Transformer models have advanced the state of the art in many Natural Language Processing (NLP) tasks. In this paper, we present a new Transformer architecture, Extended Transformer Construction (ETC), that addresses two key challenges of standard Transformer architectures, namely scaling input length and encoding structured inputs. To scale attention to longer inputs, we introduce a novel global-local attention mechanism between global tokens and regular input tokens. We also show that combining global-local attention with relative position encodings and a Contrastive Predictive Coding (CPC) pre-training objective allows ETC to encode structured inputs. We achieve state-of-the-art results on four natural language datasets requiring long and/or structured inputs.
IIT Madras（印度理工学院马德拉斯分校）；IBM Research（IBM研究院）；Robert Bosch Center for Data Science and Artificial Intelligence, IIT Madras（印度理工学院马德拉斯分校罗伯特·博世数据科学与人工智能中心）
In this work, we focus on the task of generating natural language descriptions from a structured table of facts containing fields (such as nationality, occupation, etc) and values (such as Indian, actor, director, etc). One simple choice is to treat the table as a sequence of fields and values and then use a standard seq2seq model for this task. However, such a model is too generic and does not exploit task-specific characteristics. For example, while generating descriptions from a table, a human would attend to information at two levels: (i) the fields (macro level) and (ii) the values within…
German Cancer Research Center (DKFZ)（德国癌症研究中心（DKFZ））；German Cancer Consortium (DKTK)（德国癌症联盟（DKTK））；Goethe University Frankfurt（法兰克福歌德大学）；Frankfurt Cancer Institute（法兰克福癌症研究所）
Many real-world systems are described not only by data from a single source but via multiple data views. In genomic medicine, for instance, patients can be characterized by data from different molecular layers. Latent variable models with structured sparsity are a commonly used tool for disentangling variation within and across data views. However, their interpretability is cumbersome since it requires a direct inspection and interpretation of each factor from domain experts. Here, we propose MuVI, a novel multi-view latent variable model based on a modified horseshoe prior for modeling struct…
The study of provable adversarial robustness has mostly been limited to classification tasks and models with one-dimensional real-valued outputs. We extend the scope of certifiable robustness to problems with more general and structured outputs like sets, images, language, etc. We model the output space as a metric space under a distance/similarity function, such as intersection-over-union, perceptual similarity, total variation distance, etc. Such models are used in many machine learning problems like image segmentation, object detection, generative models, image/audio-to-text systems, etc. B…
Tokenization Tradeoffs in Structured EHR Foundation Models
Child Health Evaluative Sciences（儿童健康评估科学）；The Hospital for Sick Children（圣迈克尔医院）；University Health Network（大学健康网络）；Department of Medicine（医学部）；Division of Computational Medicine, Department of Medicine（计算医学科，医学部）；Stanford University（斯坦福大学）
NativeTernary: A Self-Delimiting Binary Encoding with Unary Run-Length Hierarchy Markers for Ternary Neural Network Weights, Structured Data, and General Computing Infrastructure
Indian Institute of Technology Bombay（印度理工学院孟买分校）；IIM Udaipur（印度管理学院乌代浦尔分校）
Nanjing University（南京大学）；IBM Thomas J. Watson Research Center（IBM托马斯·J·沃森研究中心）；Squirrel AI Learning（松鼠AI智适应教育）
The celebrated Seq2Seq technique and its numerous variants achieve excellent performance on many tasks such as neural machine translation, semantic parsing, and math word problem solving. However, these models either only consider input objects as sequences while ignoring the important structural information for encoding, or they simply treat output objects as sequence outputs instead of structural objects for decoding. In this paper, we present a novel Graph-to-Tree Neural Networks, namely Graph2Tree consisting of a graph encoder and a hierarchical tree decoder, that encodes an augmented grap…
IIIT Sri City（印度信息技术学院斯里城）；UCLA（加州大学洛杉矶分校）；Wipro AI Labs（威普罗人工智能实验室）；AI Institute, University of South Carolina（南卡罗来纳大学人工智能研究所）
NLP applications for code-mixed (CM) or mix-lingual text have gained a significant momentum recently, the main reason being the prevalence of language mixing in social media communications in multi-lingual societies like India, Mexico, Europe, parts of USA etc. Word embeddings are basic build-ing blocks of any NLP system today, yet, word embedding for CM languages is an unexplored territory. The major bottleneck for CM word embeddings is switching points, where the language switches. These locations lack in contextually and statistical systems fail to model this phenomena due to high variance …
Natural language processing has made significant inroads into learning the semantics of words through distributional approaches, however representations learnt via these methods fail to capture certain kinds of information implicit in the real world. In particular, spatial relations are encoded in a way that is inconsistent with human spatial reasoning and lacking invariance to viewpoint changes. We present a system capable of capturing the semantics of spatial relations such as behind, left of, etc from natural language. Our key contributions are a novel multi-modal objective based on generat…
HiPath: Hierarchical Vision-Language Alignment for Structured Pathology Report Prediction
College of Computer Science and Electronic Engineering, Hunan University（湖南大学计算机科学与电子工程学院）；Department of Bioengineering and Imperial-X, Imperial College London（帝国理工学院伦敦校区生物工程系）；Department of Pathology, Xiangtan Maternal and Child Health Hospital（湘潭 maternal and child health hospital pathology department）；Department of Pathology, The First People’s Hospital of Xiangtan City（湘潭市第一人民医院病理科）
University of Konstanz（康斯坦茨大学）；University of Wuppertal（伍珀塔尔大学）；FIZ Karlsruhe（卡尔斯鲁厄专业信息中心）；George Washington University（乔治华盛顿大学）
In this paper, we show how selecting and combining encodings of natural and mathematical language affect classification and clustering of documents with mathematical content. We demonstrate this by using sets of documents, sections, and abstracts from the arXiv preprint server that are labeled by their subject class (mathematics, computer science, physics, etc.) to compare different encodings of text and formulae and evaluate the performance and runtimes of selected classification and clustering algorithms. Our encodings achieve classification accuracies up to $82.8\%$ and cluster purities up …
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 effective…
Spoken Language Understanding (SLU) converts hypotheses from automatic speech recognizer (ASR) into structured semantic representations. ASR recognition errors can severely degenerate the performance of the subsequent SLU module. To address this issue, word confusion networks (WCNs) have been used to encode the input for SLU, which contain richer information than 1-best or n-best hypotheses list. To further eliminate ambiguity, the last system act of dialogue context is also utilized as additional input. In this paper, a novel BERT based SLU model (WCN-BERT SLU) is proposed to encode WCNs and …
