Abstract

TeV-scale vector-like quarks (VLQs) are an essential ingredient of many new physics models. Because of their vectorlike nature, they do not contribute to the gauge anomalies and are less restricted than their chiral counterparts by the current experimental data. Ones that couple with the thirdgeneration quarks (top and bottom partners, we shall collectively refer to them as top partners) appear in composite Higgs models with a partially-composite top quark [1– 6], extra-dimensional models [7–11], Little-Higgs models [12–15], etc. However, in the last few years, an extensive direct search program at the LHC has gradually tightened the mass bounds on these quarks. For top partners like the T quark (with electromagnetic charge 2/3) or the B quark (with charge −1/3), the current exclusion limit stands as high as ∼ 1.5 TeV [16–20]. The direct VLQ searches generally assume that they decay exclusively to Standard Model (SM) particles, i.e., to a third-generation quark and a heavy vector-boson or a Higgs. However, this assumption need not hold in general, especially if one looks beyond the minimal models where the top partners can have new decay modes. For example, a top partner can decay to another heavy quark or a new boson [11, 21–43]. A possibility that has attracted some interest in the current literature is that a vector-like top partner decays to a new spinless state singlet under the SM gauge group [i.e., (1, 1, 0) under SU(3)c×SU(2)L ×U(1)Y ] and a third-generation quark. The singlet state could be

Abstract

Ankyrin is one of the most abundant protein repeat families found across all forms of life. It is found in a variety of multi-domain and single domain proteins in humans with diverse number of repeating units. They are observed to occur in several functionally diverse proteins, such as transcriptional initiators, cell cycle regulators, cytoskeletal organizers, ion transporters, signal transducers, developmental regulators, and toxins, and, consequently, defects in ankyrin repeat proteins have been associated with a number of human diseases. In this study, we have classified the human ankyrin proteins into clusters based on the sequence similarity in their ankyrin repeat domains. We analyzed the amino acid compositional bias and consensus ankyrin motif sequence of the clusters to understand the diversity of the human ankyrin proteins. We carried out network-based structural analysis of human ankyrin proteins across different clusters and showed the association of conserved residues with topologically important residues identified by network centrality measures. The analysis of conserved and structurally important residues helps in understanding their role in structural stability and function of these proteins. In this paper, we also discuss the significance of these conserved residues in disease association across the human ankyrin protein clusters.

Abstract

Periodic pattern mining is an emerging technique for knowledge discovery. Most previous approaches have aimed to find only those patterns that exhibit full (or perfect) periodic behavior in databases. Consequently, the existing approaches miss interesting patterns that exhibit partial periodic behavior in a database. With this motivation, this paper proposes a novel model for finding partial periodic patterns that may exist in temporal databases. An efficient pattern-growth algorithm, called Partial Periodic Pattern-growth (3P-growth), is also presented, which can effectively find all desired patterns within a database. Substantial experiments on both real-world and synthetic databases showed that our algorithm is not only efficient in terms of memory and runtime, but is also highly scalable. Finally, the effectiveness of our patterns is demonstrated using two case studies. In the first case study, our model was employed to identify the highly polluted areas in Japan. In the second case study, our model was employed to identify the road segments on which people regularly face traffic congestion.

Abstract

Existing Math Word Problem (MWP) solvers have achieved high accuracy on benchmark datasets. However, prior works have shown that such solvers do not generalize well and rely on superficial cues to achieve high performance. In this paper, we first conduct experiments to showcase that this behaviour is mainly associated with the limited size and diversity present in existing MWP datasets. Next, we propose several data augmentation techniques broadly categorized into Substitution and Paraphrasing based methods. By deploying these methods we increase the size of existing datasets by five folds. Extensive experiments on two benchmark datasets across three state-of-the-art MWP solvers show that proposed methods increase the generalization and robustness of existing solvers. On average, proposed methods significantly increase the state-of-the-art results by over five percentage points on benchmark datasets. Further, the solvers trained on the augmented dataset perform comparatively better on the challenge test set. We also show the effectiveness of proposed techniques through ablation studies and verify the quality of augmented samples through human evaluation.

Abstract

We investigate the task of complex NER for the English language. The task is non-trivial due to the semantic ambiguity of the textual structure and the rarity of occurrence of such entities in the prevalent literature. Using pretrained language models such as BERT, we obtain a competitive performance on this task. We qualitatively analyze the performance of multiple architectures for this task. All our models are able to outperform the baseline by a significant margin. Our best performing model beats the baseline F1-score by over 9%.

Abstract

The Securities and Exchange Board of India is the regulatory body for securities and commodity market in India. A growing number of SEBI documents ranging from government regulations to legal case files are now available in the digital form. Advances in natural language processing and machine learning provide opportunities for extracting semantic insights from these documents. We present here a system that performs semantic processing of SEBI documents using state-of-the-art language models to produce enriched regulations containing timelines of amendments and cross references to legal case files.

Abstract

The Securities and Exchange Board of India (SEBI) is the regulatory body for securities and commodities in India. SEBI creates, and enforces regulations that must be followed by all listed companies. To the best of our knowledge, this is the first work on identifying the regulation (s) that a SEBI-related case violates, which could be of substantial value to companies, lawyers, and other stakeholders in the regulatory process. We create a dataset for this task by automatically extracting violations from publicly available case-files. Using this data, we explore various multi-label text classification methods to determine the potentially multiple regulations violated by (the facts of) a case. Our experiments demonstrate the importance of employing contextual text representations to understand complex financial and legal concepts. We also highlight the challenges that must be addressed to develop a fully functional system in the real-world.

Abstract

Several popular Transformer based language models have been found to be successful for text-driven brain encoding. However, existing literature leverages only pretrained text Transformer models and has not explored the efficacy of task-specific learned Transformer representations. In this work, we explore transfer learning from representations learned for ten popular natural language processing tasks (two syntactic and eight semantic) for predicting brain responses from two diverse datasets: Pereira (subjects reading sentences from paragraphs) and Narratives (subjects listening to the spoken stories). Encoding models based on task features are used to predict activity in different regions across the whole brain. Features from coreference resolution, NER, and shallow syntax parsing explain greater variance for the reading activity. On the other hand, for the listening activity, tasks such as paraphrase generation, summarization, and natural language inference show better encoding performance. Experiments across all 10 task representations provide the following cognitive insights: (i) language left hemisphere has higher predictive brain activity versus language right hemisphere, (ii) posterior medial cortex, temporoparieto-occipital junction, dorsal frontal lobe have higher correlation versus early auditory and auditory association cortex, (iii) syntactic and semantic tasks display a good predictive performance across brain region

Abstract

How the brain captures the meaning of linguistic stimuli across multiple views is still a critical open question in neuroscience. Consider three different views of the concept apartment: (1) picture (WP) presented with the target word label, (2) sentence (S) using the target word, and (3) word cloud (WC) containing the target word along with other semantically related words. Unlike previous efforts, which focus only on single view analysis, in this paper, we study the effectiveness of brain decoding in a zero-shot cross-view learning setup. Further, we propose brain decoding in the novel context of cross-view-translation tasks like image captioning (IC), image tagging (IT), keyword extraction (KE), and sentence formation (SF). Using extensive experiments, we demonstrate that cross-view zero-shot brain decoding is practical leading to ∼0.68 average pairwise accuracy across view pairs. Also, the decoded representations are sufficiently detailed to enable high accuracy for cross-view-translation tasks with following pairwise accuracy: IC (78.0), IT (83.0), KE (83.7) and SF (74.5).

Abstract

Enabling effective brain-computer interfaces requires understanding how the human brain encodes stimuli across modalities such as visual, language (or text), etc. Brain encoding aims at constructing fMRI brain activity given a stimulus. There exists a plethora of neural encoding models which study brain encoding for single mode stimuli: visual (pretrained CNNs) or text (pretrained language models). Few recent papers have also obtained separate visual and text representation models and performed late-fusion using simple heuristics. However, previous work has failed to explore: (a) the effectiveness of image Transformer models for encoding visual stimuli, and (b) co-attentive multi-modal modeling for visual and text reasoning. In this paper, we systematically explore the efficacy of image Transformers (ViT, DEiT, and BEiT) and multi-modal Transformers (VisualBERT, LXMERT, and CLIP) for brain encoding. Extensive experiments on two popular datasets, BOLD5000 and Pereira, provide the following insights. (1) To the best of our knowledge, we are the first to investigate the effectiveness of image and multi-modal Transformers for brain encoding. (2) We find that VisualBERT, a multi-modal Transformer, significantly outperforms previously proposed single-mode CNNs, image Transformers as well as other previously proposed multi-modal models, thereby establishing new state-of-theart. The supremacy of visio-linguistic models raises the question of whether the responses elicited in the visual regions are affected implicitly by linguistic processing even when passively viewing images. Future fMRI tasks can verify this computational insight in an appropriate experimental setting.