Searcharxiv⌕ Search

arXiv subjects

Yuan Miao

Publications and source records attributed to Yuan Miao.

29 records · Page 2Linked to original sources
arXiv2021

Hierarchical Aspect-guided Explanation Generation for Explainable Recommendation

Explainable recommendation systems provide explanations for recommendation results to improve their transparency and persuasiveness. The existing explainable recommendation methods generate textual explanations without explicitly considering the user's preferences on different aspects of the item. In this paper, we propose a novel explanation generation framework, named Hierarchical Aspect-guided explanation Generation (HAG), for explainable recommendation. Specifically, HAG employs a review-based syntax graph to provide a unified view of the user/item details. An aspect-guided graph pooling operator is proposed to extract the aspect-relevant information from the review-based syntax graphs to model the user's preferences on an item at the aspect level. Then, a hierarchical explanation decoder is developed to generate aspects and aspect-relevant explanations based on the attention mechanism. The experimental results on three real datasets indicate that HAG outperforms state-of-the-art explanation generation methods in both single-aspect and multi-aspect explanation generation tasks, and also achieves comparable or even better preference prediction accuracy than strong baseline methods.

cs.CL↗
arXiv2021

On the Q operator and the spectrum of the XXZ model at root of unity

The spin-1/2 Heisenberg XXZ chain is a paradigmatic quantum integrable model. Although it can be solved exactly via Bethe ansatz techniques, there are still open issues regarding the spectrum at root of unity values of the anisotropy. We construct Baxter's Q operator at arbitrary anisotropy from a two-parameter transfer matrix associated to a complex-spin auxiliary space. A decomposition of this transfer matrix provides a simple proof of the transfer matrix fusion and Wronskian relations. At root of unity a truncation allows us to construct the Q operator explicitly in terms of finite-dimensional matrices. From its decomposition we derive truncated fusion and Wronskian relations as well as an interpolation-type formula that has been conjectured previously. We elucidate the Fabricius-McCoy (FM) strings and exponential degeneracies in the spectrum of the six-vertex transfer matrix at root of unity. Using a semicyclic auxiliary representation we give a conjecture for creation and annihilation operators of FM strings for all roots of unity. We connect our findings with the 'string-charge duality' in the thermodynamic limit, leading to a conjecture for the imaginary part of the FM string centres with potential applications to out-of-equilibrium physics.

cond-mat.stat-mech↗
arXiv2021

Semi-classical quantisation of magnetic solitons in the anisotropic Heisenberg quantum chain

Using the algebro-geometric approach, we study the structure of semi-classical eigenstates in a weakly-anisotropic quantum Heisenberg spin chain. We outline how classical nonlinear spin waves governed by the anisotropic Landau-Lifshitz equation arise as coherent macroscopic low-energy fluctuations of the ferromagnetic ground state. Special emphasis is devoted to the simplest types of solutions, describing precessional motion and elliptic magnetisation waves. The internal magnon structure of classical spin waves is resolved by performing the semi-classical quantisation using the Riemann-Hilbert problem approach. We present an expression for the overlap of two semi-classical eigenstates and discuss how correlation functions at the semi-classical level arise from classical phase-space averaging.

cond-mat.stat-mech↗
arXiv2021

External pressure dependence of Granular Orifice Flow: transition to Beverloo flow

In this paper, we have designed and employed a suspended-wall silo to remove Janssen effect in order to explore directly the local pressure dependence of Granular Orifice Flow (GOF) systematically. We find that as Janssen effect is removed, the flow rate Q changes linearly with the external pressure. The slope α of the linear change decays exponentially with the ratio of the silo size and the size of the orifice Φ/D, which suggests the existence of a characteristic ratio λ (~2.4). When Φ/D > λ, α gradually decays to zero, and the effect of external pressure on the GOF becomes negligible, where the Beverloo law retrieves. Our results show that Janssen effect is not a determining factor of the constant rate of GOF, although it may contribute to shield the top load. The key parameter in GOF is Φ/D. In small Φ/D, the flow rate of GOF can be directly adjusted by the external pressure via our suspended-wall setup, which may be useful to the transportation of granules in microgravity environment where the gravity-driven Beverloo law is disabled.

cond-mat.soft↗
arXiv2020

Commonsense knowledge adversarial dataset that challenges ELECTRA

Commonsense knowledge is critical in human reading comprehension. While machine comprehension has made significant progress in recent years, the ability in handling commonsense knowledge remains limited. Synonyms are one of the most widely used commonsense knowledge. Constructing adversarial dataset is an important approach to find weak points of machine comprehension models and support the design of solutions. To investigate machine comprehension models' ability in handling the commonsense knowledge, we created a Question and Answer Dataset with common knowledge of Synonyms (QADS). QADS are questions generated based on SQuAD 2.0 by applying commonsense knowledge of synonyms. The synonyms are extracted from WordNet. Words often have multiple meanings and synonyms. We used an enhanced Lesk algorithm to perform word sense disambiguation to identify synonyms for the context. ELECTRA achieves the state-of-art result on the SQuAD 2.0 dataset in 2019. With scale, ELECTRA can achieve similar performance as BERT does. However, QADS shows that ELECTRA has little ability to handle commonsense knowledge of synonyms. In our experiment, ELECTRA-small can achieve 70% accuracy on SQuAD 2.0, but only 20% on QADS. ELECTRA-large did not perform much better. Its accuracy on SQuAD 2.0 is 88% but dropped significantly to 26% on QADS. In our earlier experiments, BERT, although also failed badly on QADS, was not as bad as ELECTRA. The result shows that even top-performing NLP models have little ability to handle commonsense knowledge which is essential in reading comprehension.

cs.CL↗
arXiv2020

Time-aware Graph Embedding: A temporal smoothness and task-oriented approach

Knowledge graph embedding, which aims to learn the low-dimensional representations of entities and relationships, has attracted considerable research efforts recently. However, most knowledge graph embedding methods focus on the structural relationships in fixed triples while ignoring the temporal information. Currently, existing time-aware graph embedding methods only focus on the factual plausibility, while ignoring the temporal smoothness which models the interactions between a fact and its contexts, and thus can capture fine-granularity temporal relationships. This leads to the limited performance of embedding related applications. To solve this problem, this paper presents a Robustly Time-aware Graph Embedding (RTGE) method by incorporating temporal smoothness. Two major innovations of our paper are presented here. At first, RTGE integrates a measure of temporal smoothness in the learning process of the time-aware graph embedding. Via the proposed additional smoothing factor, RTGE can preserve both structural information and evolutionary patterns of a given graph. Secondly, RTGE provides a general task-oriented negative sampling strategy associated with temporally-aware information, which further improves the adaptive ability of the proposed algorithm and plays an essential role in obtaining superior performance in various tasks. Extensive experiments conducted on multiple benchmark tasks show that RTGE can increase performance in entity/relationship/temporal scoping prediction tasks.

cs.LG↗
arXiv2019

Commonsense Knowledge + BERT for Level 2 Reading Comprehension Ability Test

Commonsense knowledge plays an important role when we read. The performance of BERT on SQuAD dataset shows that the accuracy of BERT can be better than human users. However, it does not mean that computers can surpass the human being in reading comprehension. CommonsenseQA is a large-scale dataset which is designed based on commonsense knowledge. BERT only achieved an accuracy of 55.9% on it. The result shows that computers cannot apply commonsense knowledge like human beings to answer questions. Comprehension Ability Test (CAT) divided the reading comprehension ability at four levels. We can achieve human like comprehension ability level by level. BERT has performed well at level 1 which does not require common knowledge. In this research, we propose a system which aims to allow computers to read articles and answer related questions with commonsense knowledge like a human being for CAT level 2. This system consists of three parts. Firstly, we built a commonsense knowledge graph; and then automatically constructed the commonsense knowledge question dataset according to it. Finally, BERT is combined with the commonsense knowledge to achieve the reading comprehension ability at CAT level 2. Experiments show that it can pass the CAT as long as the required common knowledge is included in the knowledge base.

cs.CL↗
arXiv2019

Reading Comprehension Ability Test-A Turing Test for Reading Comprehension

Reading comprehension is an important ability of human intelligence. Literacy and numeracy are two most essential foundation for people to succeed at study, at work and in life. Reading comprehension ability is a core component of literacy. In most of the education systems, developing reading comprehension ability is compulsory in the curriculum from year one to year 12. It is an indispensable ability in the dissemination of knowledge. With the emerging artificial intelligence, computers start to be able to read and understand like people in some context. They can even read better than human beings for some tasks, but have little clue in other tasks. It will be very beneficial if we can identify the levels of machine comprehension ability, which will direct us on the further improvement. Turing test is a well-known test of the difference between computer intelligence and human intelligence. In order to be able to compare the difference between people reading and machines reading, we proposed a test called (reading) Comprehension Ability Test (CAT).CAT is similar to Turing test, passing of which means we cannot differentiate people from algorithms in term of their comprehension ability. CAT has multiple levels showing the different abilities in reading comprehension, from identifying basic facts, performing inference, to understanding the intent and sentiment.

cs.CL↗
arXiv2019

Domain wall dynamics in the Landau--Lifshitz magnet and the classical-quantum correspondence for spin transport

We investigate the dynamics of spin in the axially anisotropic Landau--Lifshitz field theory with a magnetic domain wall initial condition. Employing the analytic scattering technique, we obtain the exact scattering data and reconstruct the time-evolved profile. We identify three qualitatively distinct regimes of spin transport, ranging from ballistic expansion in the easy-plane regime, absence of transport in the easy-axis regime and log-modified diffusion for the isotropic interaction. Our results are in perfect qualitative agreement with those found in the anisotropic quantum Heisenberg spin-$1/2$ chain, indicating a remarkable classical-quantum correspondence for macroscopic spin transport.

cond-mat.stat-mech↗
arXiv2019

Interplay of Solitons and Radiation in One-Dimensional Bose Gases

We study relaxation dynamics in one-dimensional Bose gases, formulated as an initial value problem for the classical non-linear Schrödinger equation. We propose an analytic technique which takes into account the exact spectrum of non-linear modes, that is both soliton excitations and dispersive continuum of radiation modes. Our method relies on the exact large-time asymptotics and uses the so-called dressing transformation to account for the solitons. The obtained results are quantitatively compared with the predictions of the linearized approach in the framework of the Bogoliubov--de Gennes theory. In the attractive regime, the interplay between solitons and radiation yields a damped oscillatory motion of the profile which resembles breathing. For the repulsive interaction, the solitons are confined in the sound cone region separated from the supersonic radiation.

cond-mat.quant-gas↗