Probing classifiers have emerged as one of the prominent methodologies for interpreting and analyzing deep neural network models of natural language processing. The basic idea is simple—a classifier is trained to predict some linguistic property from a model’s representations—and has been used to examine a wide variety of models and properties. However, recent studies have demonstrated various methodological limitations of this approach. This squib critically reviews the probing classifiers framework, highlighting their promises, shortcomings, and advances.
{"title":"Probing Classifiers: Promises, Shortcomings, and Advances","authors":"Yonatan Belinkov","doi":"10.1162/coli_a_00422","DOIUrl":"https://doi.org/10.1162/coli_a_00422","url":null,"abstract":"Probing classifiers have emerged as one of the prominent methodologies for interpreting and analyzing deep neural network models of natural language processing. The basic idea is simple—a classifier is trained to predict some linguistic property from a model’s representations—and has been used to examine a wide variety of models and properties. However, recent studies have demonstrated various methodological limitations of this approach. This squib critically reviews the probing classifiers framework, highlighting their promises, shortcomings, and advances.","PeriodicalId":55229,"journal":{"name":"Computational Linguistics","volume":null,"pages":null},"PeriodicalIF":9.3,"publicationDate":"2021-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41865947","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 Transformers are arguably the main workhorse in recent natural language processing research. By definition, a Transformer is invariant with respect to reordering of the input. However, language is inherently sequential and word order is essential to the semantics and syntax of an utterance. In this article, we provide an overview and theoretical comparison of existing methods to incorporate position information into Transformer models. The objectives of this survey are to (1) showcase that position information in Transformer is a vibrant and extensive research area; (2) enable the reader to compare existing methods by providing a unified notation and systematization of different approaches along important model dimensions; (3) indicate what characteristics of an application should be taken into account when selecting a position encoding; and (4) provide stimuli for future research.
{"title":"Position Information in Transformers: An Overview","authors":"Philipp Dufter, Martin Schmitt, Hinrich Schütze","doi":"10.1162/coli_a_00445","DOIUrl":"https://doi.org/10.1162/coli_a_00445","url":null,"abstract":"Abstract Transformers are arguably the main workhorse in recent natural language processing research. By definition, a Transformer is invariant with respect to reordering of the input. However, language is inherently sequential and word order is essential to the semantics and syntax of an utterance. In this article, we provide an overview and theoretical comparison of existing methods to incorporate position information into Transformer models. The objectives of this survey are to (1) showcase that position information in Transformer is a vibrant and extensive research area; (2) enable the reader to compare existing methods by providing a unified notation and systematization of different approaches along important model dimensions; (3) indicate what characteristics of an application should be taken into account when selecting a position encoding; and (4) provide stimuli for future research.","PeriodicalId":55229,"journal":{"name":"Computational Linguistics","volume":null,"pages":null},"PeriodicalIF":9.3,"publicationDate":"2021-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47131158","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 The transcription bottleneck is often cited as a major obstacle for efforts to document the world’s endangered languages and supply them with language technologies. One solution is to extend methods from automatic speech recognition and machine translation, and recruit linguists to provide narrow phonetic transcriptions and sentence-aligned translations. However, I believe that these approaches are not a good fit with the available data and skills, or with long-established practices that are essentially word-based. In seeking a more effective approach, I consider a century of transcription practice and a wide range of computational approaches, before proposing a computational model based on spoken term detection that I call “sparse transcription.” This represents a shift away from current assumptions that we transcribe phones, transcribe fully, and transcribe first. Instead, sparse transcription combines the older practice of word-level transcription with interpretive, iterative, and interactive processes that are amenable to wider participation and that open the way to new methods for processing oral languages.
{"title":"Sparse Transcription","authors":"Steven Bird","doi":"10.1162/coli_a_00387","DOIUrl":"https://doi.org/10.1162/coli_a_00387","url":null,"abstract":"Abstract The transcription bottleneck is often cited as a major obstacle for efforts to document the world’s endangered languages and supply them with language technologies. One solution is to extend methods from automatic speech recognition and machine translation, and recruit linguists to provide narrow phonetic transcriptions and sentence-aligned translations. However, I believe that these approaches are not a good fit with the available data and skills, or with long-established practices that are essentially word-based. In seeking a more effective approach, I consider a century of transcription practice and a wide range of computational approaches, before proposing a computational model based on spoken term detection that I call “sparse transcription.” This represents a shift away from current assumptions that we transcribe phones, transcribe fully, and transcribe first. Instead, sparse transcription combines the older practice of word-level transcription with interpretive, iterative, and interactive processes that are amenable to wider participation and that open the way to new methods for processing oral languages.","PeriodicalId":55229,"journal":{"name":"Computational Linguistics","volume":null,"pages":null},"PeriodicalIF":9.3,"publicationDate":"2021-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"64495105","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 Weighted deduction systems provide a framework for describing parsing algorithms that can be used with a variety of operations for combining the values of partial derivations. For some operations, inside values can be computed efficiently, but outside values cannot. We view out-side values as functions from inside values to the total value of all derivations, and we analyze outside computation in terms of function composition. This viewpoint helps explain why efficient outside computation is possible in many settings, despite the lack of a general outside algorithm for semiring operations.
{"title":"Efficient Outside Computation","authors":"D. Gildea","doi":"10.1162/coli_a_00386","DOIUrl":"https://doi.org/10.1162/coli_a_00386","url":null,"abstract":"Abstract Weighted deduction systems provide a framework for describing parsing algorithms that can be used with a variety of operations for combining the values of partial derivations. For some operations, inside values can be computed efficiently, but outside values cannot. We view out-side values as functions from inside values to the total value of all derivations, and we analyze outside computation in terms of function composition. This viewpoint helps explain why efficient outside computation is possible in many settings, despite the lack of a general outside algorithm for semiring operations.","PeriodicalId":55229,"journal":{"name":"Computational Linguistics","volume":null,"pages":null},"PeriodicalIF":9.3,"publicationDate":"2021-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1162/coli_a_00386","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"64495031","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}
Cross-document event coreference resolution (CDCR) is an NLP task in which mentions of events need to be identified and clustered throughout a collection of documents. CDCR aims to benefit downstream multidocument applications, but despite recent progress on corpora and system development, downstream improvements from applying CDCR have not been shown yet. We make the observation that every CDCR system to date was developed, trained, and tested only on a single respective corpus. This raises strong concerns on their generalizability—a must-have for downstream applications where the magnitude of domains or event mentions is likely to exceed those found in a curated corpus. To investigate this assumption, we define a uniform evaluation setup involving three CDCR corpora: ECB+, the Gun Violence Corpus, and the Football Coreference Corpus (which we reannotate on token level to make our analysis possible). We compare a corpus-independent, feature-based system against a recent neural system developed for ECB+. Although being inferior in absolute numbers, the feature-based system shows more consistent performance across all corpora whereas the neural system is hit-or-miss. Via model introspection, we find that the importance of event actions, event time, and so forth, for resolving coreference in practice varies greatly between the corpora. Additional analysis shows that several systems overfit on the structure of the ECB+ corpus. We conclude with recommendations on how to achieve generally applicable CDCR systems in the future—the most important being that evaluation on multiple CDCR corpora is strongly necessary. To facilitate future research, we release our dataset, annotation guidelines, and system implementation to the public.1
{"title":"Generalizing Cross-Document Event Coreference Resolution Across Multiple Corpora","authors":"M. Bugert, Nils Reimers, Iryna Gurevych","doi":"10.1162/coli_a_00407","DOIUrl":"https://doi.org/10.1162/coli_a_00407","url":null,"abstract":"Cross-document event coreference resolution (CDCR) is an NLP task in which mentions of events need to be identified and clustered throughout a collection of documents. CDCR aims to benefit downstream multidocument applications, but despite recent progress on corpora and system development, downstream improvements from applying CDCR have not been shown yet. We make the observation that every CDCR system to date was developed, trained, and tested only on a single respective corpus. This raises strong concerns on their generalizability—a must-have for downstream applications where the magnitude of domains or event mentions is likely to exceed those found in a curated corpus. To investigate this assumption, we define a uniform evaluation setup involving three CDCR corpora: ECB+, the Gun Violence Corpus, and the Football Coreference Corpus (which we reannotate on token level to make our analysis possible). We compare a corpus-independent, feature-based system against a recent neural system developed for ECB+. Although being inferior in absolute numbers, the feature-based system shows more consistent performance across all corpora whereas the neural system is hit-or-miss. Via model introspection, we find that the importance of event actions, event time, and so forth, for resolving coreference in practice varies greatly between the corpora. Additional analysis shows that several systems overfit on the structure of the ECB+ corpus. We conclude with recommendations on how to achieve generally applicable CDCR systems in the future—the most important being that evaluation on multiple CDCR corpora is strongly necessary. To facilitate future research, we release our dataset, annotation guidelines, and system implementation to the public.1","PeriodicalId":55229,"journal":{"name":"Computational Linguistics","volume":null,"pages":null},"PeriodicalIF":9.3,"publicationDate":"2020-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43656801","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}
Di Jin, Zhijing Jin, Zhiting Hu, Olga Vechtomova, Rada Mihalcea
Text style transfer is an important task in natural language generation, which aims to control certain attributes in the generated text, such as politeness, emotion, humor, and many others. It has a long history in the field of natural language processing, and recently has re-gained significant attention thanks to the promising performance brought by deep neural models. In this article, we present a systematic survey of the research on neural text style transfer, spanning over 100 representative articles since the first neural text style transfer work in 2017. We discuss the task formulation, existing datasets and subtasks, evaluation, as well as the rich methodologies in the presence of parallel and non-parallel data. We also provide discussions on a variety of important topics regarding the future development of this task.1
{"title":"Deep Learning for Text Style Transfer: A Survey","authors":"Di Jin, Zhijing Jin, Zhiting Hu, Olga Vechtomova, Rada Mihalcea","doi":"10.1162/coli_a_00426","DOIUrl":"https://doi.org/10.1162/coli_a_00426","url":null,"abstract":"Text style transfer is an important task in natural language generation, which aims to control certain attributes in the generated text, such as politeness, emotion, humor, and many others. It has a long history in the field of natural language processing, and recently has re-gained significant attention thanks to the promising performance brought by deep neural models. In this article, we present a systematic survey of the research on neural text style transfer, spanning over 100 representative articles since the first neural text style transfer work in 2017. We discuss the task formulation, existing datasets and subtasks, evaluation, as well as the rich methodologies in the presence of parallel and non-parallel data. We also provide discussions on a variety of important topics regarding the future development of this task.1","PeriodicalId":55229,"journal":{"name":"Computational Linguistics","volume":null,"pages":null},"PeriodicalIF":9.3,"publicationDate":"2020-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49448679","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}
This article gives an overview of how sentence meaning is represented in eleven deep-syntactic frameworks, ranging from those based on linguistic theories elaborated for decades to rather lightweight NLP-motivated approaches. We outline the most important characteristics of each framework and then discuss how particular language phenomena are treated across those frameworks, while trying to shed light on commonalities as well as differences.
{"title":"Sentence Meaning Representations Across Languages: What Can We Learn from Existing Frameworks?","authors":"Z. Žabokrtský, Daniel Zeman, M. Sevcíková","doi":"10.1162/coli_a_00385","DOIUrl":"https://doi.org/10.1162/coli_a_00385","url":null,"abstract":"This article gives an overview of how sentence meaning is represented in eleven deep-syntactic frameworks, ranging from those based on linguistic theories elaborated for decades to rather lightweight NLP-motivated approaches. We outline the most important characteristics of each framework and then discuss how particular language phenomena are treated across those frameworks, while trying to shed light on commonalities as well as differences.","PeriodicalId":55229,"journal":{"name":"Computational Linguistics","volume":null,"pages":null},"PeriodicalIF":9.3,"publicationDate":"2020-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1162/coli_a_00385","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46473082","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}
The formalism for Lexical-Functional Grammar (LFG) was introduced in the 1980s as one of the first constraint-based grammatical formalisms for natural language. It has led to substantial contributions to the linguistic literature and to the construction of large-scale descriptions of particular languages. Investigations of its mathematical properties have shown that, without further restrictions, the recognition, emptiness, and generation problems are undecidable, and that they are intractable in the worst case even with commonly applied restrictions. However, grammars of real languages appear not to invoke the full expressive power of the formalism, as indicated by the fact that algorithms and implementations for recognition and generation have been developed that run—even for broad-coverage grammars—in typically polynomial time. This article formalizes some restrictions on the notation and its interpretation that are compatible with conventions and principles that have been implicit or informally stated in linguistic theory. We show that LFG grammars that respect these restrictions, while still suitable for the description of natural languages, are equivalent to linear context-free rewriting systems and allow for tractable computation.
{"title":"Tractable Lexical-Functional Grammar","authors":"Jürgen Wedekind, R. Kaplan","doi":"10.1162/coli_a_00384","DOIUrl":"https://doi.org/10.1162/coli_a_00384","url":null,"abstract":"The formalism for Lexical-Functional Grammar (LFG) was introduced in the 1980s as one of the first constraint-based grammatical formalisms for natural language. It has led to substantial contributions to the linguistic literature and to the construction of large-scale descriptions of particular languages. Investigations of its mathematical properties have shown that, without further restrictions, the recognition, emptiness, and generation problems are undecidable, and that they are intractable in the worst case even with commonly applied restrictions. However, grammars of real languages appear not to invoke the full expressive power of the formalism, as indicated by the fact that algorithms and implementations for recognition and generation have been developed that run—even for broad-coverage grammars—in typically polynomial time. This article formalizes some restrictions on the notation and its interpretation that are compatible with conventions and principles that have been implicit or informally stated in linguistic theory. We show that LFG grammars that respect these restrictions, while still suitable for the description of natural languages, are equivalent to linear context-free rewriting systems and allow for tractable computation.","PeriodicalId":55229,"journal":{"name":"Computational Linguistics","volume":null,"pages":null},"PeriodicalIF":9.3,"publicationDate":"2020-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47112928","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}
A. Krishna, Ashim Gupta, Pawan Goyal, Bishal Santra, Pavankumar Satuluri
Abstract We propose a framework using energy-based models for multiple structured prediction tasks in Sanskrit. Ours is an arc-factored model, similar to the graph-based parsing approaches, and we consider the tasks of word segmentation, morphological parsing, dependency parsing, syntactic linearization, and prosodification, a “prosody-level” task we introduce in this work. Ours is a search-based structured prediction framework, which expects a graph as input, where relevant linguistic information is encoded in the nodes, and the edges are then used to indicate the association between these nodes. Typically, the state-of-the-art models for morphosyntactic tasks in morphologically rich languages still rely on hand-crafted features for their performance. But here, we automate the learning of the feature function. The feature function so learned, along with the search space we construct, encode relevant linguistic information for the tasks we consider. This enables us to substantially reduce the training data requirements to as low as 10%, as compared to the data requirements for the neural state-of-the-art models. Our experiments in Czech and Sanskrit show the language-agnostic nature of the framework, where we train highly competitive models for both the languages. Moreover, our framework enables us to incorporate language-specific constraints to prune the search space and to filter the candidates during inference. We obtain significant improvements in morphosyntactic tasks for Sanskrit by incorporating language-specific constraints into the model. In all the tasks we discuss for Sanskrit, we either achieve state-of-the-art results or ours is the only data-driven solution for those tasks.
{"title":"A Graph-Based Framework for Structured Prediction Tasks in Sanskrit","authors":"A. Krishna, Ashim Gupta, Pawan Goyal, Bishal Santra, Pavankumar Satuluri","doi":"10.1162/coli_a_00390","DOIUrl":"https://doi.org/10.1162/coli_a_00390","url":null,"abstract":"Abstract We propose a framework using energy-based models for multiple structured prediction tasks in Sanskrit. Ours is an arc-factored model, similar to the graph-based parsing approaches, and we consider the tasks of word segmentation, morphological parsing, dependency parsing, syntactic linearization, and prosodification, a “prosody-level” task we introduce in this work. Ours is a search-based structured prediction framework, which expects a graph as input, where relevant linguistic information is encoded in the nodes, and the edges are then used to indicate the association between these nodes. Typically, the state-of-the-art models for morphosyntactic tasks in morphologically rich languages still rely on hand-crafted features for their performance. But here, we automate the learning of the feature function. The feature function so learned, along with the search space we construct, encode relevant linguistic information for the tasks we consider. This enables us to substantially reduce the training data requirements to as low as 10%, as compared to the data requirements for the neural state-of-the-art models. Our experiments in Czech and Sanskrit show the language-agnostic nature of the framework, where we train highly competitive models for both the languages. Moreover, our framework enables us to incorporate language-specific constraints to prune the search space and to filter the candidates during inference. We obtain significant improvements in morphosyntactic tasks for Sanskrit by incorporating language-specific constraints into the model. In all the tasks we discuss for Sanskrit, we either achieve state-of-the-art results or ours is the only data-driven solution for those tasks.","PeriodicalId":55229,"journal":{"name":"Computational Linguistics","volume":null,"pages":null},"PeriodicalIF":9.3,"publicationDate":"2020-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49092390","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}
Like any other science, research in natural language processing (NLP) depends on the ability to draw correct conclusions from experiments. A key tool for this is statistical significance testing: We use it to judge whether a result provides meaningful, generalizable findings or should be taken with a pinch of salt. When comparing new methods against others, performance metrics often differ by only small amounts, so researchers turn to significance tests to show that improved models are genuinely better. Unfortunately, this reasoning often fails because we choose inappropriate significance tests or carry them out incorrectly, making their outcomes meaningless. Or, the test we use may fail to indicate a significant result when a more appropriate test would find one. NLP researchers must avoid these pitfalls to ensure that their evaluations are sound and ultimately avoid wasting time and money through incorrect conclusions. This book guides NLP researchers through the whole process of significance testing, making it easy to select the right kind of test by matching canonical NLP tasks to specific significance testing procedures. As well as being a handbook for researchers, the book provides theoretical background on significance testing, includes new methods that solve problems with significance tests in the world of deep learning and multidataset benchmarks, and describes the open research problems of significance testing for NLP. The book focuses on the task of comparing one algorithm with another. At the core of this is the p-value, the probability that a difference at least as extreme as the one we observed could occur by chance. If the p-value falls below a predetermined threshold, the result is declared significant. Leaving aside the fundamental limitation of turning the validity of results into a binary question with an arbitrary threshold, to be a valid statistical significance test, the p-value must be computed in the right way. The book describes the two crucial properties of an appropriate significance test: The test must be both valid and powerful. Validity refers to the avoidance of type 1 errors, in which the result is incorrectly declared significant. Common mistakes that lead to type 1 errors include deploying tests that make incorrect assumptions, such as independence between data points. The power of a test refers to its ability to detect a significant result and therefore to avoid type 2 errors. Here, knowledge of the data and experiment must be used to choose a test that makes the correct assumptions. There is a trade-off between validity and power, but for the most common NLP tasks (language modeling, sequence labeling, translation, etc.), there are clear choices of tests that provide a good balance.
{"title":"Statistical Significance Testing for Natural Language Processing","authors":"Edwin Simpson","doi":"10.1162/coli_r_00388","DOIUrl":"https://doi.org/10.1162/coli_r_00388","url":null,"abstract":"Like any other science, research in natural language processing (NLP) depends on the ability to draw correct conclusions from experiments. A key tool for this is statistical significance testing: We use it to judge whether a result provides meaningful, generalizable findings or should be taken with a pinch of salt. When comparing new methods against others, performance metrics often differ by only small amounts, so researchers turn to significance tests to show that improved models are genuinely better. Unfortunately, this reasoning often fails because we choose inappropriate significance tests or carry them out incorrectly, making their outcomes meaningless. Or, the test we use may fail to indicate a significant result when a more appropriate test would find one. NLP researchers must avoid these pitfalls to ensure that their evaluations are sound and ultimately avoid wasting time and money through incorrect conclusions. This book guides NLP researchers through the whole process of significance testing, making it easy to select the right kind of test by matching canonical NLP tasks to specific significance testing procedures. As well as being a handbook for researchers, the book provides theoretical background on significance testing, includes new methods that solve problems with significance tests in the world of deep learning and multidataset benchmarks, and describes the open research problems of significance testing for NLP. The book focuses on the task of comparing one algorithm with another. At the core of this is the p-value, the probability that a difference at least as extreme as the one we observed could occur by chance. If the p-value falls below a predetermined threshold, the result is declared significant. Leaving aside the fundamental limitation of turning the validity of results into a binary question with an arbitrary threshold, to be a valid statistical significance test, the p-value must be computed in the right way. The book describes the two crucial properties of an appropriate significance test: The test must be both valid and powerful. Validity refers to the avoidance of type 1 errors, in which the result is incorrectly declared significant. Common mistakes that lead to type 1 errors include deploying tests that make incorrect assumptions, such as independence between data points. The power of a test refers to its ability to detect a significant result and therefore to avoid type 2 errors. Here, knowledge of the data and experiment must be used to choose a test that makes the correct assumptions. There is a trade-off between validity and power, but for the most common NLP tasks (language modeling, sequence labeling, translation, etc.), there are clear choices of tests that provide a good balance.","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_00388","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43183053","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：