arXiv subjects

Xiaofeng Zhao

Publications and source records attributed to Xiaofeng Zhao.

23 records · Page 2Linked to original sources

arXiv2021

A Three-Stage Learning Framework for Low-Resource Knowledge-Grounded Dialogue Generation

Neural conversation models have shown great potentials towards generating fluent and informative responses by introducing external background knowledge. Nevertheless, it is laborious to construct such knowledge-grounded dialogues, and existing models usually perform poorly when transfer to new domains with limited training samples. Therefore, building a knowledge-grounded dialogue system under the low-resource setting is a still crucial issue. In this paper, we propose a novel three-stage learning framework based on weakly supervised learning which benefits from large scale ungrounded dialogues and unstructured knowledge base. To better cooperate with this framework, we devise a variant of Transformer with decoupled decoder which facilitates the disentangled learning of response generation and knowledge incorporation. Evaluation results on two benchmarks indicate that our approach can outperform other state-of-the-art methods with less training data, and even in zero-resource scenario, our approach still performs well.

cs.CL↗

arXiv2021

Knowledge-Grounded Dialogue with Reward-Driven Knowledge Selection

Knowledge-grounded dialogue is a task of generating a fluent and informative response based on both conversation context and a collection of external knowledge, in which knowledge selection plays an important role and attracts more and more research interest. However, most existing models either select only one knowledge or use all knowledge for responses generation. The former may lose valuable information in discarded knowledge, while the latter may bring a lot of noise. At the same time, many approaches need to train the knowledge selector with knowledge labels that indicate ground-truth knowledge, but these labels are difficult to obtain and require a large number of manual annotations. Motivated by these issues, we propose Knoformer, a dialogue response generation model based on reinforcement learning, which can automatically select one or more related knowledge from the knowledge pool and does not need knowledge labels during training. Knoformer is evaluated on two knowledge-guided conversation datasets, and achieves state-of-the-art performance.

cs.CL↗

arXiv2021

A Conditional Cascade Model for Relational Triple Extraction

Tagging based methods are one of the mainstream methods in relational triple extraction. However, most of them suffer from the class imbalance issue greatly. Here we propose a novel tagging based model that addresses this issue from following two aspects. First, at the model level, we propose a three-step extraction framework that can reduce the total number of samples greatly, which implicitly decreases the severity of the mentioned issue. Second, at the intra-model level, we propose a confidence threshold based cross entropy loss that can directly neglect some samples in the major classes. We evaluate the proposed model on NYT and WebNLG. Extensive experiments show that it can address the mentioned issue effectively and achieves state-of-the-art results on both datasets. The source code of our model is available at: https://github.com/neukg/ConCasRTE.

cs.CL↗

arXiv2021

An Effective System for Multi-format Information Extraction

The multi-format information extraction task in the 2021 Language and Intelligence Challenge is designed to comprehensively evaluate information extraction from different dimensions. It consists of an multiple slots relation extraction subtask and two event extraction subtasks that extract events from both sentence-level and document-level. Here we describe our system for this multi-format information extraction competition task. Specifically, for the relation extraction subtask, we convert it to a traditional triple extraction task and design a voting based method that makes full use of existing models. For the sentence-level event extraction subtask, we convert it to a NER task and use a pointer labeling based method for extraction. Furthermore, considering the annotated trigger information may be helpful for event extraction, we design an auxiliary trigger recognition model and use the multi-task learning mechanism to integrate the trigger features into the event extraction model. For the document-level event extraction subtask, we design an Encoder-Decoder based method and propose a Transformer-alike decoder. Finally,our system ranks No.4 on the test set leader-board of this multi-format information extraction task, and its F1 scores for the subtasks of relation extraction, event extractions of sentence-level and document-level are 79.887%, 85.179%, and 70.828% respectively. The codes of our model are available at {https://github.com/neukg/MultiIE}.

cs.CL↗

arXiv2020

The Simulation, Fabrication Technology and Characteristic Research of Micro-Pressure Sensor with Isosceles Trapezoidal Beam-Membrane

A micro-pressure sensor with an isosceles trapezoidal beam-membrane (ITBM) is proposed in this paper, consisting of a square silicon membrane, four isosceles trapezoidal beams and four piezoresistors.To investigate how the elastic silicon membrane affects pressure sensitive characteristics, a simulation models based on ANSYS 15.0 software were used to analyze the effect of structural dimension on characteristics of pressure sensor. According to that, the chips of micro-pressure sensors were fabricated by micro-electro-mechanical system (MEMS) technology on a silicon wafer with <100> orientation.The experimental results show that the proposed sensor achieves a better sensitivity of 9.64 mV/kPa and an excellent linearity of 0.09%F.S. in the range of 0~3.0 kPa at room temperature and a supply voltage of 5.0 V,with a super temperature coefficient of sensitivity(TCS) about - 684 ppm/K from 235.15 K to 360.15 K and low pressure measurement less than 3.0 kPa.

physics.app-ph↗