1 |
Transforming Sequence Tagging Into A Seq2Seq Task ...
|
|
|
|
Abstract:
Pretrained, large, generative language models (LMs) have had great success in a wide range of sequence tagging and structured prediction tasks. Casting a sequence tagging task as a Seq2Seq one requires deciding the formats of the input and output sequences. However, we lack a principled understanding of the trade-offs associated with these formats (such as the effect on model accuracy, sequence length, multilingual generalization, hallucination). In this paper, we rigorously study different formats one could use for casting input text sentences and their output labels into the input and target (i.e., output) of a Seq2Seq model. Along the way, we introduce a new format, which we show to not only be simpler but also more effective. Additionally the new format demonstrates significant gains in the multilingual settings -- both zero-shot transfer learning and joint training. Lastly, we find that the new format is more robust and almost completely devoid of hallucination -- an issue we find common in existing ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences
|
|
URL: https://arxiv.org/abs/2203.08378 https://dx.doi.org/10.48550/arxiv.2203.08378
|
|
BASE
|
|
Hide details
|
|
3 |
A High-Quality Multilingual Dataset for Structured Documentation Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Find or Classify? Dual Strategy for Slot-Value Predictions on Multi-Domain Dialog State Tracking ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Find or Classify? Dual Strategy for Slot-Value Predictions on Multi-Domain Dialog State Tracking ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question Answering ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Multilingual Extractive Reading Comprehension by Runtime Machine Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Adaptive Joint Learning of Compositional and Non-Compositional Phrase Embeddings ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
A Joint Many-Task Model: Growing a Neural Network for Multiple NLP Tasks ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
Task-Oriented Learning of Word Embeddings for Semantic Relation Classification ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|