Text production (Reiter and Dale 2000; Gatt and Krahmer 2018) is also referred to as natural language generation (NLG). It is a subtask of natural language processing focusing on the generation of natural language text. Although as important as natural language understanding for communication, NLG had received relatively less research attention. Recently, the rise of deep learning techniques has led to a surge of research interest in text production, both in general and for specific applications such as text summarization and dialogue systems. Deep learning allows NLG models to be constructed based on neural representations, thereby enabling end-to-end NLG systems to replace traditional pipeline approaches, which frees us from tedious engineering efforts and improves the output quality. In particular, a neural encoder-decoder structure (Cho et al. 2014; Sutskever, Vinyals, and Le 2014) has been widely used as a basic framework, which computes input representations using a neural encoder, according to which a text sequence is generated token by token using a neural decoder. Very recently, pre-training techniques (Broscheit et al. 2010; Radford 2018; Devlin et al. 2019) have further allowed neural models to collect knowledge from large raw text data, further improving the quality of both encoding and decoding. This book introduces the fundamentals of neural text production, discussing both the mostly investigated tasks and the foundational neural methods. NLG tasks with different types of inputs are introduced, and benchmark datasets are discussed in detail. The encoder-decoder architecture is introduced together with basic neural network components such as convolutional neural network (CNN) (Kim 2014) and recurrent neural network (RNN) (Cho et al. 2014). Elaborations are given on the encoder, the decoder, and task-specific optimization techniques. A contrast is made between the neural solution and traditional solutions to the task. Toward the end of the book, more recent techniques such as self-attention networks (Vaswani et al. 2017) and pre-training are briefly discussed. Throughout the book, figures are given to facilitate understanding and references are provided to enable further reading. Chapter 1 introduces the task of text production, discussing three typical input settings, namely, generation from meaning representations (MR; i.e., realization), generation from data (i.e., data-to-text), and generation from text (i.e., text-to-text). At the end of the chapter, a book outline is given, and the scope, coverage, and notation convention
{"title":"Deep Learning Approaches to Text Production","authors":"Yue Zhang","doi":"10.1162/coli_r_00389","DOIUrl":"https://doi.org/10.1162/coli_r_00389","url":null,"abstract":"Text production (Reiter and Dale 2000; Gatt and Krahmer 2018) is also referred to as natural language generation (NLG). It is a subtask of natural language processing focusing on the generation of natural language text. Although as important as natural language understanding for communication, NLG had received relatively less research attention. Recently, the rise of deep learning techniques has led to a surge of research interest in text production, both in general and for specific applications such as text summarization and dialogue systems. Deep learning allows NLG models to be constructed based on neural representations, thereby enabling end-to-end NLG systems to replace traditional pipeline approaches, which frees us from tedious engineering efforts and improves the output quality. In particular, a neural encoder-decoder structure (Cho et al. 2014; Sutskever, Vinyals, and Le 2014) has been widely used as a basic framework, which computes input representations using a neural encoder, according to which a text sequence is generated token by token using a neural decoder. Very recently, pre-training techniques (Broscheit et al. 2010; Radford 2018; Devlin et al. 2019) have further allowed neural models to collect knowledge from large raw text data, further improving the quality of both encoding and decoding. This book introduces the fundamentals of neural text production, discussing both the mostly investigated tasks and the foundational neural methods. NLG tasks with different types of inputs are introduced, and benchmark datasets are discussed in detail. The encoder-decoder architecture is introduced together with basic neural network components such as convolutional neural network (CNN) (Kim 2014) and recurrent neural network (RNN) (Cho et al. 2014). Elaborations are given on the encoder, the decoder, and task-specific optimization techniques. A contrast is made between the neural solution and traditional solutions to the task. Toward the end of the book, more recent techniques such as self-attention networks (Vaswani et al. 2017) and pre-training are briefly discussed. Throughout the book, figures are given to facilitate understanding and references are provided to enable further reading. Chapter 1 introduces the task of text production, discussing three typical input settings, namely, generation from meaning representations (MR; i.e., realization), generation from data (i.e., data-to-text), and generation from text (i.e., text-to-text). At the end of the chapter, a book outline is given, and the scope, coverage, and notation convention","PeriodicalId":55229,"journal":{"name":"Computational Linguistics","volume":null,"pages":null},"PeriodicalIF":9.3,"publicationDate":"2020-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1162/coli_r_00389","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47652735","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Based on an exponentially increasing number of academic articles, discovering and citing comprehensive and appropriate resources has become a non-trivial task. Conventional citation recommender methods suffer from severe information loss. For example, they do not consider the section of the paper that the user is writing and for which they need to find a citation, the relatedness between the words in the local context (the text span that describes a citation), or the importance on each word from the local context. These shortcomings make such methods insufficient for recommending adequate citations to academic manuscripts. In this study, we propose a novel embedding-based neural network called “dual attention model for citation recommendation (DACR)” to recommend citations during manuscript preparation. Our method adapts embedding of three semantic information: words in the local context, structural contexts, and the section on which a user is working. A neural network model is designed to maximize the similarity between the embedding of the three input (local context words, section and structural contexts) and the target citation appearing in the context. The core of the neural network model is composed of self-attention and additive attention, where the former aims to capture the relatedness between the contextual words and structural context, and the latter aims to learn the importance of them. The experiments on real-world datasets demonstrate the effectiveness of the proposed approach.
在学术论文呈指数级增长的情况下，发现和引用全面、合适的资源已成为一项不容忽视的任务。传统的引文推荐方法存在严重的信息丢失问题。例如，他们不考虑用户正在写的论文的那一部分，他们需要为其找到引文，在本地上下文中单词之间的相关性(描述引文的文本跨度)，或者每个单词在本地上下文中的重要性。这些缺点使得这种方法不足以为学术手稿推荐足够的引文。在本研究中，我们提出了一种新的基于嵌入的神经网络，称为“引文推荐双注意模型(dual attention model for citation recommendation, DACR)”，用于论文准备过程中的引文推荐。我们的方法适应三种语义信息的嵌入:本地上下文中的单词、结构上下文和用户正在工作的部分。设计了一个神经网络模型，使三种输入(局部上下文词、段落和结构上下文)的嵌入与上下文中出现的目标引文之间的相似性最大化。神经网络模型的核心由自注意和加性注意组成，自注意的目的是捕捉上下文词和结构上下文之间的相关性，加性注意的目的是学习它们的重要性。在实际数据集上的实验证明了该方法的有效性。
{"title":"Dual Attention Model for Citation Recommendation","authors":"Yang Zhang, Qiang Ma","doi":"10.1162/coli_a_00438","DOIUrl":"https://doi.org/10.1162/coli_a_00438","url":null,"abstract":"Based on an exponentially increasing number of academic articles, discovering and citing comprehensive and appropriate resources has become a non-trivial task. Conventional citation recommender methods suffer from severe information loss. For example, they do not consider the section of the paper that the user is writing and for which they need to find a citation, the relatedness between the words in the local context (the text span that describes a citation), or the importance on each word from the local context. These shortcomings make such methods insufficient for recommending adequate citations to academic manuscripts. In this study, we propose a novel embedding-based neural network called “dual attention model for citation recommendation (DACR)” to recommend citations during manuscript preparation. Our method adapts embedding of three semantic information: words in the local context, structural contexts, and the section on which a user is working. A neural network model is designed to maximize the similarity between the embedding of the three input (local context words, section and structural contexts) and the target citation appearing in the context. The core of the neural network model is composed of self-attention and additive attention, where the former aims to capture the relatedness between the contextual words and structural context, and the latter aims to learn the importance of them. The experiments on real-world datasets demonstrate the effectiveness of the proposed approach.","PeriodicalId":55229,"journal":{"name":"Computational Linguistics","volume":null,"pages":null},"PeriodicalIF":9.3,"publicationDate":"2020-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41322353","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Semantic role labeling (SRL) is dedicated to recognizing the semantic predicate-argument structure of a sentence. Previous studies in terms of traditional models have shown syntactic information can make remarkable contributions to SRL performance; however, the necessity of syntactic information was challenged by a few recent neural SRL studies that demonstrate impressive performance without syntactic backbones and suggest that syntax information becomes much less important for neural semantic role labeling, especially when paired with recent deep neural network and large-scale pre-trained language models. Despite this notion, the neural SRL field still lacks a systematic and full investigation on the relevance of syntactic information in SRL, for both dependency and both monolingual and multilingual settings. This paper intends to quantify the importance of syntactic information for neural SRL in the deep learning framework. We introduce three typical SRL frameworks (baselines), sequence-based, tree-based, and graph-based, which are accompanied by two categories of exploiting syntactic information: syntax pruning-based and syntax feature-based. Experiments are conducted on the CoNLL-2005, -2009, and -2012 benchmarks for all languages available, and results show that neural SRL models can still benefit from syntactic information under certain conditions. Furthermore, we show the quantitative significance of syntax to neural SRL models together with a thorough empirical survey using existing models.
{"title":"Syntax Role for Neural Semantic Role Labeling","authors":"Z. Li, Hai Zhao, Shexia He, Jiaxun Cai","doi":"10.1162/coli_a_00408","DOIUrl":"https://doi.org/10.1162/coli_a_00408","url":null,"abstract":"Semantic role labeling (SRL) is dedicated to recognizing the semantic predicate-argument structure of a sentence. Previous studies in terms of traditional models have shown syntactic information can make remarkable contributions to SRL performance; however, the necessity of syntactic information was challenged by a few recent neural SRL studies that demonstrate impressive performance without syntactic backbones and suggest that syntax information becomes much less important for neural semantic role labeling, especially when paired with recent deep neural network and large-scale pre-trained language models. Despite this notion, the neural SRL field still lacks a systematic and full investigation on the relevance of syntactic information in SRL, for both dependency and both monolingual and multilingual settings. This paper intends to quantify the importance of syntactic information for neural SRL in the deep learning framework. We introduce three typical SRL frameworks (baselines), sequence-based, tree-based, and graph-based, which are accompanied by two categories of exploiting syntactic information: syntax pruning-based and syntax feature-based. Experiments are conducted on the CoNLL-2005, -2009, and -2012 benchmarks for all languages available, and results show that neural SRL models can still benefit from syntactic information under certain conditions. Furthermore, we show the quantitative significance of syntax to neural SRL models together with a thorough empirical survey using existing models.","PeriodicalId":55229,"journal":{"name":"Computational Linguistics","volume":null,"pages":null},"PeriodicalIF":9.3,"publicationDate":"2020-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45507622","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
M. Costa-jussà, C. España-Bonet, Pascale Fung, Noah A. Smith
We introduce the Computational Linguistics special issue on Multilingual and Interlingual Semantic Representations for Natural Language Processing. We situate the special issue’s five articles in the context of our fast-changing field, explaining our motivation for this project. We offer a brief summary of the work in the issue, which includes developments on lexical and sentential semantic representations, from symbolic and neural perspectives.
{"title":"Multilingual and Interlingual Semantic Representations for Natural Language Processing: A Brief Introduction","authors":"M. Costa-jussà, C. España-Bonet, Pascale Fung, Noah A. Smith","doi":"10.1162/coli_a_00373","DOIUrl":"https://doi.org/10.1162/coli_a_00373","url":null,"abstract":"We introduce the Computational Linguistics special issue on Multilingual and Interlingual Semantic Representations for Natural Language Processing. We situate the special issue’s five articles in the context of our fast-changing field, explaining our motivation for this project. We offer a brief summary of the work in the issue, which includes developments on lexical and sentential semantic representations, from symbolic and neural perspectives.","PeriodicalId":55229,"journal":{"name":"Computational Linguistics","volume":null,"pages":null},"PeriodicalIF":9.3,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1162/coli_a_00373","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48019826","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract Understanding predictions made by deep neural networks is notoriously difficult, but also crucial to their dissemination. As all machine learning–based methods, they are as good as their training data, and can also capture unwanted biases. While there are tools that can help understand whether such biases exist, they do not distinguish between correlation and causation, and might be ill-suited for text-based models and for reasoning about high-level language concepts. A key problem of estimating the causal effect of a concept of interest on a given model is that this estimation requires the generation of counterfactual examples, which is challenging with existing generation technology. To bridge that gap, we propose CausaLM, a framework for producing causal model explanations using counterfactual language representation models. Our approach is based on fine-tuning of deep contextualized embedding models with auxiliary adversarial tasks derived from the causal graph of the problem. Concretely, we show that by carefully choosing auxiliary adversarial pre-training tasks, language representation models such as BERT can effectively learn a counterfactual representation for a given concept of interest, and be used to estimate its true causal effect on model performance. A byproduct of our method is a language representation model that is unaffected by the tested concept, which can be useful in mitigating unwanted bias ingrained in the data.1
{"title":"CausaLM: Causal Model Explanation Through Counterfactual Language Models","authors":"Amir Feder, Nadav Oved, Uri Shalit, Roi Reichart","doi":"10.1162/coli_a_00404","DOIUrl":"https://doi.org/10.1162/coli_a_00404","url":null,"abstract":"Abstract Understanding predictions made by deep neural networks is notoriously difficult, but also crucial to their dissemination. As all machine learning–based methods, they are as good as their training data, and can also capture unwanted biases. While there are tools that can help understand whether such biases exist, they do not distinguish between correlation and causation, and might be ill-suited for text-based models and for reasoning about high-level language concepts. A key problem of estimating the causal effect of a concept of interest on a given model is that this estimation requires the generation of counterfactual examples, which is challenging with existing generation technology. To bridge that gap, we propose CausaLM, a framework for producing causal model explanations using counterfactual language representation models. Our approach is based on fine-tuning of deep contextualized embedding models with auxiliary adversarial tasks derived from the causal graph of the problem. Concretely, we show that by carefully choosing auxiliary adversarial pre-training tasks, language representation models such as BERT can effectively learn a counterfactual representation for a given concept of interest, and be used to estimate its true causal effect on model performance. A byproduct of our method is a language representation model that is unaffected by the tested concept, which can be useful in mitigating unwanted bias ingrained in the data.1","PeriodicalId":55229,"journal":{"name":"Computational Linguistics","volume":null,"pages":null},"PeriodicalIF":9.3,"publicationDate":"2020-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43733662","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Oshin Agarwal, Yinfei Yang, Byron C. Wallace, A. Nenkova
Abstract Named entity recognition systems achieve remarkable performance on domains such as English news. It is natural to ask: What are these models actually learning to achieve this? Are they merely memorizing the names themselves? Or are they capable of interpreting the text and inferring the correct entity type from the linguistic context? We examine these questions by contrasting the performance of several variants of architectures for named entity recognition, with some provided only representations of the context as features. We experiment with GloVe-based BiLSTM-CRF as well as BERT. We find that context does influence predictions, but the main factor driving high performance is learning the named tokens themselves. Furthermore, we find that BERT is not always better at recognizing predictive contexts compared to a BiLSTM-CRF model. We enlist human annotators to evaluate the feasibility of inferring entity types from context alone and find that humans are also mostly unable to infer entity types for the majority of examples on which the context-only system made errors. However, there is room for improvement: A system should be able to recognize any named entity in a predictive context correctly and our experiments indicate that current systems may be improved by such capability. Our human study also revealed that systems and humans do not always learn the same contextual clues, and context-only systems are sometimes correct even when humans fail to recognize the entity type from the context. Finally, we find that one issue contributing to model errors is the use of “entangled” representations that encode both contextual and local token information into a single vector, which can obscure clues. Our results suggest that designing models that explicitly operate over representations of local inputs and context, respectively, may in some cases improve performance. In light of these and related findings, we highlight directions for future work.
{"title":"Interpretability Analysis for Named Entity Recognition to Understand System Predictions and How They Can Improve","authors":"Oshin Agarwal, Yinfei Yang, Byron C. Wallace, A. Nenkova","doi":"10.1162/coli_a_00397","DOIUrl":"https://doi.org/10.1162/coli_a_00397","url":null,"abstract":"Abstract Named entity recognition systems achieve remarkable performance on domains such as English news. It is natural to ask: What are these models actually learning to achieve this? Are they merely memorizing the names themselves? Or are they capable of interpreting the text and inferring the correct entity type from the linguistic context? We examine these questions by contrasting the performance of several variants of architectures for named entity recognition, with some provided only representations of the context as features. We experiment with GloVe-based BiLSTM-CRF as well as BERT. We find that context does influence predictions, but the main factor driving high performance is learning the named tokens themselves. Furthermore, we find that BERT is not always better at recognizing predictive contexts compared to a BiLSTM-CRF model. We enlist human annotators to evaluate the feasibility of inferring entity types from context alone and find that humans are also mostly unable to infer entity types for the majority of examples on which the context-only system made errors. However, there is room for improvement: A system should be able to recognize any named entity in a predictive context correctly and our experiments indicate that current systems may be improved by such capability. Our human study also revealed that systems and humans do not always learn the same contextual clues, and context-only systems are sometimes correct even when humans fail to recognize the entity type from the context. Finally, we find that one issue contributing to model errors is the use of “entangled” representations that encode both contextual and local token information into a single vector, which can obscure clues. Our results suggest that designing models that explicitly operate over representations of local inputs and context, respectively, may in some cases improve performance. In light of these and related findings, we highlight directions for future work.","PeriodicalId":55229,"journal":{"name":"Computational Linguistics","volume":null,"pages":null},"PeriodicalIF":9.3,"publicationDate":"2020-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42716335","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Donghyun Choi, M. Shin, EungGyun Kim, Dong Ryeol Shin
Abstract Text-to-SQL is the problem of converting a user question into an SQL query, when the question and database are given. In this article, we present a neural network approach called RYANSQL (Recursively Yielding Annotation Network for SQL) to solve complex Text-to-SQL tasks for cross-domain databases. Statement Position Code (SPC) is defined to transform a nested SQL query into a set of non-nested SELECT statements; a sketch-based slot-filling approach is proposed to synthesize each SELECT statement for its corresponding SPC. Additionally, two input manipulation methods are presented to improve generation performance further. RYANSQL achieved competitive result of 58.2% accuracy on the challenging Spider benchmark. At the time of submission (April 2020), RYANSQL v2, a variant of original RYANSQL, is positioned at 3rd place among all systems and 1st place among the systems not using database content with 60.6% exact matching accuracy. The source code is available at https://github.com/kakaoenterprise/RYANSQL.
{"title":"RYANSQL: Recursively Applying Sketch-based Slot Fillings for Complex Text-to-SQL in Cross-Domain Databases","authors":"Donghyun Choi, M. Shin, EungGyun Kim, Dong Ryeol Shin","doi":"10.1162/coli_a_00403","DOIUrl":"https://doi.org/10.1162/coli_a_00403","url":null,"abstract":"Abstract Text-to-SQL is the problem of converting a user question into an SQL query, when the question and database are given. In this article, we present a neural network approach called RYANSQL (Recursively Yielding Annotation Network for SQL) to solve complex Text-to-SQL tasks for cross-domain databases. Statement Position Code (SPC) is defined to transform a nested SQL query into a set of non-nested SELECT statements; a sketch-based slot-filling approach is proposed to synthesize each SELECT statement for its corresponding SPC. Additionally, two input manipulation methods are presented to improve generation performance further. RYANSQL achieved competitive result of 58.2% accuracy on the challenging Spider benchmark. At the time of submission (April 2020), RYANSQL v2, a variant of original RYANSQL, is positioned at 3rd place among all systems and 1st place among the systems not using database content with 60.6% exact matching accuracy. The source code is available at https://github.com/kakaoenterprise/RYANSQL.","PeriodicalId":55229,"journal":{"name":"Computational Linguistics","volume":null,"pages":null},"PeriodicalIF":9.3,"publicationDate":"2020-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46339879","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Semantics is commonly defined as “the study of meaning” while pragmatics is generally referred to as “the study of meaning in context”. In other words, semantics deal with the sentence meaning (e.g., literal meaning of “How are you?”), while pragmatics is more concerned with the speaker/utterance meaning (e.g., the greeting meaning of “How are you?”). Both fields interact with each other and with other lower layers of language such as phonology, morphology and syntax in many ways. Semantics and pragmatics have been established as research fields a long time ago and been widely studied ever since, as also evidenced by a number of introductory text books dating from 80s to this date (Kroeger 2018; Levinson 1983; Cruse 2000; Birner 2012/2013; Kadmon 2001). Previous introductory books are remarkably rich with linguistic theorems and provide a comprehensive introduction to the topic. However, the majority of them offer a
{"title":"Linguistic Fundemantals for Natural Language Processing II: 100 Essentials from Semantics and Pragmatics","authors":"Gözde Gül Şahin","doi":"10.1162/coli_r_00381","DOIUrl":"https://doi.org/10.1162/coli_r_00381","url":null,"abstract":"Semantics is commonly defined as “the study of meaning” while pragmatics is generally referred to as “the study of meaning in context”. In other words, semantics deal with the sentence meaning (e.g., literal meaning of “How are you?”), while pragmatics is more concerned with the speaker/utterance meaning (e.g., the greeting meaning of “How are you?”). Both fields interact with each other and with other lower layers of language such as phonology, morphology and syntax in many ways. Semantics and pragmatics have been established as research fields a long time ago and been widely studied ever since, as also evidenced by a number of introductory text books dating from 80s to this date (Kroeger 2018; Levinson 1983; Cruse 2000; Birner 2012/2013; Kadmon 2001). Previous introductory books are remarkably rich with linguistic theorems and provide a comprehensive introduction to the topic. However, the majority of them offer a","PeriodicalId":55229,"journal":{"name":"Computational Linguistics","volume":null,"pages":null},"PeriodicalIF":9.3,"publicationDate":"2020-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141221205","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Fernando Alva-Manchego, Carolina Scarton, Lucia Specia
Sentence Simplification (SS) aims to modify a sentence in order to make it easier to read and understand. In order to do so, several rewriting transformations can be performed such as replacement, reordering, and splitting. Executing these transformations while keeping sentences grammatical, preserving their main idea, and generating simpler output, is a challenging and still far from solved problem. In this article, we survey research on SS, focusing on approaches that attempt to learn how to simplify using corpora of aligned original-simplified sentence pairs in English, which is the dominant paradigm nowadays. We also include a benchmark of different approaches on common data sets so as to compare them and highlight their strengths and limitations. We expect that this survey will serve as a starting point for researchers interested in the task and help spark new ideas for future developments.
{"title":"Data-Driven Sentence Simplification: Survey and Benchmark","authors":"Fernando Alva-Manchego, Carolina Scarton, Lucia Specia","doi":"10.1162/coli_a_00370","DOIUrl":"https://doi.org/10.1162/coli_a_00370","url":null,"abstract":"Sentence Simplification (SS) aims to modify a sentence in order to make it easier to read and understand. In order to do so, several rewriting transformations can be performed such as replacement, reordering, and splitting. Executing these transformations while keeping sentences grammatical, preserving their main idea, and generating simpler output, is a challenging and still far from solved problem. In this article, we survey research on SS, focusing on approaches that attempt to learn how to simplify using corpora of aligned original-simplified sentence pairs in English, which is the dominant paradigm nowadays. We also include a benchmark of different approaches on common data sets so as to compare them and highlight their strengths and limitations. We expect that this survey will serve as a starting point for researchers interested in the task and help spark new ideas for future developments.","PeriodicalId":55229,"journal":{"name":"Computational Linguistics","volume":null,"pages":null},"PeriodicalIF":9.3,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1162/coli_a_00370","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49142042","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Ivan Vulic, Simon Baker, E. Ponti, Ulla Petti, Ira Leviant, Kelly Wing, Olga Majewska, Eden Bar, Matt Malone, T. Poibeau, Roi Reichart, A. Korhonen
Abstract We introduce Multi-SimLex, a large-scale lexical resource and evaluation benchmark covering data sets for 12 typologically diverse languages, including major languages (e.g., Mandarin Chinese, Spanish, Russian) as well as less-resourced ones (e.g., Welsh, Kiswahili). Each language data set is annotated for the lexical relation of semantic similarity and contains 1,888 semantically aligned concept pairs, providing a representative coverage of word classes (nouns, verbs, adjectives, adverbs), frequency ranks, similarity intervals, lexical fields, and concreteness levels. Additionally, owing to the alignment of concepts across languages, we provide a suite of 66 crosslingual semantic similarity data sets. Because of its extensive size and language coverage, Multi-SimLex provides entirely novel opportunities for experimental evaluation and analysis. On its monolingual and crosslingual benchmarks, we evaluate and analyze a wide array of recent state-of-the-art monolingual and crosslingual representation models, including static and contextualized word embeddings (such as fastText, monolingual and multilingual BERT, XLM), externally informed lexical representations, as well as fully unsupervised and (weakly) supervised crosslingual word embeddings. We also present a step-by-step data set creation protocol for creating consistent, Multi-Simlex–style resources for additional languages. We make these contributions—the public release of Multi-SimLex data sets, their creation protocol, strong baseline results, and in-depth analyses which can be helpful in guiding future developments in multilingual lexical semantics and representation learning—available via a Web site that will encourage community effort in further expansion of Multi-Simlex to many more languages. Such a large-scale semantic resource could inspire significant further advances in NLP across languages.
{"title":"Multi-SimLex: A Large-Scale Evaluation of Multilingual and Crosslingual Lexical Semantic Similarity","authors":"Ivan Vulic, Simon Baker, E. Ponti, Ulla Petti, Ira Leviant, Kelly Wing, Olga Majewska, Eden Bar, Matt Malone, T. Poibeau, Roi Reichart, A. Korhonen","doi":"10.1162/coli_a_00391","DOIUrl":"https://doi.org/10.1162/coli_a_00391","url":null,"abstract":"Abstract We introduce Multi-SimLex, a large-scale lexical resource and evaluation benchmark covering data sets for 12 typologically diverse languages, including major languages (e.g., Mandarin Chinese, Spanish, Russian) as well as less-resourced ones (e.g., Welsh, Kiswahili). Each language data set is annotated for the lexical relation of semantic similarity and contains 1,888 semantically aligned concept pairs, providing a representative coverage of word classes (nouns, verbs, adjectives, adverbs), frequency ranks, similarity intervals, lexical fields, and concreteness levels. Additionally, owing to the alignment of concepts across languages, we provide a suite of 66 crosslingual semantic similarity data sets. Because of its extensive size and language coverage, Multi-SimLex provides entirely novel opportunities for experimental evaluation and analysis. On its monolingual and crosslingual benchmarks, we evaluate and analyze a wide array of recent state-of-the-art monolingual and crosslingual representation models, including static and contextualized word embeddings (such as fastText, monolingual and multilingual BERT, XLM), externally informed lexical representations, as well as fully unsupervised and (weakly) supervised crosslingual word embeddings. We also present a step-by-step data set creation protocol for creating consistent, Multi-Simlex–style resources for additional languages. We make these contributions—the public release of Multi-SimLex data sets, their creation protocol, strong baseline results, and in-depth analyses which can be helpful in guiding future developments in multilingual lexical semantics and representation learning—available via a Web site that will encourage community effort in further expansion of Multi-Simlex to many more languages. Such a large-scale semantic resource could inspire significant further advances in NLP across languages.","PeriodicalId":55229,"journal":{"name":"Computational Linguistics","volume":null,"pages":null},"PeriodicalIF":9.3,"publicationDate":"2020-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1162/coli_a_00391","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45590264","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：