当前期刊: arXiv - CS - Computation and Language Go to current issue    加入关注   
显示样式:        排序: IF: - GO 导出
我的关注
我的收藏
您暂时未登录!
登录
  • A Pattern-mining Driven Study on Differences of Newspapers in Expressing Temporal Information
    arXiv.cs.CL Pub Date : 2020-11-24
    Yingxue Fu; Elaine Ui Dhonnchadha

    This paper studies the differences between different types of newspapers in expressing temporal information, which is a topic that has not received much attention. Techniques from the fields of temporal processing and pattern mining are employed to investigate this topic. First, a corpus annotated with temporal information is created by the author. Then, sequences of temporal information tags mixed

    更新日期:2020-11-25
  • Cross-Document Event Coreference Resolution Beyond Corpus-Tailored Systems
    arXiv.cs.CL Pub Date : 2020-11-24
    Michael Bugert; Nils Reimers; Iryna Gurevych

    Cross-document event coreference resolution (CDCR) is an NLP task in which mentions of events need to be identified and clustered throughout a collection of documents. CDCR aims to benefit downstream multi-document applications, but despite recent progress on corpora and model development, downstream improvements from applying CDCR have not been shown yet. The reason lies in the fact that every CDCR

    更新日期:2020-11-25
  • Neural Text Classification by Jointly Learning to Cluster and Align
    arXiv.cs.CL Pub Date : 2020-11-24
    Yekun Chai; Haidong Zhang; Shuo Jin

    Distributional text clustering delivers semantically informative representations and captures the relevance between each word and semantic clustering centroids. We extend the neural text clustering approach to text classification tasks by inducing cluster centers via a latent variable model and interacting with distributional word embeddings, to enrich the representation of tokens and measure the relatedness

    更新日期:2020-11-25
  • Generating Intelligible Plumitifs Descriptions: Use Case Application with Ethical Considerations
    arXiv.cs.CL Pub Date : 2020-11-24
    David Beauchemin; Nicolas Garneau; Eve Gaumond; Pierre-Luc Déziel; Richard Khoury; Luc Lamontagne

    Plumitifs (dockets) were initially a tool for law clerks. Nowadays, they are used as summaries presenting all the steps of a judicial case. Information concerning parties' identity, jurisdiction in charge of administering the case, and some information relating to the nature and the course of the preceding are available through plumitifs. They are publicly accessible but barely understandable; they

    更新日期:2020-11-25
  • Domain-Transferable Method for Named Entity Recognition Task
    arXiv.cs.CL Pub Date : 2020-11-24
    Vladislav Mikhailov; Tatiana Shavrina

    Named Entity Recognition (NER) is a fundamental task in the fields of natural language processing and information extraction. NER has been widely used as a standalone tool or an essential component in a variety of applications such as question answering, dialogue assistants and knowledge graphs development. However, training reliable NER models requires a large amount of labelled data which is expensive

    更新日期:2020-11-25
  • Tight Integrated End-to-End Training for Cascaded Speech Translation
    arXiv.cs.CL Pub Date : 2020-11-24
    Parnia Bahar; Tobias Bieschke; Ralf Schlüter; Hermann Ney

    A cascaded speech translation model relies on discrete and non-differentiable transcription, which provides a supervision signal from the source side and helps the transformation between source speech and target text. Such modeling suffers from error propagation between ASR and MT models. Direct speech translation is an alternative method to avoid error propagation; however, its performance is often

    更新日期:2020-11-25
  • Two-Way Neural Machine Translation: A Proof of Concept for Bidirectional Translation Modeling using a Two-Dimensional Grid
    arXiv.cs.CL Pub Date : 2020-11-24
    Parnia Bahar; Christopher Brix; Hermann Ney

    Neural translation models have proven to be effective in capturing sufficient information from a source sentence and generating a high-quality target sentence. However, it is not easy to get the best effect for bidirectional translation, i.e., both source-to-target and target-to-source translation using a single model. If we exclude some pioneering attempts, such as multilingual systems, all other

    更新日期:2020-11-25
  • Gender bias in magazines oriented to men and women: a computational approach
    arXiv.cs.CL Pub Date : 2020-11-24
    Diego Kozlowski; Gabriela Lozano; Carla M. Felcher; Fernando Gonzalez; Edgar Altszyler

    Cultural products are a source to acquire individual values and behaviours. Therefore, the differences in the content of the magazines aimed specifically at women or men are a means to create and reproduce gender stereotypes. In this study, we compare the content of a women-oriented magazine with that of a men-oriented one, both produced by the same editorial group, over a decade (2008-2018). With

    更新日期:2020-11-25
  • Unequal Representations: Analyzing Intersectional Biases in Word Embeddings Using Representational Similarity Analysis
    arXiv.cs.CL Pub Date : 2020-11-24
    Michael A. Lepori

    We present a new approach for detecting human-like social biases in word embeddings using representational similarity analysis. Specifically, we probe contextualized and non-contextualized embeddings for evidence of intersectional biases against Black women. We show that these embeddings represent Black women as simultaneously less feminine than White women, and less Black than Black men. This finding

    更新日期:2020-11-25
  • Tackling Domain-Specific Winograd Schemas with Knowledge-Based Reasoning and Machine Learning
    arXiv.cs.CL Pub Date : 2020-11-24
    Suk Joon Hong; Brandon Bennett

    The Winograd Schema Challenge (WSC) is a common-sense reasoning task that requires background knowledge. In this paper, we contribute to tackling WSC in four ways. Firstly, we suggest a keyword method to define a restricted domain where distinctive high-level semantic patterns can be found. A thanking domain was defined by key-words, and the data set in this domain is used in our experiments. Secondly

    更新日期:2020-11-25
  • Picking BERT's Brain: Probing for Linguistic Dependencies in Contextualized Embeddings Using Representational Similarity Analysis
    arXiv.cs.CL Pub Date : 2020-11-24
    Michael A. Lepori; R. Thomas McCoy

    As the name implies, contextualized representations of language are typically motivated by their ability to encode context. Which aspects of context are captured by such representations? We introduce an approach to address this question using Representational Similarity Analysis (RSA). As case studies, we investigate the degree to which a verb embedding encodes the verb's subject, a pronoun embedding

    更新日期:2020-11-25
  • Argument from Old Man's View: Assessing Social Bias in Argumentation
    arXiv.cs.CL Pub Date : 2020-11-24
    Maximilian Spliethöver; Henning Wachsmuth

    Social bias in language - towards genders, ethnicities, ages, and other social groups - poses a problem with ethical impact for many NLP applications. Recent research has shown that machine learning models trained on respective data may not only adopt, but even amplify the bias. So far, however, little attention has been paid to bias in computational argumentation. In this paper, we study the existence

    更新日期:2020-11-25
  • GLGE: A New General Language Generation Evaluation Benchmark
    arXiv.cs.CL Pub Date : 2020-11-24
    Dayiheng Liu; Yu Yan; Yeyun Gong; Weizhen Qi; Hang Zhang; Jian Jiao; Weizhu Chen; Jie Fu; Linjun Shou; Ming Gong; Pengcheng Wang; Jiusheng Chen; Daxin Jiang; Jiancheng Lv; Ruofei Zhang; Winnie Wu; Ming Zhou; Nan Duan

    Multi-task benchmarks such as GLUE and SuperGLUE have driven great progress of pretraining and transfer learning in Natural Language Processing (NLP). These benchmarks mostly focus on a range of Natural Language Understanding (NLU) tasks, without considering the Natural Language Generation (NLG) models. In this paper, we present the General Language Generation Evaluation (GLGE), a new multi-task benchmark

    更新日期:2020-11-25
  • Dual Supervision Framework for Relation Extraction with Distant Supervision and Human Annotation
    arXiv.cs.CL Pub Date : 2020-11-24
    Woohwan Jung; Kyuseok Shim

    Relation extraction (RE) has been extensively studied due to its importance in real-world applications such as knowledge base construction and question answering. Most of the existing works train the models on either distantly supervised data or human-annotated data. To take advantage of the high accuracy of human annotation and the cheap cost of distant supervision, we propose the dual supervision

    更新日期:2020-11-25
  • Acoustic span embeddings for multilingual query-by-example search
    arXiv.cs.CL Pub Date : 2020-11-24
    Yushi Hu; Shane Settle; Karen Livescu

    Query-by-example (QbE) speech search is the task of matching spoken queries to utterances within a search collection. In low- or zero-resource settings, QbE search is often addressed with approaches based on dynamic time warping (DTW). Recent work has found that methods based on acoustic word embeddings (AWEs) can improve both performance and search speed. However, prior work on AWE-based QbE has primarily

    更新日期:2020-11-25
  • Advancing Humor-Focused Sentiment Analysis through Improved Contextualized Embeddings and Model Architecture
    arXiv.cs.CL Pub Date : 2020-11-23
    Felipe Godoy

    Humor is a natural and fundamental component of human interactions. When correctly applied, humor allows us to express thoughts and feelings conveniently and effectively, increasing interpersonal affection, likeability, and trust. However, understanding the use of humor is a computationally challenging task from the perspective of humor-aware language processing models. As language models become ubiquitous

    更新日期:2020-11-25
  • Multi-task Language Modeling for Improving Speech Recognition of Rare Words
    arXiv.cs.CL Pub Date : 2020-11-23
    Chao-Han Huck Yang; Linda Liu; Ankur Gandhe; Yile Gu; Anirudh Raju; Denis Filimonov; Ivan Bulyko

    End-to-end automatic speech recognition (ASR) systems are increasingly popular due to their relative architectural simplicity and competitive performance. However, even though the average accuracy of these systems may be high, the performance on rare content words often lags behind hybrid ASR systems. To address this problem, second-pass rescoring is often applied. In this paper, we propose a second-pass

    更新日期:2020-11-25
  • Using Machine Learning and Natural Language Processing Techniques to Analyze and Support Moderation of Student Book Discussions
    arXiv.cs.CL Pub Date : 2020-11-23
    Jernej Vivod

    The increasing adoption of technology to augment or even replace traditional face-to-face learning has led to the development of a myriad of tools and platforms aimed at engaging the students and facilitating the teacher's ability to present new information. The IMapBook project aims at improving the literacy and reading comprehension skills of elementary school-aged children by presenting them with

    更新日期:2020-11-25
  • Does BERT Understand Sentiment? Leveraging Comparisons Between Contextual and Non-Contextual Embeddings to Improve Aspect-Based Sentiment Models
    arXiv.cs.CL Pub Date : 2020-11-23
    Natesh Reddy; Pranaydeep Singh; Muktabh Mayank Srivastava

    When performing Polarity Detection for different words in a sentence, we need to look at the words around to understand the sentiment. Massively pretrained language models like BERT can encode not only just the words in a document but also the context around the words along with them. This begs the questions, "Does a pretrain language model also automatically encode sentiment information about each

    更新日期:2020-11-25
  • Fuzzy Stochastic Timed Petri Nets for Causal properties representation
    arXiv.cs.CL Pub Date : 2020-11-24
    Alejandro Sobrino; Eduardo C. Garrido-Merchan; Cristina Puente

    Imagery is frequently used to model, represent and communicate knowledge. In particular, graphs are one of the most powerful tools, being able to represent relations between objects. Causal relations are frequently represented by directed graphs, with nodes denoting causes and links denoting causal influence. A causal graph is a skeletal picture, showing causal associations and impact between entities

    更新日期:2020-11-25
  • A Robotic Dating Coaching System Leveraging Online Communities Posts
    arXiv.cs.CL Pub Date : 2020-11-24
    Sihyeon Jo; Donghwi Jung; Keonwoo Kim; Eun Gyo Joung; Giulia Nespoli; Seungryong Yoo; Minseob So; Seung-Woo Seo; Seong-Woo Kim

    Can a robot be a personal dating coach? Even with the increasing amount of conversational data on the internet, the implementation of conversational robots remains a challenge. In particular, a detailed and professional counseling log is expensive and not publicly accessible. In this paper, we develop a robot dating coaching system leveraging corpus from online communities. We examine people's perceptions

    更新日期:2020-11-25
  • Multimodal Pretraining for Dense Video Captioning
    arXiv.cs.CL Pub Date : 2020-11-10
    Gabriel Huang; Bo Pang; Zhenhai Zhu; Clara Rivera; Radu Soricut

    Learning specific hands-on skills such as cooking, car maintenance, and home repairs increasingly happens via instructional videos. The user experience with such videos is known to be improved by meta-information such as time-stamped annotations for the main steps involved. Generating such annotations automatically is challenging, and we describe here two relevant contributions. First, we construct

    更新日期:2020-11-25
  • Streaming Multi-speaker ASR with RNN-T
    arXiv.cs.CL Pub Date : 2020-11-23
    Ilya Sklyar; Anna Piunova; Yulan Liu

    Recent research shows end-to-end ASR systems can recognize overlapped speech from multiple speakers. However, all published works have assumed no latency constraints during inference, which does not hold for most voice assistant interactions. This work focuses on multi-speaker speech recognition based on a recurrent neural network transducer (RNN-T) that has been shown to provide high recognition accuracy

    更新日期:2020-11-25
  • The Zero Resource Speech Benchmark 2021: Metrics and baselines for unsupervised spoken language modeling
    arXiv.cs.CL Pub Date : 2020-11-23
    Tu Anh Nguyen; Maureen de Seyssel; Patricia Rozé; Morgane Rivière; Evgeny Kharitonov; Alexei Baevski; Ewan Dunbar; Emmanuel Dupoux

    We introduce a new unsupervised task, spoken language modeling: the learning of linguistic representations from raw audio signals without any labels, along with the Zero Resource Speech Benchmark 2021: a suite of 4 black-box, zero-shot metrics probing for the quality of the learned models at 4 linguistic levels: phonetics, lexicon, syntax and semantics. We present the results and analyses of a composite

    更新日期:2020-11-25
  • Studying Taxonomy Enrichment on Diachronic WordNet Versions
    arXiv.cs.CL Pub Date : 2020-11-23
    Irina Nikishina; Alexander Panchenko; Varvara Logacheva; Natalia Loukachevitch

    Ontologies, taxonomies, and thesauri are used in many NLP tasks. However, most studies are focused on the creation of these lexical resources rather than the maintenance of the existing ones. Thus, we address the problem of taxonomy enrichment. We explore the possibilities of taxonomy extension in a resource-poor setting and present methods which are applicable to a large number of languages. We create

    更新日期:2020-11-25
  • An Online Multilingual Hate speech Recognition System
    arXiv.cs.CL Pub Date : 2020-11-23
    Neeraj Vashistha; Arkaitz Zubiaga

    The exponential increase in the use of the Internet and social media over the last two decades has changed human interaction. This has led to many positive outcomes, but at the same time it has brought risks and harms. While the volume of harmful content online, such as hate speech, is not manageable by humans, interest in the academic community to investigate automated means for hate speech detection

    更新日期:2020-11-25
  • Unsupervised Domain Adaptation of a Pretrained Cross-Lingual Language Model
    arXiv.cs.CL Pub Date : 2020-11-23
    Juntao Li; Ruidan He; Hai Ye; Hwee Tou Ng; Lidong Bing; Rui Yan

    Recent research indicates that pretraining cross-lingual language models on large-scale unlabeled texts yields significant performance improvements over various cross-lingual and low-resource tasks. Through training on one hundred languages and terabytes of texts, cross-lingual language models have proven to be effective in leveraging high-resource languages to enhance low-resource language processing

    更新日期:2020-11-25
  • Bi-ISCA: Bidirectional Inter-Sentence Contextual Attention Mechanism for Detecting Sarcasm in User Generated Noisy Short Text
    arXiv.cs.CL Pub Date : 2020-11-23
    Prakamya Mishra; Saroj Kaushik; Kuntal Dey

    Many online comments on social media platforms are hateful, humorous, or sarcastic. The sarcastic nature of these comments (especially the short ones) alters their actual implied sentiments, which leads to misinterpretations by the existing sentiment analysis models. A lot of research has already been done to detect sarcasm in the text using user-based, topical, and conversational information but not

    更新日期:2020-11-25
  • STEPs-RL: Speech-Text Entanglement for Phonetically Sound Representation Learning
    arXiv.cs.CL Pub Date : 2020-11-23
    Prakamya Mishra

    In this paper, we present a novel multi-modal deep neural network architecture that uses speech and text entanglement for learning phonetically sound spoken-word representations. STEPs-RL is trained in a supervised manner to predict the phonetic sequence of a target spoken-word using its contextual spoken word's speech and text, such that the model encodes its meaningful latent representations. Unlike

    更新日期:2020-11-25
  • Evaluating Input Representation for Language Identification in Hindi-English Code Mixed Text
    arXiv.cs.CL Pub Date : 2020-11-23
    Ramchandra Joshi; Raviraj Joshi

    Natural language processing (NLP) techniques have become mainstream in the recent decade. Most of these advances are attributed to the processing of a single language. More recently, with the extensive growth of social media platforms focus has shifted to code-mixed text. The code-mixed text comprises text written in more than one language. People naturally tend to combine local language with global

    更新日期:2020-11-25
  • Employing distributional semantics to organize task-focused vocabulary learning
    arXiv.cs.CL Pub Date : 2020-11-22
    Haemanth Santhi Ponnusamy; Detmar Meurers

    How can a learner systematically prepare for reading a book they are interested in? In this paper,we explore how computational linguistic methods such as distributional semantics, morphological clustering, and exercise generation can be combined with graph-based learner models to answer this question both conceptually and in practice. Based on the highly structured learner model and concepts from network

    更新日期:2020-11-25
  • Cross-Domain Generalization Through Memorization: A Study of Nearest Neighbors in Neural Duplicate Question Detection
    arXiv.cs.CL Pub Date : 2020-11-22
    Yadollah Yaghoobzadeh; Alexandre Rochette; Timothy J. Hazen

    Duplicate question detection (DQD) is important to increase efficiency of community and automatic question answering systems. Unfortunately, gathering supervised data in a domain is time-consuming and expensive, and our ability to leverage annotations across domains is minimal. In this work, we leverage neural representations and study nearest neighbors for cross-domain generalization in DQD. We first

    更新日期:2020-11-25
  • Standardizing linguistic data: method and tools for annotating (pre-orthographic) French
    arXiv.cs.CL Pub Date : 2020-11-22
    Simon GabayUNIGE; Thibault ClériceENC; Jean-Baptiste CampsENC; Jean-Baptiste TanguySU; Matthias Gille-LevensonENS Lyon

    With the development of big corpora of various periods, it becomes crucial to standardise linguistic annotation (e.g. lemmas, POS tags, morphological annotation) to increase the interoperability of the data produced, despite diachronic variations. In the present paper, we describe both methodologically (by proposing annotation principles) and technically (by creating the required training data and

    更新日期:2020-11-25
  • Sensing Ambiguity in Henry James' "The Turn of the Screw"
    arXiv.cs.CL Pub Date : 2020-11-21
    Victor Makarenkov; Yael Segalovitz

    Fields such as the philosophy of language, continental philosophy, and literary studies have long established that human language is, at its essence, ambiguous and that this quality, although challenging to communication, enriches language and points to the complexity of human thought. On the other hand, in the NLP field there have been ongoing efforts aimed at disambiguation for various downstream

    更新日期:2020-11-25
  • Evaluating Semantic Accuracy of Data-to-Text Generation with Natural Language Inference
    arXiv.cs.CL Pub Date : 2020-11-21
    Ondřej Dušek; Zdeněk Kasner

    A major challenge in evaluating data-to-text (D2T) generation is measuring the semantic accuracy of the generated text, i.e. checking if the output text contains all and only facts supported by the input data. We propose a new metric for evaluating the semantic accuracy of D2T generation based on a neural model pretrained for natural language inference (NLI). We use the NLI model to check textual entailment

    更新日期:2020-11-25
  • LRTA: A Transparent Neural-Symbolic Reasoning Framework with Modular Supervision for Visual Question Answering
    arXiv.cs.CL Pub Date : 2020-11-21
    Weixin Liang; Feiyang Niu; Aishwarya Reganti; Govind Thattai; Gokhan Tur

    The predominant approach to visual question answering (VQA) relies on encoding the image and question with a "black-box" neural encoder and decoding a single token as the answer like "yes" or "no". Despite this approach's strong quantitative results, it struggles to come up with intuitive, human-readable forms of justification for the prediction process. To address this insufficiency, we reformulate

    更新日期:2020-11-25
  • Athena: Constructing Dialogues Dynamically with Discourse Constraints
    arXiv.cs.CL Pub Date : 2020-11-21
    Vrindavan Harrison; Juraj Juraska; Wen Cui; Lena Reed; Kevin K. Bowden; Jiaqi Wu; Brian Schwarzmann; Abteen Ebrahimi; Rishi Rajasekaran; Nikhil Varghese; Max Wechsler-Azen; Steve Whittaker; Jeffrey Flanigan; Marilyn Walker

    This report describes Athena, a dialogue system for spoken conversation on popular topics and current events. We develop a flexible topic-agnostic approach to dialogue management that dynamically configures dialogue based on general principles of entity and topic coherence. Athena's dialogue manager uses a contract-based method where discourse constraints are dispatched to clusters of response generators

    更新日期:2020-11-25
  • Self-Supervised learning with cross-modal transformers for emotion recognition
    arXiv.cs.CL Pub Date : 2020-11-20
    Aparna Khare; Srinivas Parthasarathy; Shiva Sundaram

    Emotion recognition is a challenging task due to limited availability of in-the-wild labeled datasets. Self-supervised learning has shown improvements on tasks with limited labeled datasets in domains like speech and natural language. Models such as BERT learn to incorporate context in word embeddings, which translates to improved performance in downstream tasks like question answering. In this work

    更新日期:2020-11-25
  • What do we expect from Multiple-choice QA Systems?
    arXiv.cs.CL Pub Date : 2020-11-20
    Krunal Shah; Nitish Gupta; Dan Roth

    The recent success of machine learning systems on various QA datasets could be interpreted as a significant improvement in models' language understanding abilities. However, using various perturbations, multiple recent works have shown that good performance on a dataset might not indicate performance that correlates well with human's expectations from models that "understand" language. In this work

    更新日期:2020-11-25
  • Interpretable Visual Reasoning via Induced Symbolic Space
    arXiv.cs.CL Pub Date : 2020-11-23
    Zhonghao Wang; Mo Yu; Kai Wang; Jinjun Xiong; Wen-mei Hwu; Mark Hasegawa-Johnson; Humphrey Shi

    We study the problem of concept induction in visual reasoning, i.e., identifying concepts and their hierarchical relationships from question-answer pairs associated with images; and achieve an interpretable model via working on the induced symbolic concept space. To this end, we first design a new framework named object-centric compositional attention model (OCCAM) to perform the visual reasoning task

    更新日期:2020-11-25
  • Conformance Checking of Mixed-paradigm Process Models
    arXiv.cs.CL Pub Date : 2020-11-23
    Boudewijn van Dongen; Johannes De Smedt; Claudio Di Ciccio; Jan Mendling

    Mixed-paradigm process models integrate strengths of procedural and declarative representations like Petri nets and Declare. They are specifically interesting for process mining because they allow capturing complex behaviour in a compact way. A key research challenge for the proliferation of mixed-paradigm models for process mining is the lack of corresponding conformance checking techniques. In this

    更新日期:2020-11-25
  • Speech Command Recognition in Computationally Constrained Environments with a Quadratic Self-organized Operational Layer
    arXiv.cs.CL Pub Date : 2020-11-23
    Mohammad SoltanianDepartment of Computing Sciences, Tampere University, Finland; Junaid MalikDepartment of Computing Sciences, Tampere University, Finland; Jenni RaitoharjuProgramme for Environmental Information, Finnish Environment Institute, Jyvaskyla, Finland; Alexandros IosifidisDepartment of Electrical and Computer Engineering, Aarhus University, Denmark; Serkan KiranyazElectrical Engineering

    Automatic classification of speech commands has revolutionized human computer interactions in robotic applications. However, employed recognition models usually follow the methodology of deep learning with complicated networks which are memory and energy hungry. So, there is a need to either squeeze these complicated models or use more efficient light-weight models in order to be able to implement

    更新日期:2020-11-25
  • Language guided machine action
    arXiv.cs.CL Pub Date : 2020-11-23
    Feng Qi

    Here we build a hierarchical modular network called Language guided machine action (LGMA), whose modules process information stream mimicking human cortical network that allows to achieve multiple general tasks such as language guided action, intention decomposition and mental simulation before action execution etc. LGMA contains 3 main systems: (1) primary sensory system that multimodal sensory information

    更新日期:2020-11-25
  • Hierachical Delta-Attention Method for Multimodal Fusion
    arXiv.cs.CL Pub Date : 2020-11-22
    Kunjal Panchal

    In vision and linguistics; the main input modalities are facial expressions, speech patterns, and the words uttered. The issue with analysis of any one mode of expression (Visual, Verbal or Vocal) is that lot of contextual information can get lost. This asks researchers to inspect multiple modalities to get a thorough understanding of the cross-modal dependencies and temporal context of the situation

    更新日期:2020-11-25
  • HALO 1.0: A Hardware-agnostic Accelerator Orchestration Framework for Enabling Hardware-agnostic Programming with True Performance Portability for Heterogeneous HPC
    arXiv.cs.CL Pub Date : 2020-11-22
    Michael Riera; Erfan Bank Tavakoli; Masudul Hassan Quraishi; Fengbo Ren

    Hardware-agnostic programming with high performance portability will be the bedrock for realizing the ubiquitous adoption of emerging accelerator technologies in future heterogeneous high-performance computing (HPC) systems, which is the key to achieving the next level of HPC performance on an expanding accelerator landscape. In this paper, we present HALO 1.0, an open-ended extensible multi-agent

    更新日期:2020-11-25
  • Neural Group Testing to Accelerate Deep Learning
    arXiv.cs.CL Pub Date : 2020-11-21
    Weixin Liang; James Zou

    Recent advances in deep learning have made the use of large, deep neural networks with tens of millions of parameters. The sheer size of these networks imposes a challenging computational burden during inference. Existing work focuses primarily on accelerating each forward pass of a neural network. Inspired by the group testing strategy for efficient disease testing, we propose neural group testing

    更新日期:2020-11-25
  • Topic modelling discourse dynamics in historical newspapers
    arXiv.cs.CL Pub Date : 2020-11-20
    Jani Marjanen; Elaine Zosa; Simon Hengchen; Lidia Pivovarova; Mikko Tolonen

    This paper addresses methodological issues in diachronic data analysis for historical research. We apply two families of topic models (LDA and DTM) on a relatively large set of historical newspapers, with the aim of capturing and understanding discourse dynamics. Our case study focuses on newspapers and periodicals published in Finland between 1854 and 1917, but our method can easily be transposed

    更新日期:2020-11-23
  • Fine-Tuning BERT for Sentiment Analysis of Vietnamese Reviews
    arXiv.cs.CL Pub Date : 2020-11-20
    Quoc Thai Nguyen; Thoai Linh Nguyen; Ngoc Hoang Luong; Quoc Hung Ngo

    Sentiment analysis is an important task in the field ofNature Language Processing (NLP), in which users' feedbackdata on a specific issue are evaluated and analyzed. Manydeep learning models have been proposed to tackle this task, including the recently-introduced Bidirectional Encoder Rep-resentations from Transformers (BERT) model. In this paper,we experiment with two BERT fine-tuning methods for

    更新日期:2020-11-23
  • ONION: A Simple and Effective Defense Against Textual Backdoor Attacks
    arXiv.cs.CL Pub Date : 2020-11-20
    Fanchao Qi; Yangyi Chen; Mukai Li; Zhiyuan Liu; Maosong Sun

    Backdoor attacks, which are a kind of emergent training-time threat to deep neural networks (DNNS). They can manipulate the output of DNNs and posses high insidiousness. In the field of natural language processing, some attack methods have been proposed and achieve very high attack success rates on multiple popular models. Nevertheless, the studies on defending textual backdoor defense are little conducted

    更新日期:2020-11-23
  • 1st AfricaNLP Workshop Proceedings, 2020
    arXiv.cs.CL Pub Date : 2020-11-20
    Kathleen Siminyu; Laura Martinus; Vukosi Marivate

    Proceedings of the 1st AfricaNLP Workshop held on 26th April alongside ICLR 2020, Virtual Conference, Formerly Addis Ababa Ethiopia.

    更新日期:2020-11-23
  • A Deep Language-independent Network to analyze the impact of COVID-19 on the World via Sentiment Analysis
    arXiv.cs.CL Pub Date : 2020-11-20
    Ashima Yadav; Dinesh Kumar Vishwakarma

    Towards the end of 2019, Wuhan experienced an outbreak of novel coronavirus, which soon spread all over the world, resulting in a deadly pandemic that infected millions of people around the globe. The government and public health agencies followed many strategies to counter the fatal virus. However, the virus severely affected the social and economic lives of the people. In this paper, we extract and

    更新日期:2020-11-23
  • Learning Informative Representations of Biomedical Relations with Latent Variable Models
    arXiv.cs.CL Pub Date : 2020-11-20
    Harshil Shah; Julien Fauqueur

    Extracting biomedical relations from large corpora of scientific documents is a challenging natural language processing task. Existing approaches usually focus on identifying a relation either in a single sentence (mention-level) or across an entire corpus (pair-level). In both cases, recent methods have achieved strong results by learning a point estimate to represent the relation; this is then used

    更新日期:2020-11-23
  • Are Chess Discussions Racist? An Adversarial Hate Speech Data Set
    arXiv.cs.CL Pub Date : 2020-11-20
    Rupak Sarkar; Ashiqur R. KhudaBukhsh

    On June 28, 2020, while presenting a chess podcast on Grandmaster Hikaru Nakamura, Antonio Radi\'c's YouTube handle got blocked because it contained "harmful and dangerous" content. YouTube did not give further specific reason, and the channel got reinstated within 24 hours. However, Radi\'c speculated that given the current political situation, a referral to "black against white", albeit in the context

    更新日期:2020-11-23
  • Collaborative Storytelling with Large-scale Neural Language Models
    arXiv.cs.CL Pub Date : 2020-11-20
    Eric Nichols; Leo Gao; Randy Gomez

    Storytelling plays a central role in human socializing and entertainment. However, much of the research on automatic storytelling generation assumes that stories will be generated by an agent without any human interaction. In this paper, we introduce the task of collaborative storytelling, where an artificial intelligence agent and a person collaborate to create a unique story by taking turns adding

    更新日期:2020-11-23
  • Sentiment Classification in Bangla Textual Content: A Comparative Study
    arXiv.cs.CL Pub Date : 2020-11-19
    Md. Arid Hasan; Jannatul Tajrin; Shammur Absar Chowdhury; Firoj Alam

    Sentiment analysis has been widely used to understand our views on social and political agendas or user experiences over a product. It is one of the cores and well-researched areas in NLP. However, for low-resource languages, like Bangla, one of the prominent challenge is the lack of resources. Another important limitation, in the current literature for Bangla, is the absence of comparable results

    更新日期:2020-11-23
  • Detecting Universal Trigger's Adversarial Attack with Honeypot
    arXiv.cs.CL Pub Date : 2020-11-20
    Thai Le; Noseong Park; Dongwon Lee

    The Universal Trigger (UniTrigger) is a recently-proposed powerful adversarial textual attack method. Utilizing a learning-based mechanism, UniTrigger can generate a fixed phrase that when added to any benign inputs, can drop the prediction accuracy of a textual neural network (NN) model to near zero on a target class. To defend against this new attack method that may cause significant harm, we borrow

    更新日期:2020-11-23
  • User and Item-aware Estimation of Review Helpfulness
    arXiv.cs.CL Pub Date : 2020-11-20
    Noemi Mauro; Liliana Ardissono; Giovanna Petrone

    In online review sites, the analysis of user feedback for assessing its helpfulness for decision-making is usually carried out by locally studying the properties of individual reviews. However, global properties should be considered as well to precisely evaluate the quality of user feedback. In this paper we investigate the role of deviations in the properties of reviews as helpfulness determinants

    更新日期:2020-11-23
  • Towards Abstract Relational Learning in Human Robot Interaction
    arXiv.cs.CL Pub Date : 2020-11-20
    Mohamadreza Faridghasemnia; Daniele Nardi; Alessandro Saffiotti

    Humans have a rich representation of the entities in their environment. Entities are described by their attributes, and entities that share attributes are often semantically related. For example, if two books have "Natural Language Processing" as the value of their `title' attribute, we can expect that their `topic' attribute will also be equal, namely, "NLP". Humans tend to generalize such observations

    更新日期:2020-11-23
  • Finding Prerequisite Relations between Concepts using Textbook
    arXiv.cs.CL Pub Date : 2020-11-20
    Shivam Pal; Vipul Arora; Pawan Goyal

    A prerequisite is anything that you need to know or understand first before attempting to learn or understand something new. In the current work, we present a method of finding prerequisite relations between concepts using related textbooks. Previous researchers have focused on finding these relations using Wikipedia link structure through unsupervised and supervised learning approaches. In the current

    更新日期:2020-11-23
  • Sequential Targeting: an incremental learning approach for data imbalance in text classification
    arXiv.cs.CL Pub Date : 2020-11-20
    Joel Jang; Yoonjeon Kim; Kyoungho Choi; Sungho Suh

    Classification tasks require a balanced distribution of data to ensure the learner to be trained to generalize over all classes. In real-world datasets, however, the number of instances vary substantially among classes. This typically leads to a learner that promotes bias towards the majority group due to its dominating property. Therefore, methods to handle imbalanced datasets are crucial for alleviating

    更新日期:2020-11-23
Contents have been reproduced by permission of the publishers.
导出
全部期刊列表>>
施普林格,自然编辑
ERIS期刊投稿
欢迎阅读创刊号
自然职场,为您触达千万科研人才
spring&清华大学出版社
城市可持续发展前沿研究专辑
Springer 纳米技术权威期刊征稿
全球视野覆盖
施普林格·自然新
chemistry
物理学研究前沿热点精选期刊推荐
自然职位线上招聘会
欢迎报名注册2020量子在线大会
化学领域亟待解决的问题
材料学研究精选新
GIANT
ACS ES&T Engineering
ACS ES&T Water
屿渡论文,编辑服务
ACS Publications填问卷
阿拉丁试剂right
苏州大学
林亮
南方科技大学
朱守非
胡少伟
有机所林亮
隐藏1h前已浏览文章
课题组网站
新版X-MOL期刊搜索和高级搜索功能介绍
ACS材料视界
上海纽约大学
浙江大学
廖矿标
天合科研
x-mol收录
试剂库存
down
wechat
bug