• arXiv.cs.CL Pub Date : 2020-06-30
Yoel Zeldes; Dan Padnos; Or Sharir; Barak Peleg

We introduce a simple and efficient method, called Auxiliary Tuning, for adapting a pre-trained Language Model to a novel task; we demonstrate this approach on the task of conditional text generation. Our approach supplements the original pre-trained model with an auxiliary model that shifts the output distribution according to the target task. The auxiliary model is trained by adding its logits to

更新日期：2020-07-01
• arXiv.cs.CL Pub Date : 2020-06-30
Siqi Bao; Huang He; Fan Wang; Hua Wu; Haifeng Wang; Wenquan Wu; Zhen Guo; Zhibin Liu; Xinchao Xu

To build a high-quality open-domain chatbot, we introduce the effective training process of PLATO-2 via curriculum learning. There are two stages involved in the learning process. In the first stage, a coarse-grained generation model is trained to learn response generation under the simplified framework of one-to-one mapping. In the second stage, a fine-grained generation model and an evaluation model

更新日期：2020-07-01
• arXiv.cs.CL Pub Date : 2020-06-30
Dmitry Lepikhin; HyoukJoong Lee; Yuanzhong Xu; Dehao Chen; Orhan Firat; Yanping Huang; Maxim Krikun; Noam Shazeer; Zhifeng Chen

Neural network scaling has been critical for improving the model quality in many real-world machine learning applications with vast amounts of training data and compute. Although this trend of scaling is affirmed to be a sure-fire approach for better model quality, there are challenges on the path such as the computation cost, ease of programming, and efficient implementation on parallel devices. GShard

更新日期：2020-07-01
• arXiv.cs.CL Pub Date : 2020-06-30
Erion Çano; Maurizio Morisio

The fabulous results of convolution neural networks in image-related tasks, attracted attention of text mining, sentiment analysis and other text analysis researchers. It is however difficult to find enough data for feeding such networks, optimize their parameters, and make the right design choices when constructing network architectures. In this paper we present the creation steps of two big datasets

更新日期：2020-07-01
• arXiv.cs.CL Pub Date : 2020-06-29
Anandh Perumal; Chenyang Huang; Amine Trabelsi; Osmar R. Zaïane

In this paper, we describe our mUlti-task learNIng for cOmmonsense reasoNing (UNION) system submitted for Task C of the SemEval2020 Task 4, which is to generate a reason explaining why a given false statement is non-sensical. However, we found in the early experiments that simple adaptations such as fine-tuning GPT2 often yield dull and non-informative generations (e.g. simple negations). In order

更新日期：2020-07-01
• arXiv.cs.CL Pub Date : 2020-06-29
Junxian He; Taylor Berg-Kirkpatrick; Graham Neubig

Prototype-driven text generation uses non-parametric models that first choose from a library of sentence "prototypes" and then modify the prototype to generate the output text. While effective, these methods are inefficient at test time as a result of needing to store and index the entire training corpus. Further, existing methods often require heuristics to identify which prototypes to reference at

更新日期：2020-07-01
• arXiv.cs.CL Pub Date : 2020-06-29
R. Thomas McCoy; Erin Grant; Paul Smolensky; Thomas L. Griffiths; Tal Linzen

How do learners acquire languages from the limited data available to them? This process must involve some inductive biases - factors that affect how a learner generalizes - but it is unclear which inductive biases can explain observed patterns in language acquisition. To facilitate computational modeling aimed at addressing this question, we introduce a framework for giving particular linguistic inductive

更新日期：2020-07-01
• arXiv.cs.CL Pub Date : 2020-06-25
Alireza Ghasemi; Amina Chebira

We release our COVID-19 news dataset, containing more than 10,000 links to news articles related to the Coronavirus pandemic published in the Swiss media since early January 2020. This collection can prove beneficial in mining and analysis of the reaction of the Swiss media and the COVID-19 pandemic and extracting insightful information for further research. We hope this dataset helps researchers and

更新日期：2020-07-01
• arXiv.cs.CL Pub Date : 2020-06-30
Fei Yu; Jiji Tang; Weichong Yin; Yu Sun; Hao Tian; Hua Wu; Haifeng Wang

We propose a knowledge-enhanced approach, ERNIE-ViL, to learn joint representations of vision and language. ERNIE-ViL tries to construct the detailed semantic connections (objects, attributes of objects and relationships between objects in visual scenes) across vision and language, which are essential to vision-language cross-modal tasks. Incorporating knowledge from scene graphs, ERNIE-ViL constructs

更新日期：2020-07-01
• arXiv.cs.CL Pub Date : 2020-06-30
Eliane M. De Bortoli Fávero; Dalcimar Casanova; Andrey Ricardo Pimentel

Estimating effort based on requirement texts presents many challenges, especially in obtaining viable features to infer effort. Aiming to explore a more effective technique for representing textual requirements to infer effort estimates by analogy, this paper proposes to evaluate the effectiveness of pre-trained embeddings models. For this, two embeddings approach, context-less and contextualized models

更新日期：2020-07-01
• arXiv.cs.CL Pub Date : 2020-06-18
Pengyu Nie; Karl Palmskog; Junyi Jessy Li; Milos Gligoric

Should the final right bracket in a record declaration be on a separate line? Should arguments to the rewrite tactic be separated by a single space? Coq code tends to be written in distinct manners by different people and teams. The expressiveness, flexibility, and extensibility of Coq's languages and notations means that Coq projects have a wide variety of recognizable coding styles, sometimes explicitly

更新日期：2020-07-01
• arXiv.cs.CL Pub Date : 2020-06-29
Elizabeth Reichert; Helen Qiu; Jasmine Bayrooti

The censorship of toxic comments is often left to the judgment of imperfect models. Perspective API, a creation of Google technology incubator Jigsaw, is perhaps the most widely used toxicity classifier in industry; the model is employed by several online communities including The New York Times to identify and filter out toxic comments with the goal of preserving online safety. Unfortunately, Google's

更新日期：2020-07-01
• arXiv.cs.CL Pub Date : 2020-06-29
Zhiqing Sun; Yiming Yang

Autoregressive (AR) models have been the dominating approach to conditional sequence generation, but are suffering from the issue of high inference latency. Non-autoregressive (NAR) models have been recently proposed to reduce the latency by generating all output tokens in parallel but could only achieve inferior accuracy compared to their autoregressive counterparts, primarily due to a difficulty

更新日期：2020-07-01
• arXiv.cs.CL Pub Date : 2020-06-29
Stefano Martina; Leonardo Ventura; Paolo Frasconi

We report about the application of state-of-the-art deep learning techniques to the automatic and interpretable assignment of ICD-O3 topography and morphology codes to free-text cancer reports. We present results on a large dataset (more than 80 000 labeled and 1 500 000 unlabeled anonymized reports written in Italian and collected from hospitals in Tuscany over more than a decade) and with a large

更新日期：2020-07-01
• arXiv.cs.CL Pub Date : 2020-06-29
Hung Nghiep Tran; Atsuhiro Takasu

Knowledge graph completion is an important task that aims to predict the missing relational link between entities. Knowledge graph embedding methods perform this task by representing entities and relations as embedding vectors and modeling their interactions to compute the matching score of each triple. Previous work has usually treated each embedding as a whole and has modeled the interactions between

更新日期：2020-07-01
• arXiv.cs.CL Pub Date : 2020-06-29
Mirinso Shadang; Navanath Saharia; Thoudam Doren Singh

There is no or little work on natural language processing of Tangkhul language. The current work is a humble beginning of morphological processing of this language using an unsupervised approach. We use a small corpus collected from different sources of text books, short stories and articles of other topics. Based on the experiments carried out, the morpheme identification task using morphessor gives

更新日期：2020-06-30
• arXiv.cs.CL Pub Date : 2020-06-29
Lichao Sun

Deep learning has been widely adopted in natural language processing applications in recent years. Many existing studies show the vulnerabilities of machine learning and deep learning models against adversarial examples. However, most existing works currently focus on evasion attack on text data instead of positioning attack, also named \textit{backdoor attack}. In this paper, we systematically study

更新日期：2020-06-30
• arXiv.cs.CL Pub Date : 2020-06-29
Zhenyu Liu; Haiwei Huang; Chaohong Lu; Shengfei Lyu

Recent years, the approaches based on neural networks have shown remarkable potential for sentence modeling. There are two main neural network structures: recurrent neural network (RNN) and convolution neural network (CNN). RNN can capture long term dependencies and store the semantics of the previous information in a fixed-sized vector. However, RNN is a biased model and its ability to extract global

更新日期：2020-06-30
• arXiv.cs.CL Pub Date : 2020-06-29
Marouane Yassine; David Beauchemin; François Laviolette; Luc Lamontagne

Address parsing consists of identifying the segments that make up an address such as a street name or a postal code. Because of its importance for tasks like record linkage, address parsing has been approached with many techniques. Neural network methods defined a new state-of-the-art for address parsing. While this approach yielded notable results, previous work has only focused on applying neural

更新日期：2020-06-30
• arXiv.cs.CL Pub Date : 2020-06-29
Katikapalli Subramanyam Kalyan; S. Sangeetha

更新日期：2020-06-30
• arXiv.cs.CL Pub Date : 2020-06-29
Rudolf Rosa; Tomáš Musil; David Mareček

Multiple studies have probed representations emerging in neural networks trained for end-to-end NLP tasks and examined what word-level linguistic information may be encoded in the representations. In classical probing, a classifier is trained on the representations to extract the target linguistic information. However, there is a threat of the classifier simply memorizing the linguistic labels for

更新日期：2020-06-30
• arXiv.cs.CL Pub Date : 2020-06-29
Viet Bui The; Oanh Tran Thi; Phuong Le-Hong

This paper describes our study on using mutilingual BERT embeddings and some new neural models for improving sequence tagging tasks for the Vietnamese language. We propose new model architectures and evaluate them extensively on two named entity recognition datasets of VLSP 2016 and VLSP 2018, and on two part-of-speech tagging datasets of VLSP 2010 and VLSP 2013. Our proposed models outperform existing

更新日期：2020-06-30
• arXiv.cs.CL Pub Date : 2020-06-29
Jean-Benoit Delbrouck; Noé Tits; Mathilde Brousmiche; Stéphane Dupont

Understanding expressed sentiment and emotions are two crucial factors in human multimodal language. This paper describes a Transformer-based joint-encoding (TBJE) for the task of Emotion Recognition and Sentiment Analysis. In addition to use the Transformer architecture, our approach relies on a modular co-attention and a glimpse layer to jointly encode one or more modalities. The proposed solution

更新日期：2020-06-30
• arXiv.cs.CL Pub Date : 2020-06-29
Ritwik Bose; Siddharth Vashishtha; James Allen

The task of Semantic Parsing can be approximated as a transformation of an utterance into a logical form graph where edges represent semantic roles and nodes represent word senses. The resulting representation should be capture the meaning of the utterance and be suitable for reasoning. Word senses and semantic roles are interdependent, meaning errors in assigning word senses can cause errors in assigning

更新日期：2020-06-30
• arXiv.cs.CL Pub Date : 2020-06-29
Tiziana Carpi; Stefano Maria Iacus

This study analyzes the usage of Japanese gendered language on Twitter. Starting from a collection of 408 million Japanese tweets from 2015 till 2019 and an additional sample of 2355 manually classified Twitter accounts timelines into gender and categories (politicians, musicians, etc). A large scale textual analysis is performed on this corpus to identify and examine sentence-final particles (SFPs)

更新日期：2020-06-30
• arXiv.cs.CL Pub Date : 2020-06-29

Most of the previous studies on the semantic analysis of social media feeds have not considered the issue of ambiguity that is associated with slangs, abbreviations, and acronyms that are embedded in social media posts. These noisy terms have implicit meanings and form part of the rich semantic context that must be analysed to gain complete insights from social media feeds. This paper proposes an improved

更新日期：2020-06-30
• arXiv.cs.CL Pub Date : 2020-06-29
Jinhyuk Lee; Sean S. Yi; Minbyul Jeong; Mujeen Sung; Wonjin Yoon; Yonghwa Choi; Miyoung Ko; Jaewoo Kang

The recent outbreak of the novel coronavirus is wreaking havoc on the world and researchers are struggling to effectively combat it. One reason why the fight is difficult is due to the lack of information and knowledge. In this work, we outline our effort to contribute to shrinking this knowledge vacuum by creating covidAsk, a question answering (QA) system that combines biomedical text mining and

更新日期：2020-06-30
• arXiv.cs.CL Pub Date : 2020-06-29
Shengfei Lyu; Jiaqi Liu

Convolutional neural network (CNN) and recurrent neural network (RNN) are two popular architectures used in text classification. Traditional methods to combine the strengths of the two networks rely on streamlining them or concatenating features extracted from them. In this paper, we propose a novel method to keep the strengths of the two networks to a great extent. In the proposed model, a convolutional

更新日期：2020-06-30
• arXiv.cs.CL Pub Date : 2020-06-28
Petr Plechac; Thomas N. Haider

Poetic traditions across languages evolved differently, but we find that certain semantic topics occur in several of them, albeit sometimes with temporal delay, or with diverging trajectories over time. We apply Latent Dirichlet Allocation (LDA) to poetry corpora of four languages, i.e. German (52k poems), English (85k poems), Russian (18k poems), and Czech (80k poems). We align and interpret salient

更新日期：2020-06-30
• arXiv.cs.CL Pub Date : 2020-06-28
Bowen Tan; Zichao Yang; Maruan AI-Shedivat; Eric P. Xing; Zhiting Hu

Large-scale language models pretrained on massive corpora of text, such as GPT-2, are powerful open-domain text generators. However, as our systematic examination reveals, it is still challenging for such models to generate coherent long passages of text ($>$1000 tokens), especially when the models are fine-tuned to the target domain on a small corpus. To overcome the limitation, we propose a simple

更新日期：2020-06-30
• arXiv.cs.CL Pub Date : 2020-06-28
Guolin Ke; Di He; Tie-Yan Liu

How to explicitly encode positional information into neural networks is an important problem in natural language processing. In the Transformer model, the positional information is simply encoded as embedding vectors, which are used in the input layer, or encoded as a bias term in the self-attention module. In this work, we investigate the problems in the previous formulations and propose a new positional

更新日期：2020-06-30
• arXiv.cs.CL Pub Date : 2020-06-28
Sevinj Yolchuyeva; Géza Németh; Bálint Gyires-Tóth

Self-attention networks (SAN) have shown promising performance in various Natural Language Processing (NLP) scenarios, especially in machine translation. One of the main points of SANs is the strength of capturing long-range and multi-scale dependencies from the data. In this paper, we present a novel intent detection system which is based on a self-attention network and a Bi-LSTM. Our approach shows

更新日期：2020-06-30
• arXiv.cs.CL Pub Date : 2020-06-28
Chen Liang; Yue Yu; Haoming Jiang; Siawpeng Er; Ruijia Wang; Tuo Zhao; Chao Zhang

We study the open-domain named entity recognition (NER) problem under distant supervision. The distant supervision, though does not require large amounts of manual annotations, yields highly incomplete and noisy distant labels via external knowledge bases. To address this challenge, we propose a new computational framework -- BOND, which leverages the power of pre-trained language models (e.g., BERT

更新日期：2020-06-30
• arXiv.cs.CL Pub Date : 2020-06-27
Zi-Yi Dou; Sachin Kumar; Yulia Tsvetkov

Cross-lingual text summarization aims at generating a document summary in one language given input in another language. It is a practically important but under-explored task, primarily due to the dearth of available data. Existing methods resort to machine translation to synthesize training data, but such pipeline approaches suffer from error propagation. In this work, we propose an end-to-end cross-lingual

更新日期：2020-06-30
• arXiv.cs.CL Pub Date : 2020-06-27
Beliz Gunel; Chenguang Zhu; Michael Zeng; Xuedong Huang

Neural models have become successful at producing abstractive summaries that are human-readable and fluent. However, these models have two critical shortcomings: they often don't respect the facts that are either included in the source article or are known to humans as commonsense knowledge, and they don't produce coherent summaries when the source article is long. In this work, we propose a novel

更新日期：2020-06-30
• arXiv.cs.CL Pub Date : 2020-06-27
David R. W. Sears

This chapter considers how string-based methods might be adapted to address music-analytic questions related to the discovery of musical organization, with particular attention devoted to the analysis of tonal harmony. I begin by applying the taxonomy of mental organization proposed by Mandler (1979) to the concept of musical organization. Using this taxonomy as a guide, I then present evidence for

更新日期：2020-06-30
• arXiv.cs.CL Pub Date : 2020-06-27
Hung Le; Steven C. H. Hoi

Pre-trained language models have shown remarkable success in improving various downstream NLP tasks due to their ability to capture dependencies in textual data and generate natural responses. In this paper, we leverage the power of pre-trained language models for improving video-grounded dialogue, which is very challenging and involves complex features of different dynamics: (1) Video features which

更新日期：2020-06-30
• arXiv.cs.CL Pub Date : 2020-06-27

Recent success of large-scale pre-trained language models crucially hinge on fine-tuning them on large amounts of labeled data for the downstream task, that are typically expensive to acquire. In this work, we study self-training as one of the earliest semi-supervised learning approaches to reduce the annotation bottleneck by making use of large-scale unlabeled data for the target task. Standard self-training

更新日期：2020-06-30
• arXiv.cs.CL Pub Date : 2020-06-26
Jesse Vig; Ali Madani; Lav R. Varshney; Caiming Xiong; Richard Socher; Nazneen Fatema Rajani

Transformer architectures have proven to learn useful representations for protein classification and generation tasks. However, these representations present challenges in interpretability. Through the lens of attention, we analyze the inner workings of the Transformer and explore how the model discerns structural and functional properties of proteins. We show that attention (1) captures the folding

更新日期：2020-06-30
• arXiv.cs.CL Pub Date : 2020-06-29

The explosion of available speech data and new speaker modeling methods based on deep neural networks (DNN) have given the ability to develop more robust speaker recognition systems. Among DNN speaker modelling techniques, x-vector system has shown a degree of robustness in noisy environments. Previous studies suggest that by increasing the number of speakers in the training data and using data augmentation

更新日期：2020-06-30
• arXiv.cs.CL Pub Date : 2020-06-26
Mike Lewis; Marjan Ghazvininejad; Gargi Ghosh; Armen Aghajanyan; Sida Wang; Luke Zettlemoyer

We introduce MARGE, a pre-trained sequence-to-sequence model learned with an unsupervised multi-lingual multi-document paraphrasing objective. MARGE provides an alternative to the dominant masked language modeling paradigm, where we self-supervise the reconstruction of target text by retrieving a set of related texts (in many languages) and conditioning on them to maximize the likelihood of generating

更新日期：2020-06-29
• arXiv.cs.CL Pub Date : 2020-06-26
Andrei Ionut Damian; Laurentiu Piciu; Cosmin Mihai Marinescu

In retail vertical industries, businesses are dealing with human limitation of quickly understanding and adapting to new purchasing behaviors. Moreover, retail businesses need to overcome the human limitation of properly managing a massive selection of products/brands/categories. These limitations lead to deficiencies from both commercial (e.g. loss of sales, decrease in customer satisfaction) and

更新日期：2020-06-29
• arXiv.cs.CL Pub Date : 2020-06-26
Eugene Kharitonov; Rahma Chaabouni

Sequence-to-sequence (seq2seq) learners are widely used, but we still have only limited knowledge about what inductive biases shape the way they generalize. We address that by investigating how popular seq2seq learners generalize in tasks that have high ambiguity in the training data. We use SCAN and three new tasks to study learners' preferences for memorization, arithmetic, hierarchical, and compositional

更新日期：2020-06-29
• arXiv.cs.CL Pub Date : 2020-06-25
Jipeng Qiang; Yun Li; Yi Zhu; Yunhao Yuan; Xindong Wu

Lexical simplification (LS) aims to replace complex words in a given sentence with their simpler alternatives of equivalent meaning, to simplify the sentence. Recently unsupervised lexical simplification approaches only rely on the complex word itself regardless of the given sentence to generate candidate substitutions, which will inevitably produce a large number of spurious candidates. In this paper

更新日期：2020-06-29
• arXiv.cs.CL Pub Date : 2020-06-26
Asli Celikyilmaz; Elizabeth Clark; Jianfeng Gao

The paper surveys evaluation methods of natural language generation (NLG) systems that have been developed in the last few years. We group NLG evaluation methods into three categories: (1) human-centric evaluation metrics, (2) automatic metrics that require no training, and (3) machine-learned metrics. For each category, we discuss the progress that has been made and the challenges still being faced

更新日期：2020-06-29
• arXiv.cs.CL Pub Date : 2020-06-26

Dialog systems research has primarily been focused around two main types of applications - task-oriented dialog systems that learn to use clarification to aid in understanding a goal, and open-ended dialog systems that are expected to carry out unconstrained "chit chat" conversations. However, dialog interactions can also be used to obtain various types of knowledge that can be used to improve an underlying

更新日期：2020-06-29
• arXiv.cs.CL Pub Date : 2020-06-26
Liqun Chen; Zhe Gan; Yu Cheng; Linjie Li; Lawrence Carin; Jingjing Liu

Cross-domain alignment between two sets of entities (e.g., objects in an image, words in a sentence) is fundamental to both computer vision and natural language processing. Existing methods mainly focus on designing advanced attention mechanisms to simulate soft alignment, with no training signals to explicitly encourage alignment. The learned attention matrices are also dense and lacks interpretability

更新日期：2020-06-29
• arXiv.cs.CL Pub Date : 2020-06-25
Rudolf Rosa; Ondřej Dušek; Tom Kocmi; David Mareček; Tomáš Musil; Patrícia Schmidtová; Dominik Jurko; Ondřej Bojar; Daniel Hrbek; David Košťák; Martina Kinská; Josef Doležal; Klára Vosecká

We present THEaiTRE, a starting project aimed at automatic generation of theatre play scripts. This paper reviews related work and drafts an approach we intend to follow. We plan to adopt generative neural language models and hierarchical generation approaches, supported by summarization and machine translation methods, and complemented with a human-in-the-loop approach.

更新日期：2020-06-29
• arXiv.cs.CL Pub Date : 2020-06-25
Pranav Sharma

The goal of serving and delighting customers in a personal and near human like manner is very high on automation agendas of most Enterprises. Last few years, have seen huge progress in Natural Language Processing domain which has led to deployments of conversational agents in many enterprises. Most of the current industrial deployments tend to use Monolithic Single Agent designs that model the entire

更新日期：2020-06-29
• arXiv.cs.CL Pub Date : 2020-06-26
Xiang Deng; Huan Sun; Alyssa Lees; You Wu; Cong Yu

Relational tables on the Web store a vast amount of knowledge. Owing to the wealth of such tables, there has been tremendous progress on a variety of tasks in the area of table understanding. However, existing work generally relies on heavily-engineered task specific features and model architectures. In this paper, we present TURL, a novel framework that introduces the pre-training/finetuning paradigm

更新日期：2020-06-29
• arXiv.cs.CL Pub Date : 2020-06-26
Gagan Bansal; Tongshuang Wu; Joyce Zhu; Raymond Fok; Besmira Nushi; Ece Kamar; Marco Tulio Ribeiro; Daniel S. Weld

Increasingly, organizations are pairing humans with AI systems to improve decision-making and reducing costs. Proponents of human-centered AI argue that team performance can even further improve when the AI model explains its recommendations. However, a careful analysis of existing literature reveals that prior studies observed improvements due to explanations only when the AI, alone, outperformed

更新日期：2020-06-29
• arXiv.cs.CL Pub Date : 2020-06-25
Vivek Srivastava; Mayank Singh

Code-mixing is the phenomenon of using multiple languages in the same utterance of a text or speech. It is a frequently used pattern of communication on various platforms such as social media sites, online gaming, product reviews, etc. Sentiment analysis of the monolingual text is a well-studied task. Code-mixing adds to the challenge of analyzing the sentiment of the text due to the non-standard writing

更新日期：2020-06-26
• arXiv.cs.CL Pub Date : 2020-06-25
Hongfei Xu; Josef van Genabith; Deyi Xiong; Qiuhui Liu; Jingyi Zhang

The Transformer translation model (Vaswani et al., 2017) based on a multi-head attention mechanism can be computed effectively in parallel and has significantly pushed forward the performance of Neural Machine Translation (NMT). Though intuitively the attentional network can connect distant words via shorter network paths than RNNs, empirical analysis demonstrates that it still has difficulty in fully

更新日期：2020-06-26
• arXiv.cs.CL Pub Date : 2020-06-25
Santosh Kumar Barnwal; Uma Shanker Tiwary

Repeated reading (RR) helps learners, who have little to no experience with reading fluently to gain confidence, speed and process words automatically. The benefits of repeated readings include helping all learners with fact recall, aiding identification of learners' main ideas and vocabulary, increasing comprehension, leading to faster reading as well as increasing word recognition accuracy, and assisting

更新日期：2020-06-26
• arXiv.cs.CL Pub Date : 2020-06-25
Alex Sokolov; Denis Filimonov

Training a spoken language understanding system, as the one in Alexa, typically requires a large human-annotated corpus of data. Manual annotations are expensive and time consuming. In Alexa Skill Kit (ASK) user experience with the skill greatly depends on the amount of data provided by skill developer. In this work, we present an automatic natural language generation system, capable of generating

更新日期：2020-06-26
• arXiv.cs.CL Pub Date : 2020-06-25
Marina Sedinkina; Nikolas Breitkopf; Hinrich Schütze

In this paper, we automatically create sentiment dictionaries for predicting financial outcomes. We compare three approaches: (I) manual adaptation of the domain-general dictionary H4N, (ii) automatic adaptation of H4N and (iii) a combination consisting of first manual, then automatic adaptation. In our experiments, we demonstrate that the automatically adapted sentiment dictionary outperforms the

更新日期：2020-06-26
• arXiv.cs.CL Pub Date : 2020-06-25
Rajarshi Das; Ameya Godbole; Shehzaad Dhuliawala; Manzil Zaheer; Andrew McCallum

We present a surprisingly simple yet accurate approach to reasoning in knowledge graphs (KGs) that requires \emph{no training}, and is reminiscent of case-based reasoning in classical artificial intelligence (AI). Consider the task of finding a target entity given a source entity and a binary relation. Our non-parametric approach derives crisp logical rules for each query by finding multiple \textit{graph

更新日期：2020-06-26
• arXiv.cs.CL Pub Date : 2020-06-25
Alex Sokolov; Tracy Rohlin; Ariya Rastrow

Grapheme-to-phoneme (G2P) models are a key component in Automatic Speech Recognition (ASR) systems, such as the ASR system in Alexa, as they are used to generate pronunciations for out-of-vocabulary words that do not exist in the pronunciation lexicons (mappings like "e c h o" to "E k oU"). Most G2P systems are monolingual and based on traditional joint-sequence based n-gram models [1,2]. As an alternative

更新日期：2020-06-26
• arXiv.cs.CL Pub Date : 2020-06-25
Ning Wang; Mingxuan Chen; K. P. Subbalakshmi

In this work, we propose three explainable deep learning architectures to automatically detect patients with Alzheimer`s disease based on their language abilities. The architectures use: (1) only the part-of-speech features; (2) only language embedding features and (3) both of these feature classes via a unified architecture. We use self-attention mechanisms and interpretable 1-dimensional ConvolutionalNeural

更新日期：2020-06-26
• arXiv.cs.CL Pub Date : 2020-06-25
Fenil Doshi; Jimit Gandhi; Deep Gosalia; Sudhir Bagul

Social media networks and chatting platforms often use an informal version of natural text. Adversarial spelling attacks also tend to alter the input text by modifying the characters in the text. Normalizing these texts is an essential step for various applications like language translation and text to speech synthesis where the models are trained over clean regular English language. We propose a new

更新日期：2020-06-26
Contents have been reproduced by permission of the publishers.

down
wechat
bug