arXiv research

The paper studies graph products of groups and recovers graph and vertex groups under certain conditions.

New bifurcation found in perturbations of non-generic closed self-shrinkers.

Study on static manifolds with boundary and rigidity of curvature.

This study improves sentence embeddings from BERT models.

The choice of sentence encoder architecture reflects assumptions about how a sentence's meaning is composed from its constituent words. We examine the contribution of these architectures by holding them randomly initialised and fixed, effectively treating them as as hand-crafted language priors, and evaluating the resu…

Framework learns sentence order from paragraphs using attention and transformer networks.

In this work we describe a method to reconstruct the braid monodromy of the preimage of a curve by a Kummer cover. This method is interesting, since it combines two techniques, namely, the reconstruction of a highly non-generic braid monodromy with a systematic method to go from a non-generic to a generic braid monodro…

While neural sequence generation models achieve initial success for many NLP applications, the canonical decoding procedure with left-to-right generation order (i.e., autoregressive) in one-pass can not reflect the true nature of human revising a sentence to obtain a refined result. In this work, we propose XL-Editor, …

Extends positive and almost positive links to successively almost positive ones.

Axis bundles in free-by-cyclic groups have non-generic monodromies.

Diverse and accurate vision+language modeling is an important goal to retain creative freedom and maintain user engagement. However, adequately capturing the intricacies of diversity in language models is challenging. Recent works commonly resort to latent variable models augmented with more or less supervision from ob…

In this paper we explore the "vector semantics" problem from the perspective of "almost orthogonal" property of high-dimensional random vectors. We show that this intriguing property can be used to "memorize" random vectors by simply adding them, and we provide an efficient probabilistic solution to the set membership …

Neural language models are a critical component of state-of-the-art systems for machine translation, summarization, audio transcription, and other tasks. These language models are almost universally autoregressive in nature, generating sentences one token at a time from left to right. This paper studies the influence o…

Recent state-of-the-art natural language understanding models, such as BERT and XLNet, score a pair of sentences (A and B) using multiple cross-attention operations - a process in which each word in sentence A attends to all words in sentence B and vice versa. As a result, computing the similarity between a query sente…

An oriented link is positive if it has a link diagram whose crossings are all positive. An oriented link is almost positive if it is not positive and has a link diagram with exactly one negative crossing. It is known that the Rasmussen invariant, $4$-genus and $3$-genus of a positive knot are equal. In this paper, we p…

Estimating the difficulty level of math word problems is an important task for many educational applications. Identification of relevant and irrelevant sentences in math word problems is an important step for calculating the difficulty levels of such problems. This paper addresses a novel application of text categoriza…

New metrics predict human sentence comprehension across languages.

Given vector representations for individual words, it is necessary to compute vector representations of sentences for many applications in a compositional manner, often using artificial neural networks. Relatively little work has explored the internal structure and properties of such sentence vectors. In this paper, we…

Existing models based on artificial neural networks (ANNs) for sentence classification often do not incorporate the context in which sentences appear, and classify sentences individually. However, traditional sentence classification approaches have been shown to greatly benefit from jointly classifying subsequent sente…

We characterize positive links in terms of strong quasipositivity, homogeneity and the value of Rasmussen, Beliakova and Wehrli's $s$-invariant. We also study almost positive links, in particular, determine the $s$-invariants of almost positive links. This result suggests that all almost positive links might be strongl…

In this paper, we show that a link which has a positive and almost alternating diagram is alternating, besides that a positive and non-alternating Montesinos link has an almost positive-alternating diagram.

Study of new link types and their invariants, extending previous results.

Gradient descent struggles to achieve zero loss in deep learning models due to non-generic data distributions.

We propose a new generative model of sentences that first samples a prototype sentence from the training corpus and then edits it into a new sentence. Compared to traditional models that generate from scratch either left-to-right or by first sampling a latent sentence vector, our prototype-then-edit model improves perp…

Paper proposes a novel model to improve n-ary cross-sentence relation extraction by addressing noisy data and non-consecutive sentences.

The extrinsic Bonnet-Myers theorem is proven for positive Ricci curvature manifolds.

A Riemannian manifold is called almost positively curved if the set of points for which all $2$-planes have positive sectional curvature is open and dense. We find three new examples of almost positively curved manifolds: $Sp(3)/Sp(1)^2$, and two circle quotients of $Sp(3)/Sp(1)^2$. We also show the quasi-positively cu…

An important part of the information gathering and data analysis is to find out what people think about, either a product or an entity. Twitter is an opinion rich social networking site. The posts or tweets from this data can be used for mining people's opinions. The recent surge of activity in this area can be attribu…

Using the Fiedler-Polyak-Viro Gauss diagram formulas we study the Vassiliev invariants of degree 2 and 3 on almost positive knots. As a consequence we show that the number of almost positive knots of given genus or unknotting number grows polynomially in the crossing number, and also recover and extend, inter alia to t…

We show that the unit tangent bundle of S^4 and a real cohomology CP^3 admit Riemannian metrics with positive sectional curvature almost everywhere. These are the only examples so far with positive curvature almost everywhere that are not also known to admit positive curvature.

Distributed representations of sentences have become ubiquitous in natural language processing tasks. In this paper, we consider a continual learning scenario for sentence representations: Given a sequence of corpora, we aim to optimize the sentence encoder with respect to the new corpus while maintaining its accuracy …

In real-world applications of natural language generation, there are often constraints on the target sentences in addition to fluency and naturalness requirements. Existing language generation techniques are usually based on recurrent neural networks (RNNs). However, it is non-trivial to impose constraints on RNNs whil…

Positivity of intersections in 4-manifolds leads to taming symplectic structures.

Unsupervised scheme ranks sentences in text documents based on semantic importance.

In the sentence classification task, context formed from sentences adjacent to the sentence being classified can provide important information for classification. This context is, however, often ignored. Where methods do make use of context, only small amounts are considered, making it difficult to scale. We present a …

New bounds on Jones polynomial positivity for specific links.

Bayesian EnKF improves sentence comprehension uncertainty modeling.

We train multi-task autoencoders on linguistic tasks and analyze the learned hidden sentence representations. The representations change significantly when translation and part-of-speech decoders are added. The more decoders a model employs, the better it clusters sentences according to their syntactic similarity, as t…

A Riemannian manifold is said to be almost positively curved if the sets of points for which all $2$-planes have positive sectional curvature is open and dense. We show that the Grassmannian of oriented $2$-planes in $\mathbb{R}^7$ admits a metric of almost positive curvature, giving the first example of an almost posi…

We formulate coherence modeling as a regression task and propose two novel methods to combine techniques from our setup with pairwise approaches. The first of our methods is a model that we call "first-next," which operates similarly to selection sorting but conditions decision-making on information about already-sorte…

A graph model improves short text classification by integrating sentence relationships.

New findings show that not all area-minimizing surfaces are calibrated, even on complex manifolds.

SFBoW provides sentence embeddings with predefined dimensions.

We prove that Ricci flows with almost maximal extinction time must be nearly round, provided that they have positive isotropic curvature when crossed with $\mathbb{R}^{2}$. As an application, we show that positively curved metrics on $S^{3}$ and $RP^{3}$ with almost maximal width must be nearly round.

Existing relation classification methods that rely on distant supervision assume that a bag of sentences mentioning an entity pair are all describing a relation for the entity pair. Such methods, performing classification at the bag level, cannot identify the mapping between a relation and a sentence, and largely suffe…

We study twistor forms on products of compact Riemannian manifolds and show that they are defined by Killing forms on the factors. The main result of this note is a necessary step in the classification of compact Riemannian manifolds with non-generic holonomy carrying twistor forms.

Case Law has a significant impact on the proceedings of legal cases. Therefore, the information that can be obtained from previous court cases is valuable to lawyers and other legal officials when performing their duties. This paper describes a methodology of applying discourse relations between sentences when processi…

We introduce the Attentive Unsupervised Text (W)riter (AUTR), which is a word level generative model for natural language. It uses a recurrent neural network with a dynamic attention and canvas memory mechanism to iteratively construct sentences. By viewing the state of the memory at intermediate stages and where the m…