Search Results for author:
Found 13 papers, 10 papers with code
Inducing Transformer’s Compositional Generalization Ability via Auxiliary Sequence Prediction Tasks
Motivated by the failure of a Transformer model on the SCAN compositionality challenge (Lake and Baroni, 2018), which requires parsing a command into actions, we propose two auxiliary sequence prediction tasks as additional training supervision.
Inducing Systematicity in Transformers by Attending to Structurally Quantized Embeddings
Transformers generalize to novel compositions of structures and entities after being trained on a complex dataset, but easily overfit on datasets of insufficient complexity.
Data Factors for Better Compositional Generalization
However, in contrast to this poor performance, state-of-the-art models trained on larger and more general datasets show better generalization ability.
Mutual Exclusivity Training and Primitive Augmentation to Induce Compositionality
Recent datasets expose the lack of the systematic generalization ability in standard sequence-to-sequence models.
Structural Biases for Improving Transformers on Translation into Morphologically Rich Languages
Machine translation has seen rapid progress with the advent of Transformer-based models.
Learning and Analyzing Generation Order for Undirected Sequence Models
On examples with a maximum source and target length of 30 from De-En, WMT'16 English-Romanian, and WMT'21 English-Chinese translation tasks, our learned order outperforms all heuristic generation orders on four out of six tasks.
Inducing Transformer's Compositional Generalization Ability via Auxiliary Sequence Prediction Tasks
Motivated by the failure of a Transformer model on the SCAN compositionality challenge (Lake and Baroni, 2018), which requires parsing a command into actions, we propose two auxiliary sequence prediction tasks that track the progress of function and argument semantics, as additional training supervision.
Enriching Transformers with Structured Tensor-Product Representations for Abstractive Summarization
On several syntactic and semantic probing tasks, we demonstrate the emergent structural information in the role vectors and improved syntactic interpretability in the TPR layer outputs.
HoVer: A Dataset for Many-Hop Fact Extraction And Claim Verification
We introduce HoVer (HOppy VERification), a dataset for many-hop evidence extraction and fact verification.
Self-Assembling Modular Networks for Interpretable Multi-Hop Reasoning
Multi-hop QA requires a model to connect multiple pieces of evidence scattered in a long context to answer the question.
Avoiding Reasoning Shortcuts: Adversarial Evaluation, Training, and Model Development for Multi-Hop QA
After adversarial training, the baseline's performance improves but is still limited on the adversarial evaluation.
Explore, Propose, and Assemble: An Interpretable Model for Multi-Hop Reading Comprehension
Multi-hop reading comprehension requires the model to explore and connect relevant information from multiple sentences/documents in order to answer the question about the context.
Closed-Book Training to Improve Summarization Encoder Memory
A good neural sequence-to-sequence summarization model should have a strong encoder that can distill and memorize the important information from long input texts so that the decoder can generate salient summaries based on the encoder's memory.
Ranked #40 on
Abstractive Text Summarization
on CNN / Daily Mail
