United States

The metrics standardly used to evaluate Natural Language Generation (NLG) models, such as BLEU or METEOR, fail to provide information on which linguistic factors impact performance. Focusing on Surface Realization (SR), the task of converting an unordered dependency tree into a well-formed sentence, we propose a framework for error analysis which permits identifying which features of the input affect the models’ results. This framework consists of two main components: (i) correlation analyses between a wide range of syntactic metrics and standard performance metrics and (ii) a set of techniques to automatically identify syntactic constructs that often co-occur with low performance scores. We demonstrate the advantages of our framework by performing error analysis on the results of 174 system runs submitted to the Multilingual SR shared tasks; we show that dependency edge accuracy correlate with automatic metrics thereby providing a more interpretable basis for evaluation; and we suggest ways in which our framework could be used to improve models and data. The framework is available in the form of a toolkit which can be used both by campaign organizers to provide detailed, linguistically interpretable feedback on the state of the art in multilingual SR, and by individual researchers to improve models and datasets.

NAACL 2021

An Error Analysis Framework for Shallow Surface Realisation

2021 Annual Conference of the North American Chapter of the Association for Computational Linguistics.

**Whova App** 
Stay in touch with your fellow conference attendees via the [Whova App](https://whova.com/portal/webapp/nacon_202106/)

**Conference Structure**
https://2021.naacl.org/blog/conference-structure/

**Walkthrough video of how to NAACL 2021** 

Please take a moment to view this video explaining how to navigate the platform, attend sessions network with other attendees. 


<figure class="video_container">
  <iframe src="https://screencast-o-matic.com/watch/crhwbGVh3vx?v=6&ff=1&title=0&controls=1" width=640  height=350  frameborder="0" allowfullscreen="true"> </iframe>
</figure>

<br>
<br>

technical paper

Graph-based semantic parsing aims to represent textual meaning through directed graphs. As one of the most promising general-purpose meaning representations, these structures and their parsing have gained a significant interest momentum during recent years, with several diverse formalisms being proposed. Yet, owing to this very heterogeneity, most of the research effort has focused mainly on solutions specific to a given formalism. In this work, instead, we reframe semantic parsing towards multiple formalisms as Multilingual Neural Machine Translation (MNMT), and propose SGL, a many-to-many seq2seq architecture trained with an MNMT objective. Backed by several experiments, we show that this framework is indeed effective once the learning procedure is enhanced with large parallel corpora coming from Machine Translation: we report competitive performances on AMR and UCCA parsing, especially once paired with pre-trained architectures. Furthermore, we find that models trained under this configuration scale remarkably well to tasks such as Cross-Lingual AMR parsing: SGL outperforms all its competitors by a large margin without even explicitly seeing non-English to AMR examples at training time and, once these examples are included as well, sets an unprecedented state of the art in this task.

SGL: Speaking the Graph Languages of Semantic Parsing via Multilingual Translation

The importance of building semantic parsers which can be applied to new domains and generate programs unseen at training has long been acknowledged, and datasets testing out- of-domain performance are becoming increas- ingly available. However, little or no attention has been devoted to learning algorithms or objectives which promote domain general- ization, with virtually all existing approaches relying on standard supervised learning. In this work, we use a meta-learning framework which targets zero-shot domain generalization for semantic parsing. We apply a model- agnostic training algorithm that simulates zero- shot parsing by constructing virtual train and test sets from disjoint domains. The learning objective capitalizes on the intuition that gradient steps that improve source-domain performance should also improve target-domain per- formance, thus encouraging a parser to gen- eralize to unseen target domains. Experimental results on the (English) Spider and Chinese Spider datasets show that the meta-learning ob- jective significantly boosts the performance of a baseline parser.

Meta-Learning for Domain Generalization in Semantic Parsing

**Read the paper on the folowing link:**

https://www.aclweb.org/anthology/2021.naacl-srw.1/

**Abstract:**

0

Sampling and Filtering of Neural Machine Translation Distillation Data

In primary school, children's books, as well as in modern language learning apps, multi-modal learning strategies like illustrations of terms and phrases are used to support reading comprehension. Also, several studies in educational psychology suggest that integrating cross-modal information will improve reading comprehension. We claim that state-of-the-art multi-modal transformers, which could be used in a language learner context to improve human reading, will perform poorly because of the short and relatively simple textual data those models are trained with. To prove our hypotheses, we collected a new multi-modal image-retrieval dataset based on data from Wikipedia. In an in-depth data analysis, we highlight the differences between our dataset and other popular datasets. Additionally, we evaluate several state-of-the-art multi-modal transformers on text-image retrieval on our dataset and analyze their meager results, which verify our claims.

Towards Multi-Modal Text-Image Retrieval to improve Human Reading

Automatic Text Summarization (ATS) is the task of generating concise and fluent summaries from one or more documents. In this paper, we present IceSum, the first Icelandic corpus annotated with human-generated summaries. IceSum consists of 1,000 online news articles and their extractive summaries. We train and evaluate several neural network-based models on this dataset, comparing them against a selection of baseline methods. The best model obtains a ROUGE-2 recall score of 71.06, outperforming all baseline methods. Furthermore, we evaluate how the amount of training data affects the quality of the generated summaries. Our results show that while the corpus is sufficiently large to train a well-performing model, there could still be significant gains from increasing the size of the training set.

IceSum: An Icelandic Text Summarization Corpus

Negation is a linguistic universal that poses dif- ficulties for cognitive and computational processing. Despite many advances in text analytics, negation resolution remains an acute and continuously researched question in Natural Language Processing. Reliable negation parsing affects results in biomedical text mining, sentiment analysis, machine translation, and many other fields. The availability of multilingual pre-trained general representation models makes it possible to experiment with negation detection in languages that lack annotated data. In this work we test the performance of two state-of-the-art contextual representation models, Multilingual BERT and XLM-RoBERTa. We resolve negation scope by conducting zero-shot transfer between En- glish, Spanish, French, and Russian. Our best result amounts to a token-level F1-score of 86.86% between Spanish and Russian. We correlate these results with a linguistic negation typology and lexical capacity of the models.

Negation typology and general representation models for cross-lingual zero-shot negation scope resolution in Russian, French, and Spanish.

We propose neural models to generate text from formal meaning representations based on Discourse Representation Structures (DRSs). DRSs are document-level representations which encode rich semantic detail pertaining to rhetorical relations,

Text Generation from Discourse Representation Structures

Natural language often exhibits inherent hierarchical structure ingrained with complex syntax and semantics. However, most state-ofthe-art deep generative models learn embeddings only in Euclidean vector space, without accounting for this structural property of language. We investigate text generation in a hyperbolic latent space to learn continuous hierarchical representations. An Adversarial Poincaré Variational Autoencoder (APo-VAE) is presented, where both the prior and variational posterior of latent variables are defined over a Poincaré ball via wrapped normal distributions. By adopting the primal-dual formulation of Kullback-Leibler divergence, an adversarial learning procedure is introduced to empower robust model training. Extensive experiments in language modeling, unaligned style transfer, and dialog-response generation demonstrate the effectiveness of the proposed APo-VAE model over VAEs in Euclidean latent space, thanks to its superb capabilities in capturing latent language hierarchies in hyperbolic space.

APo-VAE: Text Generation in Hyperbolic Space

We rely on arguments in our daily lives to deliver our opinions and base them on evidence, making them more convincing in turn. However, finding and formulating arguments can be challenging. In this work, we present the Arg-CTRL - a language model for argument generation that can be controlled to generate sentence-level arguments for a given topic, stance, and aspect. We define argument aspect detection as a necessary method to allow this fine-granular control and crowdsource a dataset with 5,032 arguments annotated with aspects. Our evaluation shows that the Arg-CTRL is able to generate high-quality, aspect-specific arguments, applicable to automatic counter-argument generation. We publish the model weights and all datasets and code to train the Arg-CTRL.

Aspect-Controlled Neural Argument Generation

We present DART, an open domain structured DAta Record to Text generation dataset with over 82k instances (DARTs). Data-to-Text annotations can be a costly process, especially when dealing with tables which are the major source of structured data and contain nontrivial structures. To this end, we propose a procedure of extracting semantic triples from tables that encodes their structures by exploiting the semantic dependencies among table headers and the table title. Our dataset construction framework effectively merged heterogeneous sources from open domain semantic parsing and dialogue-act-based meaning representation tasks by utilizing techniques such as: tree ontology annotation, question-answer pair to declarative sentence conversion, and predicate unification, all with minimum post-editing. We present systematic evaluation on DART as well as new state-of-the-art results on WebNLG 2017 to show that DART (1) poses new challenges to existing data-to-text datasets and (2) facilitates out-of-domain generalization.

An Error Analysis Framework for Shallow Surface Realisation

Downloads

Next from NAACL 2021

SGL: Speaking the Graph Languages of Semantic Parsing via Multilingual Translation

Similar lecture

Word Complexity is in the Eye of the Beholder

An Error Analysis Framework for Shallow Surface Realisation

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from NAACL 2021

SGL: Speaking the Graph Languages of Semantic Parsing via Multilingual Translation

Similar lecture

Word Complexity is in the Eye of the Beholder

Downloads