Searcharxiv⌕ Search

arXiv subjects

Qin Lu

Publications and source records attributed to Qin Lu.

51 records · Page 3Linked to original sources
arXiv2018

Curriculum Guidelines for Undergraduate Programs in Data Science

The Park City Math Institute (PCMI) 2016 Summer Undergraduate Faculty Program met for the purpose of composing guidelines for undergraduate programs in Data Science. The group consisted of 25 undergraduate faculty from a variety of institutions in the U.S., primarily from the disciplines of mathematics, statistics and computer science. These guidelines are meant to provide some structure for institutions planning for or revising a major in Data Science.

stat.OT↗
arXiv2017

A Question Answering Approach to Emotion Cause Extraction

Emotion cause extraction aims to identify the reasons behind a certain emotion expressed in text. It is a much more difficult task compared to emotion classification. Inspired by recent advances in using deep memory networks for question answering (QA), we propose a new approach which considers emotion cause identification as a reading comprehension task in QA. Inspired by convolutional neural networks, we propose a new mechanism to store relevant context in different memory slots to model context information. Our proposed approach can extract both word level sequence features and lexical features. Performance evaluation shows that our method achieves the state-of-the-art performance on a recently released emotion cause dataset, outperforming a number of competitive baselines by at least 3.01% in F-measure.

cs.CL↗
arXiv2016

Unsupervised Measure of Word Similarity: How to Outperform Co-occurrence and Vector Cosine in VSMs

In this paper, we claim that vector cosine, which is generally considered among the most efficient unsupervised measures for identifying word similarity in Vector Space Models, can be outperformed by an unsupervised measure that calculates the extent of the intersection among the most mutually dependent contexts of the target words. To prove it, we describe and evaluate APSyn, a variant of the Average Precision that, without any optimization, outperforms the vector cosine and the co-occurrence on the standard ESL test set, with an improvement ranging between +9.00% and +17.98%, depending on the number of chosen top contexts.

cs.CL↗
arXiv2016

What a Nerd! Beating Students and Vector Cosine in the ESL and TOEFL Datasets

In this paper, we claim that Vector Cosine, which is generally considered one of the most efficient unsupervised measures for identifying word similarity in Vector Space Models, can be outperformed by a completely unsupervised measure that evaluates the extent of the intersection among the most associated contexts of two target words, weighting such intersection according to the rank of the shared contexts in the dependency ranked lists. This claim comes from the hypothesis that similar words do not simply occur in similar contexts, but they share a larger portion of their most relevant contexts compared to other related words. To prove it, we describe and evaluate APSyn, a variant of Average Precision that, independently of the adopted parameters, outperforms the Vector Cosine and the co-occurrence on the ESL and TOEFL test sets. In the best setting, APSyn reaches 0.73 accuracy on the ESL dataset and 0.70 accuracy in the TOEFL dataset, beating therefore the non-English US college applicants (whose average, as reported in the literature, is 64.50%) and several state-of-the-art approaches.

cs.CL↗
arXiv2016

Nine Features in a Random Forest to Learn Taxonomical Semantic Relations

ROOT9 is a supervised system for the classification of hypernyms, co-hyponyms and random words that is derived from the already introduced ROOT13 (Santus et al., 2016). It relies on a Random Forest algorithm and nine unsupervised corpus-based features. We evaluate it with a 10-fold cross validation on 9,600 pairs, equally distributed among the three classes and involving several Parts-Of-Speech (i.e. adjectives, nouns and verbs). When all the classes are present, ROOT9 achieves an F1 score of 90.7%, against a baseline of 57.2% (vector cosine). When the classification is binary, ROOT9 achieves the following results against the baseline: hypernyms-co-hyponyms 95.7% vs. 69.8%, hypernyms-random 91.8% vs. 64.1% and co-hyponyms-random 97.8% vs. 79.4%. In order to compare the performance with the state-of-the-art, we have also evaluated ROOT9 in subsets of the Weeds et al. (2014) datasets, proving that it is in fact competitive. Finally, we investigated whether the system learns the semantic relation or it simply learns the prototypical hypernyms, as claimed by Levy et al. (2015). The second possibility seems to be the most likely, even though ROOT9 can be trained on negative examples (i.e., switched hypernyms) to drastically reduce this bias.

cs.CL↗
arXiv2016

ROOT13: Spotting Hypernyms, Co-Hyponyms and Randoms

In this paper, we describe ROOT13, a supervised system for the classification of hypernyms, co-hyponyms and random words. The system relies on a Random Forest algorithm and 13 unsupervised corpus-based features. We evaluate it with a 10-fold cross validation on 9,600 pairs, equally distributed among the three classes and involving several Parts-Of-Speech (i.e. adjectives, nouns and verbs). When all the classes are present, ROOT13 achieves an F1 score of 88.3%, against a baseline of 57.6% (vector cosine). When the classification is binary, ROOT13 achieves the following results: hypernyms-co-hyponyms (93.4% vs. 60.2%), hypernymsrandom (92.3% vs. 65.5%) and co-hyponyms-random (97.3% vs. 81.5%). Our results are competitive with stateof-the-art models.

cs.CL↗
arXiv2003

An Improved k-Nearest Neighbor Algorithm for Text Categorization

k is the most important parameter in a text categorization system based on k-Nearest Neighbor algorithm (kNN).In the classification process, k nearest documents to the test one in the training set are determined firstly. Then, the predication can be made according to the category distribution among these k nearest neighbors. Generally speaking, the class distribution in the training set is uneven. Some classes may have more samples than others. Therefore, the system performance is very sensitive to the choice of the parameter k. And it is very likely that a fixed k value will result in a bias on large categories. To deal with these problems, we propose an improved kNN algorithm, which uses different numbers of nearest neighbors for different categories, rather than a fixed number across all categories. More samples (nearest neighbors) will be used for deciding whether a test document should be classified to a category, which has more samples in the training set. Preliminary experiments on Chinese text categorization show that our method is less sensitive to the parameter k than the traditional one, and it can properly classify documents belonging to smaller classes with a large k. The method is promising for some cases, where estimating the parameter k via cross-validation is not allowed.

cs.CL↗
arXiv2003

Algebraic K-theory of mapping class groups

We prove that the Fibered Isomorphism Conjecture of T. Farrell and L. Jones holds for various mapping class groups. In many cases, we explicitly calculate the lower algebraic K-groups, showing that they do not always vanish.

math.KT↗
arXiv2002

On QCD Predictions for the Chiral Lagrangian Coefficients

Based on a previous study of deriving the chiral Lagrangian (CL) from QCD, we illustrate the main feature of QCD predictions for the CL coefficients (CLC) in certain approximations. We first show that, in the large-N(c) limit, the anomaly part contributions to the CLC are exactly cancelled by certain terms in the normal part contributions (NPC), so that the final results only concern the remaining NPC depending on QCD interactions. We then do the calculation in a simple approach with further approximations. The obtained CLC and quark condensate are consistent with the experiments.

hep-ph↗
arXiv2002

Farrell cohomology of low genus pure mapping class groups with punctures

In this paper, we calculate the p-torsion of the Farrell cohomology for low genus pure mapping class groups with punctures, where p is an odd prime. Here, `low genus' means g=1,2,3; and `pure mapping class groups with punctures' means the mapping class groups with any number of punctures, where the punctures are not allowed to be permuted. These calculations use our previous results about the periodicity of pure mapping class groups with punctures, as well as other cohomological tools. The low genus cases are interesting because we know that the high genus cases can be reduced to the low genus ones. Also, the cohomological properties of the mapping class groups without punctures are closely related to our cases.

math.AT↗
arXiv2002

Calculation of the Chiral Lagrangian Coefficients from the Underlying Theory of QCD: A Simple Approach

We calculate the coefficients in the chiral Lagrangian approximately from QCD based on a previous study of deriving the chiral Lagrangian from the first principles of QCD in which the chiral Lagrangian coefficients are defined in terms of certain Green's functions in QCD. We first show that, in the large N(c)-limit, the anomaly part contributions to the coefficients are exactly cancelled by certain terms in the normal part contributions, and the final results of the coefficients only concern the remaining normal part contributions depending on QCD interactions. We then do the calculation in a simple approach with the approximations of taking the large-N(c) limit, the leading order in dynamical perturbation theory, and the improved ladder approximation, thereby the relevant Green's functions are expressed in terms of the quark self energy. By solving the Schwinger-Dyson equation for the quark self energy, we obtain the approximate QCD predicted coefficients and the quark condensate which are consistent with the experimental values.

hep-ph↗
arXiv2002

Fermion determinant with dynamical chiral symmetry breaking

One -loop fermion determinant is discussed for the case in which dynamical chiral symmetry breaking caused by momentum dependent fermion self energy $Σ(p^2)$ take place. The obtained series generalizes the heat kernel expansion for hard fermion mass.

hep-ph↗