arXiv subjects

Haifeng Tang

Publications and source records attributed to Haifeng Tang.

26 records · Page 2Linked to original sources

arXiv2023

Multi-turn Response Selection using Dialogue Dependency Relations

Multi-turn response selection is a task designed for developing dialogue agents. The performance on this task has a remarkable improvement with pre-trained language models. However, these models simply concatenate the turns in dialogue history as the input and largely ignore the dependencies between the turns. In this paper, we propose a dialogue extraction algorithm to transform a dialogue history into threads based on their dependency relations. Each thread can be regarded as a self-contained sub-dialogue. We also propose Thread-Encoder model to encode threads and candidates into compact representations by pre-trained Transformers and finally get the matching score through an attention layer. The experiments show that dependency relations are helpful for dialogue context understanding, and our model outperforms the state-of-the-art baselines on both DSTC7 and DSTC8*, with competitive results on UbuntuV2.

cs.CL↗

arXiv2023

Information recovery in the Hayden-Preskill protocol

We revisit information retrieval from evaporating black holes in the Hayden-Preskill protocol, treating the black hole dynamics as Haar-random. We compute, down to the first exponentially suppressed terms, all integer-indexed Rényi mutual informations between a black hole, its radiation, and a reference that catalogues Alice's diaries. We find that dropping a diary into a young black hole effectively delays the Page time. We also compute the radiation : diary reflected Rényi entropies, and identify a technical reason why they cannot be continued to the reflected entropy by the replica trick.

hep-th↗

arXiv2023

Reducing Sensitivity on Speaker Names for Text Generation from Dialogues

Changing speaker names consistently throughout a dialogue should not affect its meaning and corresponding outputs for text generation from dialogues. However, pre-trained language models, serving as the backbone for dialogue-processing tasks, have shown to be sensitive to nuances. This may result in unfairness in real-world applications. No comprehensive analysis of this problem has been done in the past. In this work, we propose to quantitatively measure a model's sensitivity on speaker names, and comprehensively evaluate a number of known methods for reducing speaker name sensitivity, including a novel approach of our own. Extensive experiments on multiple datasets provide a benchmark for this problem and show the favorable performance of our approach in sensitivity reduction and quality of generation.

cs.CL↗

arXiv2023

In-sample Curriculum Learning by Sequence Completion for Natural Language Generation

Curriculum learning has shown promising improvements in multiple domains by training machine learning models from easy samples to hard ones. Previous works which either design rules or train models for scoring the difficulty highly rely on task-specific expertise, and cannot generalize. Inspired by the "easy-to-hard" intuition, we propose to do in-sample curriculum learning for natural language generation tasks. Our learning strategy starts training the model to generate the last few words, i.e., do sequence completion, and gradually extends to generate the whole output sequence. Comprehensive experiments show that it generalizes well to different tasks and achieves significant improvements over strong baselines.

cs.CL↗

arXiv2022

Krylov Complexity in Open Quantum Systems

Krylov complexity is a novel measure of operator complexity that exhibits universal behavior and bounds a large class of other measures. In this letter, we generalize Krylov complexity from a closed system to an open system coupled to a Markovian bath, where Lindbladian evolution replaces Hamiltonian evolution. We show that Krylov complexity in open systems can be mapped to a non-hermitian tight-binding model in a half-infinite chain. We discuss the properties of the non-hermitian terms and show that the strengths of the non-hermitian terms increase linearly with the increase of the Krylov basis index $n$. Such a non-hermitian tight-binding model can exhibit localized edge modes that determine the long-time behavior of Krylov complexity. Hence, the growth of Krylov complexity is suppressed by dissipation, and at long-time, Krylov complexity saturates at a finite value much smaller than that of a closed system with the same Hamitonian. Our conclusions are supported by numerical results on several models, such as the Sachdev-Ye-Kitaev model and the interacting fermion model. Our work provides insights for discussing complexity, chaos, and holography for open quantum systems.

cond-mat.str-el↗

arXiv2022

Post-Training Dialogue Summarization using Pseudo-Paraphrasing

Previous dialogue summarization techniques adapt large language models pretrained on the narrative text by injecting dialogue-specific features into the models. These features either require additional knowledge to recognize or make the resulting models harder to tune. To bridge the format gap between dialogues and narrative summaries in dialogue summarization tasks, we propose to post-train pretrained language models (PLMs) to rephrase from dialogue to narratives. After that, the model is fine-tuned for dialogue summarization as usual. Comprehensive experiments show that our approach significantly improves vanilla PLMs on dialogue summarization and outperforms other SOTA models by the summary quality and implementation costs.

cs.CL↗

arXiv2021

Enriching Ontology with Temporal Commonsense for Low-Resource Audio Tagging

Audio tagging aims at predicting sound events occurred in a recording. Traditional models require enormous laborious annotations, otherwise performance degeneration will be the norm. Therefore, we investigate robust audio tagging models in low-resource scenarios with the enhancement of knowledge graphs. Besides existing ontological knowledge, we further propose a semi-automatic approach that can construct temporal knowledge graphs on diverse domain-specific label sets. Moreover, we leverage a variant of relation-aware graph neural network, D-GCN, to combine the strength of the two knowledge types. Experiments on AudioSet and SONYC urban sound tagging datasets suggest the effectiveness of the introduced temporal knowledge, and the advantage of the combined KGs with D-GCN over single knowledge source.

cs.SD↗

arXiv2021

Testing density functional theory in a quantum Ising chain

By using the quantum Ising chain as a test bed and treating the spin polarization along the external transverse field as the "generalized density", we examine the performance of different levels of density functional approximations parallel to those widely used for interacting electrons, such as local density approximation (LDA) and generalized gradient approximation (GGA). We show that by adding the lowest-order and nearest-neighbor density variation correction to the simple LDA, a semi-local energy functional in the spirit of GGA is almost exact over a wide range of inhomogeneous density distribution. In addition, the LDA and GGA error structures bear a high level of resemblance to the quantum phase diagram of the system. These results provide insights into the triumph and failure of these approximations in a general context.

physics.comp-ph↗