arXiv subjects

Rui Xie

Publications and source records attributed to Rui Xie.

94 records · Page 6Linked to original sources

arXiv2020

Leveraging Code Generation to Improve Code Retrieval and Summarization via Dual Learning

Code summarization generates brief natural language description given a source code snippet, while code retrieval fetches relevant source code given a natural language query. Since both tasks aim to model the association between natural language and programming language, recent studies have combined these two tasks to improve their performance. However, researchers have yet been able to effectively leverage the intrinsic connection between the two tasks as they train these tasks in a separate or pipeline manner, which means their performance can not be well balanced. In this paper, we propose a novel end-to-end model for the two tasks by introducing an additional code generation task. More specifically, we explicitly exploit the probabilistic correlation between code summarization and code generation with dual learning, and utilize the two encoders for code summarization and code generation to train the code retrieval task via multi-task learning. We have carried out extensive experiments on an existing dataset of SQL and Python, and results show that our model can significantly improve the results of the code retrieval task over the-state-of-art models, as well as achieve competitive performance in terms of BLEU score for the code summarization task.

cs.IR↗

arXiv2019

Exploiting Entity BIO Tag Embeddings and Multi-task Learning for Relation Extraction with Imbalanced Data

In practical scenario, relation extraction needs to first identify entity pairs that have relation and then assign a correct relation class. However, the number of non-relation entity pairs in context (negative instances) usually far exceeds the others (positive instances), which negatively affects a model's performance. To mitigate this problem, we propose a multi-task architecture which jointly trains a model to perform relation identification with cross-entropy loss and relation classification with ranking loss. Meanwhile, we observe that a sentence may have multiple entities and relation mentions, and the patterns in which the entities appear in a sentence may contain useful semantic information that can be utilized to distinguish between positive and negative instances. Thus we further incorporate the embeddings of character-wise/word-wise BIO tag from the named entity recognition task into character/word embeddings to enrich the input representation. Experiment results show that our proposed approach can significantly improve the performance of a baseline model with more than 10% absolute increase in F1-score, and outperform the state-of-the-art models on ACE 2005 Chinese and English corpus. Moreover, BIO tag embeddings are particularly effective and can be used to improve other models as well.

cs.CL↗

arXiv2017

The lunar cycle's influence on sex determination at conception in humans

The lunar cycle has long been suspected to influence biological phenomena. Folklore alludes to such a relationship, but previous scientific analyses have failed to find significant associations. It has been shown that lunar cycles indeed have effects on animals; significant associations between human circadian rhythms and lunar cycles have also been reported. We set out to determine whether a significant statistical correlation exists between the lunar phase and sex determination during conception. We found that significant associations (\textit{p}-value $< 5 \times 10^{-5}$) exist between the average sex ratio (male:female) and the lunar month. The likelihood of conception of a male is at its highest point five days after the full moon, whereas the highest likelihood of female conception occurs nineteen days after the full moon. Furthermore, we found that the strength of this influence is correlated with the amount of solar radiation (which is proportional to moonlight). Our results suggest that sex determination may be influenced by the moon cycle, which suggests the possibility of lunar influence on other biological phenomena. We suggest for future research the exploration of similar effects in other phenomena involving humans and other species.

q-bio.OT↗

arXiv2014

Rapid polynomial approximation in $L_2$-spaces with Freud weights on the real line

The weights $W_α(x)=\exp{(-|x|^α)}$ $(α>1)$ form a subclass of Freud weights on the real line. Primarily from a functional analytic angle, we investigate the subspace of $L_2(\mathbb R, W_α^2(x)\,dx)$ consisting of those elements that can be rapidly approximated by polynomials. This subspace has a natural Fréchet topology, in which it is isomorphic to the space of rapidly decreasing sequences. We show that it consists of smooth functions and obtain concrete results on its topology. For $α=2$ there is a complete and elementary description of this topological vector space in terms of the Schwartz functions.

math.CA↗