The correct use of Dutch pronouns 'die' and 'dat' is a stumbling block for both native and non-native speakers of Dutch due to the multiplicity of syntactic functions and the dependency on the antecedent's gender and number. Drawing on previous research conducted on neural context-dependent dt-mistake correction models (Heyman et al. 2018), this study constructs the first neural network model for Dutch demonstrative and relative pronoun resolution that specifically focuses on the correction and part-of-speech prediction of these two pronouns. Two separate datasets are built with sentences obtained from, respectively, the Dutch Europarl corpus (Koehn 2015) - which contains the proceedings of the European Parliament from 1996 to the present - and the SoNaR corpus (Oostdijk et al. 2013) - which contains Dutch texts from a variety of domains such as newspapers, blogs and legal texts. Firstly, a binary classification model solely predicts the correct 'die' or 'dat'. The classifier with a bidirectional long short-term memory architecture achieves 84.56% accuracy. Secondly, a multitask classification model simultaneously predicts the correct 'die' or 'dat' and its part-of-speech tag. The model containing a combination of a sentence and context encoder with both a bidirectional long short-term memory architecture results in 88.63% accuracy for die/dat prediction and 87.73% accuracy for part-of-speech prediction. More evenly-balanced data, larger word embeddings, an extra bidirectional long short-term memory layer and integrated part-of-speech knowledge positively affects die/dat prediction performance, while a context encoder architecture raises part-of-speech prediction performance. This study shows promising results and can serve as a starting point for future research on machine learning models for Dutch anaphora resolution.
Anaphora resolution (coreference) systems designed for the CONLL 2012 dataset typically cannot handle key aspects of the full anaphora resolution task such as the identification of singletons and of certain types of non-referring expressions (e.g., expletives), as these aspects are not annotated in that corpus. However, the recently released dataset for the CRAC 2018 Shared Task can now be used for that purpose. In this paper, we introduce an architecture to simultaneously identify non-referring expressions (including expletives, predicative s, and other types) and build coreference chains, in…
Resolving abstract anaphora is an important, but difficult task for text understanding. Yet, with recent advances in representation learning this task becomes a more tangible aim. A central property of abstract anaphora is that it establishes a relation between the anaphor embedded in the anaphoric sentence and its (typically non-nominal) antecedent. We propose a mention-ranking model that learns how abstract anaphors relate to their antecedents with an LSTM-Siamese Net. We overcome the lack of training data by generating artificial anaphoric sentence--antecedent pairs. Our model outperforms s…
We present a new Dutch news dataset with labeled partisanship. The dataset contains more than 100K articles that are labeled on the publisher level and 776 articles that were crowdsourced using an internal survey platform and labeled on the article level. In this paper, we document our original motivation, the collection and annotation process, limitations, and applications.
Recent research in Natural Language Processing has revealed that word embeddings can encode social biases present in the training data which can affect minorities in real world applications. This paper explores the gender bias implicit in Dutch embeddings while investigating whether English language based approaches can also be used in Dutch. We implement the Word Embeddings Association Test (WEAT), Clustering and Sentence Embeddings Association Test (SEAT) methods to quantify the gender bias in Dutch word embeddings, then we proceed to reduce the bias with Hard-Debias and Sent-Debias mitigati…
Nedap Healthcare（内达普医疗）；University of Twente（特文特大学）；Radboud University（拉德堡德大学）
Unstructured information in electronic health records provide an invaluable resource for medical research. To protect the confidentiality of patients and to conform to privacy regulations, de-identification methods automatically remove personally identifying information from these medical records. However, due to the unavailability of labeled data, most existing research is constrained to English medical text and little is known about the generalizability of de-identification methods across languages and domains. In this study, we construct a varied dataset consisting of the medical records of…
We present ÆTHEL, a semantic compositionality dataset for written Dutch. ÆTHEL consists of two parts. First, it contains a lexicon of supertags for about 900 000 words in context. The supertags correspond to types of the simply typed linear lambda-calculus, enhanced with dependency decorations that capture grammatical roles supplementary to function-argument structures. On the basis of these types, ÆTHEL further provides 72 192 validated derivations, presented in four formats: natural-deduction and sequent-style proofs, linear logic proofnets and the associated programs (lambda terms) for mean…
We evaluated the effectiveness of using language models, that were pre-trained in one domain, as the basis for a classification model in another domain: Dutch book reviews. Pre-trained language models have opened up new possibilities for classification tasks with limited labelled data, because representation can be learned in an unsupervised fashion. In our experiments we have studied the effects of training set size (100-1600 items) on the prediction accuracy of a ULMFiT classifier, based on a language models that we pre-trained on the Dutch Wikipedia. We also compared ULMFiT to Support Vecto…
Word embeddings have recently seen a strong increase in interest as a result of strong performance gains on a variety of tasks. However, most of this research also underlined the importance of benchmark datasets, and the difficulty of constructing these for a variety of language-specific tasks. Still, many of the datasets used in these tasks could prove to be fruitful linguistic resources, allowing for unique observations into language use and variability. In this paper we demonstrate the performance of multiple types of embeddings, created with both count and prediction-based architectures on…
KU Leuven（鲁汶大学）；TU Berlin（柏林工业大学）；Weizenbaum Institute（魏岑鲍姆研究所）
Large transformer-based language models, e.g. BERT and GPT-3, outperform previous architectures on most natural language processing tasks. Such language models are first pre-trained on gigantic corpora of text and later used as base-model for finetuning on a particular task. Since the pre-training step is usually not repeated, base models are not up-to-date with the latest information. In this paper, we update RobBERT, a RoBERTa-based state-of-the-art Dutch language model, which was trained in 2019. First, the tokenizer of RobBERT is updated to include new high-frequent tokens present in the l…
Queen Mary University of London（伦敦玛丽女王大学）；UKP Lab, Technische Universität Darmstadt（达姆施塔特工业大学UKP实验室）
The state-of-the-art on basic, single-antecedent anaphora has greatly improved in recent years. Researchers have therefore started to pay more attention to more complex cases of anaphora such as split-antecedent anaphora, as in Time-Warner is considering a legal challenge to Telecommunications Inc's plan to buy half of Showtime Networks Inc-a move that could lead to all-out war between the two powerful companies. Split-antecedent anaphora is rarer and more complex to resolve than single-antecedent anaphora; as a result, it is not annotated in many datasets designed to test coreference, and pre…
Most previous studies on bridging anaphora resolution (Poesio et al., 2004; Hou et al., 2013b; Hou, 2018a) use the pairwise model to tackle the problem and assume that the gold mention information is given. In this paper, we cast bridging anaphora resolution as question answering based on context. This allows us to find the antecedent for a given anaphor without knowing any gold mention information (except the anaphor itself). We present a question answering framework (BARQA) for this task, which leverages the power of transfer learning. Furthermore, we propose a novel method to generate a lar…
One critical issue of zero anaphora resolution (ZAR) is the scarcity of labeled data. This study explores how effectively this problem can be alleviated by data augmentation. We adopt a state-of-the-art data augmentation method, called the contextual data augmentation (CDA), that generates labeled training instances using a pretrained language model. The CDA has been reported to work well for several other natural language processing tasks, including text classification and machine translation. This study addresses two underexplored issues on CDA, that is, how to reduce the computational cost …
VIT University（韦洛尔理工大学）；Nanyang Technological University（南洋理工大学）
Entity resolution aims at resolving repeated references to an entity in a document and forms a core component of natural language processing (NLP) research. This field possesses immense potential to improve the performance of other NLP fields like machine translation, sentiment analysis, paraphrase detection, summarization, etc. The area of entity resolution in NLP has seen proliferation of research in two separate sub-areas namely: anaphora resolution and coreference resolution. Through this review article, we aim at clarifying the scope of these two tasks in entity resolution. We also carry …
Yandex；University of Amsterdam（阿姆斯特丹大学）；University of Edinburgh（爱丁堡大学）；University of Zurich（苏黎世大学）
Standard machine translation systems process sentences in isolation and hence ignore extra-sentential information, even though extended context can both prevent mistakes in ambiguous cases and improve translation coherence. We introduce a context-aware neural machine translation model designed in such way that the flow of information from the extended context to the translation model can be controlled and analyzed. We experiment with an English-Russian subtitles dataset, and observe that much of what is captured by our model deals with improving pronoun translation. We measure correspondences …
The University of Melbourne（墨尔本大学）；Facebook AI Research（脸书人工智能研究院）；University of Washington（华盛顿大学）
We present a new architecture for storing and accessing entity mentions during online text processing. While reading the text, entity references are identified, and may be stored by either updating or overwriting a cell in a fixed-length memory. The update operation implies coreference with the other mentions that are stored in the same cell; the overwrite operation causes these mentions to be forgotten. By encoding the memory operations as differentiable gates, it is possible to train the model end-to-end, using both a supervised anaphora resolution objective as well as a supplementary langua…
School of Interactive Computing（交互计算学院）；Georgia Institute of Technology（佐治亚理工学院）
Anaphora resolution is an important task for information extraction across a range of languages, text genres, and domains, motivating the need for methods that do not require large annotated datasets. In-context learning has emerged as a promising approach, yet there are a number of challenges in applying in-context learning to resolve anaphora. For example, encoding a single in-context demonstration that consists of: an anaphor, a paragraph-length context, and a list of corresponding antecedents, requires conditioning a language model on a long sequence of tokens, limiting the number of demon…
Nanyang Technological University（南洋理工大学）；Salesforce Research Asia（赛富时亚洲研究院）；Sofia University（索非亚大学）；Qatar Computing Research Institute（卡塔尔计算研究所）
The ongoing neural revolution in machine translation has made it easier to model larger contexts beyond the sentence-level, which can potentially help resolve some discourse-level ambiguities such as pronominal anaphora, thus enabling better translations. Unfortunately, even when the resulting improvements are seen as substantial by humans, they remain virtually unnoticed by traditional automatic evaluation measures like BLEU, as only a few words end up being affected. Thus, specialized evaluation measures are needed. With this aim in mind, we contribute an extensive, targeted dataset that can…
We evaluate a rule-based (Lee et al., 2013) and neural (Lee et al., 2018) coreference system on Dutch datasets of two domains: literary novels and news/Wikipedia text. The results provide insight into the relative strengths of data-driven and knowledge-driven systems, as well as the influence of domain, document length, and annotation schemes. The neural system performs best on news/Wikipedia text, while the rule-based system performs best on literature. The neural system shows weaknesses with limited training data and long documents, while the rule-based system is affected by annotation diffe…
Most previous studies on information status (IS) classification and bridging anaphora recognition assume that the gold mention or syntactic tree information is given (Hou et al., 2013; Roesiger et al., 2018; Hou, 2020; Yu and Poesio, 2020). In this paper, we propose an end-to-end neural approach for information status classification. Our approach consists of a mention extraction component and an information status assignment component. During the inference time, our system takes a raw text as the input and generates mentions together with their information status. On the ISNotes corpus (Marker…
McGill University（麦吉尔大学）；Microsoft Research Montreal（微软研究院蒙特利尔分院）
We introduce a new benchmark for coreference resolution and NLI, Knowref, that targets common-sense understanding and world knowledge. Previous coreference resolution tasks can largely be solved by exploiting the number and gender of the antecedents, or have been handcrafted and do not reflect the diversity of naturally occurring text. We present a corpus of over 8,000 annotated text passages with ambiguous pronominal anaphora. These instances are both challenging and realistic. We show that various coreference systems, whether rule-based, feature-rich, or neural, perform significantly worse o…
Radboud University（拉德堡德大学）；National University of Singapore（新加坡国立大学）
In this paper, we describe several techniques for improving the acoustic and language model of an automatic speech recognition (ASR) system operating on code-switching (CS) speech. We focus on the recognition of Frisian-Dutch radio broadcasts where one of the mixed languages, namely Frisian, is an under-resourced language. In previous work, we have proposed several automatic transcription strategies for CS speech to increase the amount of available training speech data. In this work, we explore how the acoustic modeling (AM) can benefit from monolingual speech data belonging to the high-resour…
In Flanders, all TV shows are subtitled. However, the process of subtitling is a very time-consuming one and can be sped up by providing the output of a speech recognizer run on the audio of the TV show, prior to the subtitling. Naturally, this speech recognition will perform much better if the employed language model is adapted to the register and the topic of the program. We present several language models trained on subtitles of television shows provided by the Flemish public-service broadcaster VRT. This data was gathered in the context of the project STON which has as purpose to facilitat…
Centering, Anaphora Resolution, and Discourse Structure
居中被表述为注意状态、指称表达形式和话语段内话语连贯性之间关系的模型（Grosz，Joshi and Weinstein，1986; Grosz，Joshi and Weinstein，1995）。在本章中，我认为，中心化的限制，在一个语篇段内运作，以整合中心化与全球话语结构的模式应该放弃。段内限制导致三个问题。第一个问题是，中心往往是连续的话语段边界与代词所指的表达，其形式是相同的，发生在一个话语段。第二个问题是，最近的工作表明，听众感知段边界在不同的粒度级别。第三个问题是，即使对于话语片段内的话语，在片段内的相邻话语是分层最近的话语与片段内的相邻话语是线性最近的话语之间也存在强烈的对比。本章认为，这些问题可以通过用一个替代模型（缓存模型）取代Grosz和Sidner的注意状态堆栈模型来消除。我展示了如何缓存模型很容易集成的中心算法，并提供了几种类型的数据，从自然发生的话语，支持建议的集成模型。未来的工作应该提供额外的支持，这些索赔与一个更大的语料库的自然发生的话语检查。
Instituut voor de Nederlandse Taal（荷兰语言研究所）；KU Leuven（鲁汶大学）；Hochschule für Technik und Wirtschaft（德累斯顿工程与经济应用科学大学）
When applying automated speech recognition (ASR) for Belgian Dutch (Van Dyck et al. 2021), the output consists of an unsegmented stream of words, without any punctuation. A next step is to perform segmentation and insert punctuation, making the ASR output more readable and easy to manually correct. As far as we know there is no publicly available punctuation insertion system for Dutch that functions at a usable level. The model we present here is an extension of the models of Guhr et al. (2021) for Dutch and is made publicly available. We trained a sequence classification model, based on the D…
We present an effective system adapted from the end-to-end neural coreference resolution model, targeting on the task of anaphora resolution in dialogues. Three aspects are specifically addressed in our approach, including the support of singletons, encoding speakers and turns throughout dialogue interactions, and knowledge transfer utilizing existing resources. Despite the simplicity of our adaptation strategies, they are shown to bring significant impact to the final performance, with up to 27 F1 improvement over the baseline. Our final system ranks the 1st place on the leaderboard of the an…
We use the Lambek Calculus with soft sub-exponential modalities to model and reason about discourse relations such as anaphora and ellipsis. A semantics for this logic is obtained by using truncated Fock spaces, developed in our previous work. We depict these semantic computations via a new string diagram. The Fock Space semantics has the advantage that its terms are learnable from large corpora of data using machine learning and they can be experimented with on mainstream natural language tasks. Further, and thanks to an existing translation from vector spaces to quantum circuits, we can also…
Facebook AI Research（Facebook AI研究院）；Université de Paris（巴黎大学）；CoML, ENS/CNRS/EHESS/INRIA/PSL University（计算语言学实验室，巴黎高等师范学院/法国国家科学研究中心/法国社会科学高等研究院/法国国家信息与自动化研究所/巴黎文理研究大学）；CRI, Département Frontières du Vivant et de l’Apprendre, IIFR, Université de Paris（认知研究所，生命与学习前沿系，法国医学研究院，巴黎大学）；École normale supérieure, PSL University, CNRS（巴黎高等师范学院，巴黎文理研究大学，法国国家科学研究中心）
Our ability to comprehend speech remains, to date, unrivaled by deep learning models. This feat could result from the brain's ability to fine-tune generic sound representations for speech-specific processes. To test this hypothesis, we compare i) five types of deep neural networks to ii) human brain responses elicited by spoken sentences and recorded in 102 Dutch subjects using functional Magnetic Resonance Imaging (fMRI). Each network was either trained on an acoustics scene classification, a speech-to-text task (based on Bengali, English, or Dutch), or not trained. The similarity between eac…
