scispace - formally typeset
Search or ask a question
Posted Content

The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics.

TL;DR: GEM as discussed by the authors is a living benchmark for natural language generation (NLG), its Evaluation and Metrics, which provides an environment in which models can easily be applied to a wide set of tasks and in which evaluation strategies can be tested.
Abstract: We introduce GEM, a living benchmark for natural language Generation (NLG), its Evaluation, and Metrics. Measuring progress in NLG relies on a constantly evolving ecosystem of automated metrics, datasets, and human evaluation standards. Due to this moving target, new models often still evaluate on divergent anglo-centric corpora with well-established, but flawed, metrics. This disconnect makes it challenging to identify the limitations of current models and opportunities for progress. Addressing this limitation, GEM provides an environment in which models can easily be applied to a wide set of tasks and in which evaluation strategies can be tested. Regular updates to the benchmark will help NLG research become more multilingual and evolve the challenge alongside models. This paper serves as the description of the data for which we are organizing a shared task at our ACL 2021 Workshop and to which we invite the entire NLG community to participate.
Citations
More filters
Posted Content
TL;DR: This paper surveys evaluation methods of natural language generation (NLG) systems that have been developed in the last few years, with a focus on the evaluation of recently proposed NLG tasks and neural NLG models.
Abstract: 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, with a focus on the evaluation of recently proposed NLG tasks and neural NLG models We then present two examples for task-specific NLG evaluations for automatic text summarization and long text generation, and conclude the paper by proposing future research directions

186 citations

Posted Content
TL;DR: A comprehensive review of the research on knowledge-enhanced text generation over the past five years is presented, which includes two parts: (i) general methods and architectures for integrating knowledge into text generation; (ii) specific techniques and applications according to different forms of knowledge data.
Abstract: The goal of text generation is to make machines express in human language. It is one of the most important yet challenging tasks in natural language processing (NLP). Since 2014, various neural encoder-decoder models pioneered by Seq2Seq have been proposed to achieve the goal by learning to map input text to output text. However, the input text alone often provides limited knowledge to generate the desired output, so the performance of text generation is still far from satisfaction in many real-world scenarios. To address this issue, researchers have considered incorporating various forms of knowledge beyond the input text into the generation models. This research direction is known as knowledge-enhanced text generation. In this survey, we present a comprehensive review of the research on knowledge enhanced text generation over the past five years. The main content includes two parts: (i) general methods and architectures for integrating knowledge into text generation; (ii) specific techniques and applications according to different forms of knowledge data. This survey can have broad audiences, researchers and practitioners, in academia and industry.

115 citations

Posted Content
TL;DR: This article presents a systematic survey of the research on neural text style transfer, spanning over 100 representative articles since the first neuralText style transfer work in 2017, as well as the rich methodologies in the presence of parallel and non-parallel data.
Abstract: Text style transfer (TST) is an important task in natural language generation (NLG), 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 (NLP), and recently has re-gained significant attention thanks to the promising performance brought by deep neural models. In this paper, 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 TST. Our curated paper list is at this https URL

101 citations

Posted Content
TL;DR: The authors show that byte-level models are significantly more robust to noise and perform better on tasks that are sensitive to spelling and pronunciation than their token-level counterparts. But they also show that the trade-offs in terms of parameter count, training FLOPs, and inference speed are worse than those of token-based models.
Abstract: Most widely-used pre-trained language models operate on sequences of tokens corresponding to word or subword units. Encoding text as a sequence of tokens requires a tokenizer, which is typically created as an independent artifact from the model. Token-free models that instead operate directly on raw text (bytes or characters) have many benefits: they can process text in any language out of the box, they are more robust to noise, and they minimize technical debt by removing complex and error-prone text preprocessing pipelines. Since byte or character sequences are longer than token sequences, past work on token-free models has often introduced new model architectures designed to amortize the cost of operating directly on raw text. In this paper, we show that a standard Transformer architecture can be used with minimal modifications to process byte sequences. We carefully characterize the trade-offs in terms of parameter count, training FLOPs, and inference speed, and show that byte-level models are competitive with their token-level counterparts. We also demonstrate that byte-level models are significantly more robust to noise and perform better on tasks that are sensitive to spelling and pronunciation. As part of our contribution, we release a new set of pre-trained byte-level Transformer models based on the T5 architecture, as well as all code and data used in our experiments.

43 citations

Posted Content
TL;DR: Datasets as discussed by the authors is a community library for contemporary NLP designed to support the scale, variety, and quantity of publicly-available NLP datasets, as well as new tasks, larger models, and novel benchmarks.
Abstract: The scale, variety, and quantity of publicly-available NLP datasets has grown rapidly as researchers propose new tasks, larger models, and novel benchmarks. Datasets is a community library for contemporary NLP designed to support this ecosystem. Datasets aims to standardize end-user interfaces, versioning, and documentation, while providing a lightweight front-end that behaves similarly for small datasets as for internet-scale corpora. The design of the library incorporates a distributed, community-driven approach to adding datasets and documenting usage. After a year of development, the library now includes more than 650 unique datasets, has more than 250 contributors, and has helped support a variety of novel cross-dataset research projects and shared tasks. The library is available at this https URL.

28 citations

References
More filters
Proceedings ArticleDOI
11 Oct 2018
TL;DR: BERT as mentioned in this paper pre-trains deep bidirectional representations from unlabeled text by jointly conditioning on both left and right context in all layers, which can be fine-tuned with just one additional output layer to create state-of-the-art models for a wide range of tasks.
Abstract: We introduce a new language representation model called BERT, which stands for Bidirectional Encoder Representations from Transformers. Unlike recent language representation models (Peters et al., 2018a; Radford et al., 2018), BERT is designed to pre-train deep bidirectional representations from unlabeled text by jointly conditioning on both left and right context in all layers. As a result, the pre-trained BERT model can be fine-tuned with just one additional output layer to create state-of-the-art models for a wide range of tasks, such as question answering and language inference, without substantial task-specific architecture modifications. BERT is conceptually simple and empirically powerful. It obtains new state-of-the-art results on eleven natural language processing tasks, including pushing the GLUE score to 80.5 (7.7 point absolute improvement), MultiNLI accuracy to 86.7% (4.6% absolute improvement), SQuAD v1.1 question answering Test F1 to 93.2 (1.5 point absolute improvement) and SQuAD v2.0 Test F1 to 83.1 (5.1 point absolute improvement).

24,672 citations

Proceedings Article
01 Jan 2015
TL;DR: It is conjecture that the use of a fixed-length vector is a bottleneck in improving the performance of this basic encoder-decoder architecture, and it is proposed to extend this by allowing a model to automatically (soft-)search for parts of a source sentence that are relevant to predicting a target word, without having to form these parts as a hard segment explicitly.
Abstract: Neural machine translation is a recently proposed approach to machine translation. Unlike the traditional statistical machine translation, the neural machine translation aims at building a single neural network that can be jointly tuned to maximize the translation performance. The models proposed recently for neural machine translation often belong to a family of encoder-decoders and consists of an encoder that encodes a source sentence into a fixed-length vector from which a decoder generates a translation. In this paper, we conjecture that the use of a fixed-length vector is a bottleneck in improving the performance of this basic encoder-decoder architecture, and propose to extend this by allowing a model to automatically (soft-)search for parts of a source sentence that are relevant to predicting a target word, without having to form these parts as a hard segment explicitly. With this new approach, we achieve a translation performance comparable to the existing state-of-the-art phrase-based system on the task of English-to-French translation. Furthermore, qualitative analysis reveals that the (soft-)alignments found by the model agree well with our intuition.

20,027 citations

Posted Content
TL;DR: It is found that BERT was significantly undertrained, and can match or exceed the performance of every model published after it, and the best model achieves state-of-the-art results on GLUE, RACE and SQuAD.
Abstract: Language model pretraining has led to significant performance gains but careful comparison between different approaches is challenging. Training is computationally expensive, often done on private datasets of different sizes, and, as we will show, hyperparameter choices have significant impact on the final results. We present a replication study of BERT pretraining (Devlin et al., 2019) that carefully measures the impact of many key hyperparameters and training data size. We find that BERT was significantly undertrained, and can match or exceed the performance of every model published after it. Our best model achieves state-of-the-art results on GLUE, RACE and SQuAD. These results highlight the importance of previously overlooked design choices, and raise questions about the source of recently reported improvements. We release our models and code.

13,994 citations

Journal ArticleDOI
TL;DR: The theory of communication is extended to include a number of new factors, in particular the effect of noise in the channel, and the savings possible due to the statistical structure of the original message anddue to the nature of the final destination of the information.
Abstract: HE recent development of various methods of modulation such as PCM and PPM which exchange bandwidth for signal-to-noise ratio has intensified the interest in a general theory of communication. A basis for such a theory is contained in the important papers of Nyquist1 and Hartley2 on this subject. In the present paper we will extend the theory to include a number of new factors, in particular the effect of noise in the channel, and the savings possible due to the statistical structure of the original message and due to the nature of the final destination of the information. The fundamental problem of communication is that of reproducing at one point either exactly or approximately a message selected at another point. Frequently the messages have meaning; that is they refer to or are correlated according to some system with certain physical or conceptual entities. These semantic aspects of communication are irrelevant to the engineering problem. The significant aspect is that the actual message is one selected from a set of possible messages. The system must be designed to operate for each possible selection, not just the one which will actually be chosen since this is unknown at the time of design. If the number of messages in the set is finite then this number or any monotonic function of this number can be regarded as a measure of the information produced when one message is chosen from the set, all choices being equally likely. As was pointed out by Hartley the most natural choice is the logarithmic function. Although this definition must be generalized considerably when we consider the influence of the statistics of the message and when we have a continuous range of messages, we will in all cases use an essentially logarithmic measure. The logarithmic measure is more convenient for various reasons:

10,281 citations

Proceedings Article
25 Jul 2004
TL;DR: Four different RouGE measures are introduced: ROUGE-N, ROUge-L, R OUGE-W, and ROUAGE-S included in the Rouge summarization evaluation package and their evaluations.
Abstract: ROUGE stands for Recall-Oriented Understudy for Gisting Evaluation. It includes measures to automatically determine the quality of a summary by comparing it to other (ideal) summaries created by humans. The measures count the number of overlapping units such as n-gram, word sequences, and word pairs between the computer-generated summary to be evaluated and the ideal summaries created by humans. This paper introduces four different ROUGE measures: ROUGE-N, ROUGE-L, ROUGE-W, and ROUGE-S included in the ROUGE summarization evaluation package and their evaluations. Three of them have been used in the Document Understanding Conference (DUC) 2004, a large-scale summarization evaluation sponsored by NIST.

9,293 citations