COLING 2020 论文列表

The automatic generation of music comments is of great significance for increasing the popularity of music and the music platform’s activity. In human music comments, there exists high distinction and diverse perspectives for the same song. In other words, for a song, different comments stem from different musical perspectives. However, to date, this characteristic has not been considered well in research on automatic comment generation. The existing methods tend to generate common and meaningless comments. In this paper, we propose an effective multi-perspective strategy to enhance the diversity of the generated comments. The experiment results on two music comment datasets show that our proposed model can effectively generate a series of diverse music comments based on different perspectives, which outperforms state-of-the-art baselines by a substantial margin.

While recurrent models have been effective in NLP tasks, their performance on context-free languages (CFLs) has been found to be quite weak. Given that CFLs are believed to capture important phenomena such as hierarchical structure in natural languages, this discrepancy in performance calls for an explanation. We study the performance of recurrent models on Dyck-n languages, a particularly important and well-studied class of CFLs. We find that while recurrent models generalize nearly perfectly if the lengths of the training and test strings are from the same range, they perform poorly if the test strings are longer. At the same time, we observe that RNNs are expressive enough to recognize Dyck words of arbitrary lengths in finite precision if their depths are bounded. Hence, we evaluate our models on samples generated from Dyck languages with bounded depth and find that they are indeed able to generalize to much higher lengths. Since natural language datasets have nested dependencies of bounded depth, this may help explain why they perform well in modeling hierarchical dependencies in natural language data despite prior works indicating poor generalization performance on Dyck languages. We perform probing studies to support our results and provide comparisons with Transformers.

Most of the research on text simplification is limited to sentence level nowadays. In this paper, we are the first to investigate the helpfulness of document context on sentence simplification and apply it to the sequence-to-sequence model. We firstly construct a sentence simplification dataset in which the contexts for the original sentence are provided by Wikipedia corpus. The new dataset contains approximately 116K sentence pairs with context. We then propose a new model that makes full use of the context information. Our model uses neural networks to learn the different effects of the preceding sentences and the following sentences on the current sentence and applies them to the improved transformer model. Evaluated on the newly constructed dataset, our model achieves 36.52 on SARI value, which outperforms the best performing model in the baselines by 2.46 (7.22%), indicating that context indeed helps improve sentence simplification. In the ablation experiment, we show that using either the preceding sentences or the following sentences as context can significantly improve simplification.

In this work, we present a model to generate e-commerce product summaries. The consistency between the generated summary and the product attributes is an essential criterion for the ecommerce product summarization task. To enhance the consistency, first, we encode the product attribute table to guide the process of summary generation. Second, we identify the attribute words from the vocabulary, and we constrain these attribute words can be presented in the summaries only through copying from the source, i.e., the attribute words not in the source cannot be generated. We construct a Chinese e-commerce product summarization dataset, and the experimental results on this dataset demonstrate that our models significantly improve the faithfulness.

This paper presents a prototype of a chat room that detects offensive expressions in a video live streaming chat in real time. Focusing on Twitch, one of the most popular live streaming platforms, we created a dataset for the task of detecting offensive expressions. We collected 2,000 chat posts across four popular game titles with genre diversity (e.g., competitive, violent, peaceful). To make use of the similarity in offensive expressions among different social media platforms, we adopted state-of-the-art models trained on offensive expressions from Twitter for our Twitch data (i.e., transfer learning). We investigated two similarity measurements to predict the transferability, textual similarity, and game-genre similarity. Our results show that the transfer of features from social media to live streaming is effective. However, the two measurements show less correlation in the transferability prediction.

The emergence of a variety of graph-based meaning representations (MRs) has sparked an important conversation about how to adequately represent semantic structure. MRs exhibit structural differences that reflect different theoretical and design considerations, presenting challenges to uniform linguistic analysis and cross-framework semantic parsing. Here, we ask the question of which design differences between MRs are meaningful and semantically-rooted, and which are superficial. We present a methodology for normalizing discrepancies between MRs at the compositional level (Lindemann et al., 2019), finding that we can normalize the majority of divergent phenomena using linguistically-grounded rules. Our work significantly increases the match in compositional structure between MRs and improves multi-task learning (MTL) in a low-resource setting, serving as a proof of concept for future broad-scale cross-MR normalization.

Morphological inflection, like many sequence-to-sequence tasks, sees great performance from recurrent neural architectures when data is plentiful, but performance falls off sharply in lower-data settings. We investigate one aspect of neural seq2seq models that we hypothesize contributes to overfitting - teacher forcing. By creating different training and test conditions, exposure bias increases the likelihood that a system too closely models its training data. Experiments show that teacher-forced models struggle to recover when they enter unknown territory. However, a simple modification to the training algorithm to more closely mimic test conditions creates models that are better able to generalize to unseen environments.

The automatic summarization of argumentative texts has hardly been explored. This paper takes a further step in this direction, targeting news editorials, i.e., opinionated articles with a well-defined argumentation structure. With Webis-EditorialSum-2020, we present a corpus of 1330 carefully curated summaries for 266 news editorials. We evaluate these summaries based on a tailored annotation scheme, where a high-quality summary is expected to be thesis-indicative, persuasive, reasonable, concise, and self-contained. Our corpus contains at least three high-quality summaries for about 90% of the editorials, rendering it a valuable resource for the development and evaluation of summarization technology for long argumentative texts. We further report details of both, an in-depth corpus analysis, and the evaluation of two extractive summarization models.

We introduce a new set of benchmark datasets derived from ACLED data for fine-grained event classification and compare the performance of various state-of-the-art models on these datasets, including SVM based on TF-IDF character n-grams and neural context-free embeddings (GLOVE and FASTTEXT) as well as deep learning-based BERT with its contextual embeddings. The best results in terms of micro (94.3-94.9%) and macro F1 (86.0-88.9%) were obtained using BERT transformer, with simpler TF-IDF character n-gram based SVM being an interesting alternative. Further, we discuss the pros and cons of the considered benchmark models in terms of their robustness and the dependence of the classification performance on the size of training data.

We propose neural models that can normalize text by considering the similarities of word strings and sounds. We experimentally compared a model that considers the similarities of both word strings and sounds, a model that considers only the similarity of word strings or of sounds, and a model without the similarities as a baseline. Results showed that leveraging the word string similarity succeeded in dealing with misspellings and abbreviations, and taking into account the sound similarity succeeded in dealing with phonetic substitutions and emphasized characters. So that the proposed models achieved higher F1 scores than the baseline.

Deep neural networks excel at learning from labeled data and achieve state-of-the-art results on a wide array of Natural Language Processing tasks. In contrast, learning from unlabeled data, especially under domain shift, remains a challenge. Motivated by the latest advances, in this survey we review neural unsupervised domain adaptation techniques which do not require labeled target domain data. This is a more challenging yet a more widely applicable setup. We outline methods, from early traditional non-neural methods to pre-trained model transfer. We also revisit the notion of domain, and we uncover a bias in the type of Natural Language Processing tasks which received most attention. Lastly, we outline future directions, particularly the broader need for out-of-distribution generalization of future NLP.

We present a method for completing multilingual translation dictionaries. Our probabilistic approach can synthesize new word forms, allowing it to operate in settings where correct translations have not been observed in text (cf. cross-lingual embeddings). In addition, we propose an approximate Maximum Mutual Information (MMI) decoding objective to further improve performance in both many-to-one and one-to-one word level translation tasks where we use either multiple input languages for a single target language or more typical single language pair translation. The model is trained in a many-to-many setting, where it can leverage information from related languages to predict words in each of its many target languages. We focus on 6 languages: French, Spanish, Italian, Portuguese, Romanian, and Turkish. When indirect multilingual information is available, ensembling with mixture-of-experts as well as incorporating related languages leads to a 27% relative improvement in whole-word accuracy of predictions over a single-source baseline. To seed the completion when multilingual data is unavailable, it is better to decode with an MMI objective.

In this paper, we present a study on a French Spoken Language Understanding (SLU) task: the MEDIA task. Many works and studies have been proposed for many tasks, but most of them are focused on English language and tasks. The exploration of a richer language like French within the framework of a SLU task implies to recent approaches to handle this difficulty. Since the MEDIA task seems to be one of the most difficult, according several previous studies, we propose to explore Neural Networks approaches focusing of three aspects: firstly, the Neural Network inputs and more specifically the word embeddings; secondly, we compared French version of BERT against the best setup through different ways; Finally, the comparison against State-of-the-Art approaches. Results show that the word embeddings trained on a small corpus need to be updated during SLU model training. Furthermore, the French BERT fine-tuned approaches outperform the classical Neural Network Architectures and achieves state of the art results. However, the contextual embeddings extracted from one of the French BERT approaches achieve comparable results in comparison to word embedding, when integrated into the proposed neural architecture.

This paper presents a neural machine translation model and dataset for the Chibchan language Bribri, with an average performance of BLEU 16.9±1.7. This was trained on an extremely small dataset (5923 Bribri-Spanish pairs), providing evidence for the applicability of NMT in extremely low-resource environments. We discuss the challenges entailed in managing training input from languages without standard orthographies, we provide evidence of successful learning of Bribri grammar, and also examine the translations of structures that are infrequent in major Indo-European languages, such as positional verbs, ergative markers, numerical classifiers and complex demonstrative systems. In addition to this, we perform an experiment of augmenting the dataset through iterative back-translation (Sennrich et al., 2016a; Hoang et al., 2018) by using Spanish sentences to create synthetic Bribri sentences. This improves the score by an average of 1.0 BLEU, but only when the new Spanish sentences belong to the same domain as the other Spanish examples. This contributes to the small but growing body of research on Chibchan NLP.

Named entity recognition is a key component in various natural language processing systems, and neural architectures provide significant improvements over conventional approaches. Regardless of different word embedding and hidden layer structures of the networks, a conditional random field layer is commonly used for the output. This work proposes to use a neural language model as an alternative to the conditional random field layer, which is more flexible for the size of the corpus. Experimental results show that the proposed system has a significant advantage in terms of training speed, with a marginal performance degradation.

Automated essay scoring (AES) is the task of automatically assigning scores to essays as an alternative to grading by human raters. Conventional AES typically relies on handcrafted features, whereas recent studies have proposed AES models based on deep neural networks (DNNs) to obviate the need for feature engineering. Furthermore, hybrid methods that integrate handcrafted features in a DNN-AES model have been recently developed and have achieved state-of-the-art accuracy. One of the most popular hybrid methods is formulated as a DNN-AES model with an additional recurrent neural network (RNN) that processes a sequence of handcrafted sentence-level features. However, this method has the following problems: 1) It cannot incorporate effective essay-level features developed in previous AES research. 2) It greatly increases the numbers of model parameters and tuning parameters, increasing the difficulty of model training. 3) It has an additional RNN to process sentence-level features, enabling extension to various DNN-AES models complex. To resolve these problems, we propose a new hybrid method that integrates handcrafted essay-level features into a DNN-AES model. Specifically, our method concatenates handcrafted essay-level features to a distributed essay representation vector, which is obtained from an intermediate layer of a DNN-AES model. Our method is a simple DNN-AES extension, but significantly improves scoring accuracy.

A natural language interface to databases (NLIDB) enables users without technical expertise to easily access information from relational databases. Interest in NLIDBs has resurged in the past years due to the availability of large datasets and improvements to neural sequence-to-sequence models. In this survey we focus on the key design decisions behind current state of the art neural approaches, which we group into encoder and decoder improvements. We highlight the three most important directions, namely linking question tokens to database schema elements (schema linking), better architectures for encoding the textual query taking into account the schema (schema encoding), and improved generation of structured queries using autoregressive neural models (grammar-based decoders). To foster future research, we also present an overview of the most important NLIDB datasets, together with a comparison of the top performing neural models and a short insight into recent non deep learning solutions.

We propose a novel task of native-like expression identification by contrasting texts written by native speakers and those by proficient second language speakers. This task is highly challenging mainly because 1) the combinatorial nature of expressions prevents us from choosing candidate expressions a priori and 2) the distributions of the two types of texts overlap considerably. Our solution to the first problem is to combine a powerful neural network-based classifier of sentence-level nativeness with an explainability method that measures an approximate contribution of a given expression to the classifier’s prediction. To address the second problem, we introduce a special label neutral and reformulate the classification task as complementary-label learning. Our crowdsourcing-based evaluation and in-depth analysis suggest that our method successfully uncovers linguistically interesting usages distinctive of native speech.

There is a large body of work on Biomedical Entity Recognition (Bio-NER) for English but there have only been a few attempts addressing NER for Chinese biomedical texts. Because of the growing amount of Chinese biomedical discoveries being patented, and lack of NER models for patent data, we train and evaluate NER models for the analysis of Chinese biomedical patent data, based on BERT. By doing so, we show the value and potential of this domain-specific NER task. For the evaluation of our methods we built our own Chinese biomedical patents NER dataset, and our optimized model achieved an F1 score of 0.54±0.15. Further biomedical analysis indicates that our solution can help detecting meaningful biomedical entities and novel gene-gene interactions, with limited labeled data, training time and computing power.