and Tools
Machine translation (MT) is an important sub-field of natural language processing that aims to translate natural languages using computers.
Modeling Voting for System Combination in Machine Translation
System combination is an important technique for combining the hypotheses of different machine translation systems to improve translation performance.
Learning to Copy for Automatic Post-Editing
To better identify translation errors, our method learns the representations of source sentences and system outputs in an interactive way.
