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
  • Let's Stop Incorrect Comparisons in End-to-end Relation Extraction!
    arXiv.cs.CL Pub Date : 2020-09-22
    Bruno Taillé; Vincent Guigue; Geoffrey Scoutheeten; Patrick Gallinari

    Despite efforts to distinguish three different evaluation setups (Bekoulis et al., 2018), numerous end-to-end Relation Extraction (RE) articles present unreliable performance comparison to previous work. In this paper, we first identify several patterns of invalid comparisons in published papers and describe them to avoid their propagation. We then propose a small empirical study to quantify the impact

    更新日期:2020-09-23
  • AutoRC: Improving BERT Based Relation Classification Models via Architecture Search
    arXiv.cs.CL Pub Date : 2020-09-22
    Wei Zhu; Xiaoling Wang; Xipeng Qiu; Yuan Ni; Guotong Xie

    Although BERT based relation classification (RC) models have achieved significant improvements over the traditional deep learning models, it seems that no consensus can be reached on what is the optimal architecture. Firstly, there are multiple alternatives for entity span identification. Second, there are a collection of pooling operations to aggregate the representations of entities and contexts

    更新日期:2020-09-23
  • GRACE: Gradient Harmonized and Cascaded Labeling for Aspect-based Sentiment Analysis
    arXiv.cs.CL Pub Date : 2020-09-22
    Huaishao Luo; Lei Ji; Tianrui Li; Nan Duan; Daxin Jiang

    In this paper, we focus on the imbalance issue, which is rarely studied in aspect term extraction and aspect sentiment classification when regarding them as sequence labeling tasks. Besides, previous works usually ignore the interaction between aspect terms when labeling polarities. We propose a GRadient hArmonized and CascadEd labeling model (GRACE) to solve these problems. Specifically, a cascaded

    更新日期:2020-09-23
  • Context-theoretic Semantics for Natural Language: an Algebraic Framework
    arXiv.cs.CL Pub Date : 2020-09-22
    Daoud Clarke

    Techniques in which words are represented as vectors have proved useful in many applications in computational linguistics, however there is currently no general semantic formalism for representing meaning in terms of vectors. We present a framework for natural language semantics in which words, phrases and sentences are all represented as vectors, based on a theoretical analysis which assumes that

    更新日期:2020-09-23
  • SUMBT+LaRL: End-to-end Neural Task-oriented Dialog System with Reinforcement Learning
    arXiv.cs.CL Pub Date : 2020-09-22
    Hwaran Lee; Seokhwan Jo; HyungJun Kim; Sangkeun Jung; Tae-Yoon Kim

    The recent advent of neural approaches for developing each dialog component in task-oriented dialog systems has greatly improved, yet optimizing the overall system performance remains a challenge. In this paper, we propose an end-to-end trainable neural dialog system with reinforcement learning, named SUMBT+LaRL. The SUMBT+ estimates user-acts as well as dialog belief states, and the LaRL models latent

    更新日期:2020-09-23
  • CREDIT: Coarse-to-Fine Sequence Generation for Dialogue State Tracking
    arXiv.cs.CL Pub Date : 2020-09-22
    Zhi Chen; Lu Chen; Zihan Xu; Yanbin Zhao; Su Zhu; Kai Yu

    In dialogue systems, a dialogue state tracker aims to accurately find a compact representation of the current dialogue status, based on the entire dialogue history. While previous approaches often define dialogue states as a combination of separate triples ({\em domain-slot-value}), in this paper, we employ a structured state representation and cast dialogue state tracking as a sequence generation

    更新日期:2020-09-23
  • Dual Learning for Dialogue State Tracking
    arXiv.cs.CL Pub Date : 2020-09-22
    Zhi Chen; Lu Chen; Yanbin Zhao; Su Zhu; Kai Yu

    In task-oriented multi-turn dialogue systems, dialogue state refers to a compact representation of the user goal in the context of dialogue history. Dialogue state tracking (DST) is to estimate the dialogue state at each turn. Due to the dependency on complicated dialogue history contexts, DST data annotation is more expensive than single-sentence language understanding, which makes the task more challenging

    更新日期:2020-09-23
  • Logical foundations for hybrid type-logical grammars
    arXiv.cs.CL Pub Date : 2020-09-22
    Richard MootTEXTE, LIRMM, CNRS; Symon Stevens-Guille

    This paper explores proof-theoretic aspects of hybrid type-logical grammars , a logic combining Lambek grammars with lambda grammars. We prove some basic properties of the calculus, such as normalisation and the subformula property and also present both a sequent and a proof net calculus for hybrid type-logical grammars. In addition to clarifying the logical foundations of hybrid type-logical grammars

    更新日期:2020-09-23
  • Global-to-Local Neural Networks for Document-Level Relation Extraction
    arXiv.cs.CL Pub Date : 2020-09-22
    Difeng Wang; Wei Hu; Ermei Cao; Weijian Sun

    Relation extraction (RE) aims to identify the semantic relations between named entities in text. Recent years have witnessed it raised to the document level, which requires complex reasoning with entities and mentions throughout an entire document. In this paper, we propose a novel model to document-level RE, by encoding the document information in terms of entity global and local representations as

    更新日期:2020-09-23
  • Structured Hierarchical Dialogue Policy with Graph Neural Networks
    arXiv.cs.CL Pub Date : 2020-09-22
    Zhi Chen; Xiaoyuan Liu; Lu Chen; Kai Yu

    Dialogue policy training for composite tasks, such as restaurant reservation in multiple places, is a practically important and challenging problem. Recently, hierarchical deep reinforcement learning (HDRL) methods have achieved good performance in composite tasks. However, in vanilla HDRL, both top-level and low-level policies are all represented by multi-layer perceptrons (MLPs) which take the concatenation

    更新日期:2020-09-23
  • Distributed Structured Actor-Critic Reinforcement Learning for Universal Dialogue Management
    arXiv.cs.CL Pub Date : 2020-09-22
    Zhi Chen; Lu Chen; Xiaoyuan Liu; Kai Yu

    The task-oriented spoken dialogue system (SDS) aims to assist a human user in accomplishing a specific task (e.g., hotel booking). The dialogue management is a core part of SDS. There are two main missions in dialogue management: dialogue belief state tracking (summarising conversation history) and dialogue decision-making (deciding how to reply to the user). In this work, we only focus on devising

    更新日期:2020-09-23
  • Deep Reinforcement Learning for On-line Dialogue State Tracking
    arXiv.cs.CL Pub Date : 2020-09-22
    Zhi Chen; Lu Chen; Xiang Zhou; Kai Yu

    Dialogue state tracking (DST) is a crucial module in dialogue management. It is usually cast as a supervised training problem, which is not convenient for on-line optimization. In this paper, a novel companion teaching based deep reinforcement learning (DRL) framework for on-line DST optimization is proposed. To the best of our knowledge, this is the first effort to optimize the DST module within DRL

    更新日期:2020-09-23
  • PodSumm -- Podcast Audio Summarization
    arXiv.cs.CL Pub Date : 2020-09-22
    Aneesh Vartakavi; Amanmeet Garg

    The diverse nature, scale, and specificity of podcasts present a unique challenge to content discovery systems. Listeners often rely on text descriptions of episodes provided by the podcast creators to discover new content. Some factors like the presentation style of the narrator and production quality are significant indicators of subjective user preference but are difficult to quantify and not reflected

    更新日期:2020-09-23
  • Event Coreference Resolution via a Multi-loss Neural Network without Using Argument Information
    arXiv.cs.CL Pub Date : 2020-09-22
    Xinyu Zuo; Yubo Chen; Kang Liu; Jun Zhao

    Event coreference resolution(ECR) is an important task in Natural Language Processing (NLP) and nearly all the existing approaches to this task rely on event argument information. However, these methods tend to suffer from error propagation from the stage of event argument extraction. Besides, not every event mention contains all arguments of an event, and argument information may confuse the model

    更新日期:2020-09-23
  • Towards Causal Explanation Detection with Pyramid Salient-Aware Network
    arXiv.cs.CL Pub Date : 2020-09-22
    Xinyu Zuo; Yubo Chen; Kang Liu; Jun Zhao

    Causal explanation analysis (CEA) can assist us to understand the reasons behind daily events, which has been found very helpful for understanding the coherence of messages. In this paper, we focus on \emph{Causal Explanation Detection}, an important subtask of causal explanation analysis, which determines whether a causal explanation exists in one message. We design a \textbf{P}yramid \textbf{S}a

    更新日期:2020-09-23
  • Constructing interval variables via faceted Rasch measurement and multitask deep learning: a hate speech application
    arXiv.cs.CL Pub Date : 2020-09-22
    Chris J. Kennedy; Geoff Bacon; Alexander Sahn; Claudia von Vacano

    We propose a general method for measuring complex variables on a continuous, interval spectrum by combining supervised deep learning with the Constructing Measures approach to faceted Rasch item response theory (IRT). We decompose the target construct, hate speech in our case, into multiple constituent components that are labeled as ordinal survey items. Those survey responses are transformed via IRT

    更新日期:2020-09-23
  • ALICE: Active Learning with Contrastive Natural Language Explanations
    arXiv.cs.CL Pub Date : 2020-09-22
    Weixin Liang; James Zou; Zhou Yu

    Training a supervised neural network classifier typically requires many annotated training samples. Collecting and annotating a large number of data points are costly and sometimes even infeasible. Traditional annotation process uses a low-bandwidth human-machine communication interface: classification labels, each of which only provides several bits of information. We propose Active Learning with

    更新日期:2020-09-23
  • An Empirical Study on Neural Keyphrase Generation
    arXiv.cs.CL Pub Date : 2020-09-22
    Rui Meng; Xingdi Yuan; Tong Wang; Sanqiang Zhao; Adam Trischler; Daqing He

    Recent years have seen a flourishing of neural keyphrase generation works, including the release of several large-scale datasets and a host of new models to tackle them. Model performance on keyphrase generation tasks has increased significantly with evolving deep learning research. However, there lacks a comprehensive comparison among models, and an investigation on related factors (e.g., architectural

    更新日期:2020-09-23
  • The Persian Dependency Treebank Made Universal
    arXiv.cs.CL Pub Date : 2020-09-21
    Mohammad Sadegh Rasooli; Pegah Safari; Amirsaeid Moloodi; Alireza Nourian

    We describe an automatic method for converting the Persian Dependency Treebank (Rasooli et al, 2013) to Universal Dependencies. This treebank contains 29107 sentences. Our experiments along with manual linguistic analysis show that our data is more compatible with Universal Dependencies than the Uppsala Persian Universal Dependency Treebank (Seraji et al., 2016), and is larger in size and more diverse

    更新日期:2020-09-23
  • SSMBA: Self-Supervised Manifold Based Data Augmentation for Improving Out-of-Domain Robustness
    arXiv.cs.CL Pub Date : 2020-09-21
    Nathan Ng; Kyunghyun Cho; Marzyeh Ghassemi

    Models that perform well on a training domain often fail to generalize to out-of-domain (OOD) examples. Data augmentation is a common method used to prevent overfitting and improve OOD generalization. However, in natural language, it is difficult to generate new examples that stay on the underlying data manifold. We introduce SSMBA, a data augmentation method for generating synthetic training examples

    更新日期:2020-09-23
  • A Crowdsourced Open-Source Kazakh Speech Corpus and Initial Speech Recognition Baseline
    arXiv.cs.CL Pub Date : 2020-09-22
    Yerbolat Khassanov; Saida Mussakhojayeva; Almas Mirzakhmetov; Alen Adiyev; Mukhamet Nurpeiissov; Huseyin Atakan Varol

    We present an open-source speech corpus for the Kazakh language. The Kazakh speech corpus (KSC) contains around 335 hours of transcribed audio comprising over 154,000 utterances spoken by participants from different regions, age groups, and gender. It was carefully inspected by native Kazakh speakers to ensure high quality. The KSC is the largest publicly available database developed to advance various

    更新日期:2020-09-23
  • "When they say weed causes depression, but it's your fav antidepressant": Knowledge-aware Attention Framework for Relationship Extraction
    arXiv.cs.CL Pub Date : 2020-09-21
    Shweta Yadav; Usha Lokala; Raminta Daniulaityte; Krishnaprasad Thirunarayan; Francois Lamy; Amit Sheth

    With the increasing legalization of medical and recreational use of cannabis, more research is needed to understand the association between depression and consumer behavior related to cannabis consumption. Big social media data has potential to provide deeper insights about these associations to public health analysts. In this interdisciplinary study, we demonstrate the value of incorporating domain-specific

    更新日期:2020-09-23
  • End-to-End Speech Recognition and Disfluency Removal
    arXiv.cs.CL Pub Date : 2020-09-22
    Paria Jamshid Lou; Mark Johnson

    Disfluency detection is usually an intermediate step between an automatic speech recognition (ASR) system and a downstream task. By contrast, this paper aims to investigate the task of end-to-end speech recognition and disfluency removal. We specifically explore whether it is possible to train an ASR model to directly map disfluent speech into fluent transcripts, without relying on a separate disfluency

    更新日期:2020-09-23
  • CodeBLEU: a Method for Automatic Evaluation of Code Synthesis
    arXiv.cs.CL Pub Date : 2020-09-22
    Shuo Ren; Daya Guo; Shuai Lu; Long Zhou; Shujie Liu; Duyu Tang; Ming Zhou; Ambrosio Blanco; Shuai Ma

    Evaluation metrics play a vital role in the growth of an area as it defines the standard of distinguishing between good and bad models. In the area of code synthesis, the commonly used evaluation metric is BLEU or perfect accuracy, but they are not suitable enough to evaluate codes, because BLEU is originally designed to evaluate the natural language, neglecting important syntactic and semantic features

    更新日期:2020-09-23
  • SQuARE: Semantics-based Question Answering and Reasoning Engine
    arXiv.cs.CL Pub Date : 2020-09-22
    Kinjal Basu; Sarat Chandra Varanasi; Farhad Shakerin; Gopal Gupta

    Understanding the meaning of a text is a fundamental challenge of natural language understanding (NLU) and from its early days, it has received significant attention through question answering (QA) tasks. We introduce a general semantics-based framework for natural language QA and also describe the SQuARE system, an application of this framework. The framework is based on the denotational semantics

    更新日期:2020-09-23
  • A Finitist's Manifesto: Do we need to Reformulate the Foundations of Mathematics?
    arXiv.cs.CL Pub Date : 2020-09-14
    Jonathan Lenchner

    There is a problem with the foundations of classical mathematics, and potentially even with the foundations of computer science, that mathematicians have by-and-large ignored. This essay is a call for practicing mathematicians who have been sleep-walking in their infinitary mathematical paradise to take heed. Much of mathematics relies upon either (i) the "existence'" of objects that contain an infinite

    更新日期:2020-09-23
  • Composed Variational Natural Language Generation for Few-shot Intents
    arXiv.cs.CL Pub Date : 2020-09-21
    Congying Xia; Caiming Xiong; Philip Yu; Richard Socher

    In this paper, we focus on generating training examples for few-shot intents in the realistic imbalanced scenario. To build connections between existing many-shot intents and few-shot intents, we consider an intent as a combination of a domain and an action, and propose a composed variational natural language generator (CLANG), a transformer-based conditional variational autoencoder. CLANG utilizes

    更新日期:2020-09-22
  • Latin BERT: A Contextual Language Model for Classical Philology
    arXiv.cs.CL Pub Date : 2020-09-21
    David Bamman; Patrick J. Burns

    We present Latin BERT, a contextual language model for the Latin language, trained on 642.7 million words from a variety of sources spanning the Classical era to the 21st century. In a series of case studies, we illustrate the affordances of this language-specific model both for work in natural language processing for Latin and in using computational methods for traditional scholarship: we show that

    更新日期:2020-09-22
  • UCD-CS at W-NUT 2020 Shared Task-3: A Text to Text Approach for COVID-19 Event Extraction on Social Media
    arXiv.cs.CL Pub Date : 2020-09-21
    Congcong Wang; David Lillis

    In this paper, we describe our approach in the shared task: COVID-19 event extraction from Twitter. The objective of this task is to extract answers from COVID-related tweets to a set of predefined slot-filling questions. Our approach treats the event extraction task as a question answering task by leveraging the transformer-based T5 text-to-text model. According to the official exact match based evaluation

    更新日期:2020-09-22
  • Adjusting for Confounders with Text: Challenges and an Empirical Evaluation Framework for Causal Inference
    arXiv.cs.CL Pub Date : 2020-09-21
    Galen Weld; Peter West; Maria Glenski; David Arbour; Ryan Rossi; Tim Althoff

    Leveraging text, such as social media posts, for causal inferences requires the use of NLP models to 'learn' and adjust for confounders, which could otherwise impart bias. However, evaluating such models is challenging, as ground truth is almost never available. We demonstrate the need for empirical evaluation frameworks for causal inference in natural language by showing that existing, commonly used

    更新日期:2020-09-22
  • WESSA at SemEval-2020 Task 9: Code-Mixed Sentiment Analysis using Transformers
    arXiv.cs.CL Pub Date : 2020-09-21
    Ahmed SultanWideBot; Mahmoud SalimWideBot; Amina GaberWideBot; Islam El HosaryWideBot

    In this paper, we describe our system submitted for SemEval 2020 Task 9, Sentiment Analysis for Code-Mixed Social Media Text alongside other experiments. Our best performing system is a Transfer Learning-based model that fine-tunes "XLM-RoBERTa", a transformer-based multilingual masked language model, on monolingual English and Spanish data and Spanish-English code-mixed data. Our system outperforms

    更新日期:2020-09-22
  • Content Planning for Neural Story Generation with Aristotelian Rescoring
    arXiv.cs.CL Pub Date : 2020-09-21
    Seraphina Goldfarb-Tarrant; Tuhin Chakrabarty; Ralph Weischedel; Nanyun Peng

    Long-form narrative text generated from large language models manages a fluent impersonation of human writing, but only at the local sentence level, and lacks structure or global cohesion. We posit that many of the problems of story generation can be addressed via high-quality content planning, and present a system that focuses on how to learn good plot structures to guide story generation. We utilize

    更新日期:2020-09-22
  • Rethinking Supervised Learning and Reinforcement Learning in Task-Oriented Dialogue Systems
    arXiv.cs.CL Pub Date : 2020-09-21
    Ziming Li; Julia Kiseleva; Maarten de Rijke

    Dialogue policy learning for task-oriented dialogue systems has enjoyed great progress recently mostly through employing reinforcement learning methods. However, these approaches have become very sophisticated. It is time to re-evaluate it. Are we really making progress developing dialogue agents only based on reinforcement learning? We demonstrate how (1)~traditional supervised learning together with

    更新日期:2020-09-22
  • SDST: Successive Decoding for Speech-to-text Translation
    arXiv.cs.CL Pub Date : 2020-09-21
    Qianqian Dong; Mingxuan Wang; Hao Zhou; Shuang Xu; Bo Xu; Lei Li

    End-to-end speech-to-text translation (ST), which directly translates the source language speech to the target language text, has attracted intensive attention recently. However, the combination of speech recognition and machine translation in a single model poses a heavy burden on the direct cross-modal cross-lingual mapping. To reduce the learning difficulty, we propose SDST, an integral framework

    更新日期:2020-09-22
  • Multitask Pointer Network for Multi-Representational Parsing
    arXiv.cs.CL Pub Date : 2020-09-21
    Daniel Fernández-González; Carlos Gómez-Rodríguez

    We propose a transition-based approach that, by training a single model, can efficiently parse any input sentence with both constituent and dependency trees, supporting both continuous/projective and discontinuous/non-projective syntactic structures. To that end, we develop a Pointer Network architecture with two separate task-specific decoders and a common encoder, and follow a multitask learning

    更新日期:2020-09-22
  • Empathetic Dialogue Generation via Knowledge Enhancing and Emotion Dependency Modeling
    arXiv.cs.CL Pub Date : 2020-09-21
    Qintong Li; Piji Li; Zhumin Chen; Zhaochun Ren

    Enabling the machines with empathetic abilities to provide context-consistent responses is crucial on both semantic and emotional levels. The task of empathetic dialogue generation is proposed to address this problem. However, two challenges still exist in this task: perceiving nuanced emotions implied in the dialogue context and modelling emotional dependencies. Lacking useful external knowledge makes

    更新日期:2020-09-22
  • TED: Triple Supervision Decouples End-to-end Speech-to-text Translation
    arXiv.cs.CL Pub Date : 2020-09-21
    Qianqian Dong; Mingxuan Wang; Hao Zhou; Shuang Xu; Bo Xu; Lei Li

    An end-to-end speech-to-text translation (ST) takes audio in a source language and outputs the text in a target language. Inspired by neuroscience, humans have perception systems and cognitive systems to process different information, we propose TED, \textbf{T}ransducer-\textbf{E}ncoder-\textbf{D}ecoder, a unified framework with triple supervision to decouple the end-to-end speech-to-text translation

    更新日期:2020-09-22
  • Profile Consistency Identification for Open-domain Dialogue Agents
    arXiv.cs.CL Pub Date : 2020-09-21
    Haoyu Song; Yan Wang; Wei-Nan Zhang; Zhengyu Zhao; Ting Liu; Xiaojiang Liu

    Maintaining a consistent attribute profile is crucial for dialogue agents to naturally converse with humans. Existing studies on improving attribute consistency mainly explored how to incorporate attribute information in the responses, but few efforts have been made to identify the consistency relations between response and attribute profile. To facilitate the study of profile consistency identification

    更新日期:2020-09-22
  • Accent Estimation of Japanese Words from Their Surfaces and Romanizations for Building Large Vocabulary Accent Dictionaries
    arXiv.cs.CL Pub Date : 2020-09-21
    Hideyuki Tachibana; Yotaro Katayama

    In Japanese text-to-speech (TTS), it is necessary to add accent information to the input sentence. However, there are a limited number of publicly available accent dictionaries, and those dictionaries e.g. UniDic, do not contain many compound words, proper nouns, etc., which are required in a practical TTS system. In order to build a large scale accent dictionary that contains those words, the authors

    更新日期:2020-09-22
  • Alleviating the Inequality of Attention Heads for Neural Machine Translation
    arXiv.cs.CL Pub Date : 2020-09-21
    Zewei Sun; Shujian Huang; Xinyu Dai; Jiajun Chen

    Recent studies show that the attention heads in Transformer are not equal. We relate this phenomenon to the imbalance training of multi-head attention and the model dependence on specific heads. To tackle this problem, we propose a simple masking method: HeadMask, in two specific ways. Experiments show that translation improvements are achieved on multiple language pairs. Subsequent empirical analyses

    更新日期:2020-09-22
  • Generative Imagination Elevates Machine Translation
    arXiv.cs.CL Pub Date : 2020-09-21
    Quanyu Long; Mingxuan Wang; Lei Li

    There are thousands of languages on earth, but visual perception is shared among peoples. Existing multimodal neural machine translation (MNMT) methods achieve knowledge transfer by enforcing one encoder to learn shared representation across textual and visual modalities. However, the training and inference process heavily relies on well-aligned bilingual sentence - image triplets as input, which are

    更新日期:2020-09-22
  • Modality-Transferable Emotion Embeddings for Low-Resource Multimodal Emotion Recognition
    arXiv.cs.CL Pub Date : 2020-09-21
    Wenliang Dai; Zihan Liu; Tiezheng Yu; Pascale Fung

    Despite the recent achievements made in the multi-modal emotion recognition task, two problems still exist and have not been well investigated: 1) the relationship between different emotion categories are not utilized, which leads to sub-optimal performance; and 2) current models fail to cope well with low-resource emotions, especially for unseen emotions. In this paper, we propose a modality-transferable

    更新日期:2020-09-22
  • Weakly Supervised Learning of Nuanced Frames for Analyzing Polarization in News Media
    arXiv.cs.CL Pub Date : 2020-09-21
    Shamik Roy; Dan Goldwasser

    In this paper we suggest a minimally-supervised approach for identifying nuanced frames in news article coverage of politically divisive topics. We suggest to break the broad policy frames suggested by Boydstun et al., 2014 into fine-grained subframes which can capture differences in political ideology in a better way. We evaluate the suggested subframes and their embedding, learned using minimal supervision

    更新日期:2020-09-22
  • Assessing the Severity of Health States based on Social Media Posts
    arXiv.cs.CL Pub Date : 2020-09-21
    Shweta Yadav; Joy Prakash Sain; Amit Sheth; Asif Ekbal; Sriparna Saha; Pushpak Bhattacharyya

    The unprecedented growth of Internet users has resulted in an abundance of unstructured information on social media including health forums, where patients request health-related information or opinions from other users. Previous studies have shown that online peer support has limited effectiveness without expert intervention. Therefore, a system capable of assessing the severity of health state from

    更新日期:2020-09-22
  • Improving Robustness and Generality of NLP Models Using Disentangled Representations
    arXiv.cs.CL Pub Date : 2020-09-21
    Jiawei Wu; Xiaoya Li; Xiang Ao; Yuxian Meng; Fei Wu; Jiwei Li

    Supervised neural networks, which first map an input $x$ to a single representation $z$, and then map $z$ to the output label $y$, have achieved remarkable success in a wide range of natural language processing (NLP) tasks. Despite their success, neural models lack for both robustness and generality: small perturbations to inputs can result in absolutely different outputs; the performance of a model

    更新日期:2020-09-22
  • Vector Projection Network for Few-shot Slot Tagging in Natural Language Understanding
    arXiv.cs.CL Pub Date : 2020-09-21
    Su Zhu; Ruisheng Cao; Lu Chen; Kai Yu

    Few-shot slot tagging becomes appealing for rapid domain transfer and adaptation, motivated by the tremendous development of conversational dialogue systems. In this paper, we propose a vector projection network for few-shot slot tagging, which exploits projections of contextual word embeddings on each target label vector as word-label similarities. Essentially, this approach is equivalent to a normalized

    更新日期:2020-09-22
  • Relation Extraction from Biomedical and Clinical Text: Unified Multitask Learning Framework
    arXiv.cs.CL Pub Date : 2020-09-20
    Shweta Yadav; Srivatsa Ramesh; Sriparna Saha; Asif Ekbal

    To minimize the accelerating amount of time invested in the biomedical literature search, numerous approaches for automated knowledge extraction have been proposed. Relation extraction is one such task where semantic relations between the entities are identified from the free text. In the biomedical domain, extraction of regulatory pathways, metabolic processes, adverse drug reaction or disease models

    更新日期:2020-09-22
  • Persian Ezafe Recognition Using Transformers and Its Role in Part-Of-Speech Tagging
    arXiv.cs.CL Pub Date : 2020-09-20
    Ehsan Doostmohammadi; Minoo Nassajian; Adel Rahimi

    Ezafe is a grammatical particle in some Iranian languages that links two words together. Regardless of the important information it conveys, it is almost always not indicated in Persian script, resulting in mistakes in reading complex sentences and errors in natural language processing tasks. In this paper, we experiment with different machine learning methods to achieve state-of-the-art results in

    更新日期:2020-09-22
  • Dialogue Distillation: Open-domain Dialogue Augmentation Using Unpaired Data
    arXiv.cs.CL Pub Date : 2020-09-20
    Rongsheng Zhang; Yinhe Zheng; Jianzhi Shao; Xiaoxi Mao; Yadong Xi; Minlie Huang

    Recent advances in open-domain dialogue systems rely on the success of neural models that are trained on large-scale data. However, collecting large-scale dialogue data is usually time-consuming and labor-intensive. To address this data dilemma, we propose a novel data augmentation method for training open-domain dialogue models by utilizing unpaired data. Specifically, a data-level distillation process

    更新日期:2020-09-22
  • F^2-Softmax: Diversifying Neural Text Generation via Frequency Factorized Softmax
    arXiv.cs.CL Pub Date : 2020-09-20
    Byung-Ju Choi; Jimin Hong; David Keetae Park; Sang Wan Lee

    Despite recent advances in neural text generation, encoding the rich diversity in human language remains elusive. We argue that the sub-optimal text generation is mainly attributable to the imbalanced token distribution, which particularly misdirects the learning model when trained with the maximum-likelihood objective. As a simple yet effective remedy, we propose two novel methods, F^2-Softmax and

    更新日期:2020-09-22
  • Difference-aware Knowledge Selection for Knowledge-grounded Conversation Generation
    arXiv.cs.CL Pub Date : 2020-09-20
    Chujie Zheng; Yunbo Cao; Daxin Jiang; Minlie Huang

    In a multi-turn knowledge-grounded dialog, the difference between the knowledge selected at different turns usually provides potential clues to knowledge selection, which has been largely neglected in previous research. In this paper, we propose a difference-aware knowledge selection method. It first computes the difference between the candidate knowledge sentences provided at the current turn and

    更新日期:2020-09-22
  • Softmax Tempering for Training Neural Machine Translation Models
    arXiv.cs.CL Pub Date : 2020-09-20
    Raj Dabre; Atsushi Fujita

    Neural machine translation (NMT) models are typically trained using a softmax cross-entropy loss where the softmax distribution is compared against smoothed gold labels. In low-resource scenarios, NMT models tend to over-fit because the softmax distribution quickly approaches the gold label distribution. To address this issue, we propose to divide the logits by a temperature coefficient, prior to applying

    更新日期:2020-09-22
  • Understanding Mention Detector-Linker Interaction for Neural Coreference Resolution
    arXiv.cs.CL Pub Date : 2020-09-20
    Zhaofeng Wu; Matt Gardner

    Coreference resolution is an important task for discourse-level natural language understanding. However, despite significant recent progress, the quality of current state-of-the-art systems still considerably trails behind human-level performance. Using the CoNLL-2012 and PreCo datasets, we dissect the best instantiation of the mainstream end-to-end coreference resolution model that underlies most

    更新日期:2020-09-22
  • Not Low-Resource Anymore: Aligner Ensembling, Batch Filtering, and New Datasets for Bengali-English Machine Translation
    arXiv.cs.CL Pub Date : 2020-09-20
    Tahmid Hasan; Abhik Bhattacharjee; Kazi Samin; Md Hasan; Madhusudan Basak; M. Sohel Rahman; Rifat Shahriyar

    Despite being the seventh most widely spoken language in the world, Bengali has received much less attention in machine translation literature due to being low in resources. Most publicly available parallel corpora for Bengali are not large enough; and have rather poor quality, mostly because of incorrect sentence alignments resulting from erroneous sentence segmentation, and also because of a high

    更新日期:2020-09-22
  • Biomedical Event Extraction on Graph Edge-conditioned Attention Networks with Hierarchical Knowledge Graphs
    arXiv.cs.CL Pub Date : 2020-09-20
    Kung-Hsiang Huang; Mu Yang; Nanyun Peng

    Biomedical event extraction is critical in understanding biomolecular interactions described in scientific corpus. One of the main challenges is to identify nested structured events that are associated with non-indicative trigger words. We propose to incorporate domain knowledge from Unified Medical Language System (UMLS) to a pre-trained language model via Graph Edge-conditioned Attention Networks

    更新日期:2020-09-22
  • Towards Computational Linguistics in Minangkabau Language: Studies on Sentiment Analysis and Machine Translation
    arXiv.cs.CL Pub Date : 2020-09-19
    Fajri Koto; Ikhwan Koto

    Although some linguists (Rusmali et al., 1985; Crouch, 2009) have fairly attempted to define the morphology and syntax of Minangkabau, information processing in this language is still absent due to the scarcity of the annotated resource. In this work, we release two Minangkabau corpora: sentiment analysis and machine translation that are harvested and constructed from Twitter and Wikipedia. We conduct

    更新日期:2020-09-22
  • Word class flexibility: A deep contextualized approach
    arXiv.cs.CL Pub Date : 2020-09-19
    Bai Li; Guillaume Thomas; Yang Xu; Frank Rudzicz

    Word class flexibility refers to the phenomenon whereby a single word form is used across different grammatical categories. Extensive work in linguistic typology has sought to characterize word class flexibility across languages, but quantifying this phenomenon accurately and at scale has been fraught with difficulties. We propose a principled methodology to explore regularity in word class flexibility

    更新日期:2020-09-22
  • BioALBERT: A Simple and Effective Pre-trained Language Model for Biomedical Named Entity Recognition
    arXiv.cs.CL Pub Date : 2020-09-19
    Usman Naseem; Matloob Khushi; Vinay Reddy; Sakthivel Rajendran; Imran Razzak; Jinman Kim

    In recent years, with the growing amount of biomedical documents, coupled with advancement in natural language processing algorithms, the research on biomedical named entity recognition (BioNER) has increased exponentially. However, BioNER research is challenging as NER in the biomedical domain are: (i) often restricted due to limited amount of training data, (ii) an entity can refer to multiple types

    更新日期:2020-09-22
  • Learning to Attack: Towards Textual Adversarial Attacking in Real-world Situations
    arXiv.cs.CL Pub Date : 2020-09-19
    Yuan Zang; Bairu Hou; Fanchao Qi; Zhiyuan Liu; Xiaojun Meng; Maosong Sun

    Adversarial attacking aims to fool deep neural networks with adversarial examples. In the field of natural language processing, various textual adversarial attack models have been proposed, varying in the accessibility to the victim model. Among them, the attack models that only require the output of the victim model are more fit for real-world situations of adversarial attacking. However, to achieve

    更新日期:2020-09-22
  • OpenAttack: An Open-source Textual Adversarial Attack Toolkit
    arXiv.cs.CL Pub Date : 2020-09-19
    Guoyang Zeng; Fanchao Qi; Qianrui Zhou; Tingji Zhang; Bairu Hou; Yuan Zang; Zhiyuan Liu; Maosong Sun

    Textual adversarial attacking has received wide and increasing attention in recent years. Various attack models have been proposed, which are enormously distinct and implemented with different programming frameworks and settings. These facts hinder quick utilization and apt comparison of attack models. In this paper, we present an open-source textual adversarial attack toolkit named OpenAttack. It

    更新日期:2020-09-22
Contents have been reproduced by permission of the publishers.
导出
全部期刊列表>>
物理学研究前沿热点精选期刊推荐
chemistry
《自然》编辑与您分享如何成为优质审稿人-信息流
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
自然职场线上招聘会
ACS ES&T Engineering
ACS ES&T Water
ACS Publications填问卷
屿渡论文,编辑服务
阿拉丁试剂right
南昌大学
王辉
南方科技大学
刘天飞
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
天合科研
x-mol收录
X-MOL
苏州大学
廖矿标
深圳湾
试剂库存
down
wechat
bug