The effectiveness of a language model is influenced by its token representations, which must encode contextual information and handle the same word form having a plurality of meanings (polysemy). Currently, none of the common language modelling architectures explicitly model polysemy. We propose a language model which not only predicts the next word, but also its sense in context. We argue that this higher prediction granularity may be useful for end tasks such as assistive writing, and allow for more a precise linking of language models with knowledge bases. We find that multi-sense language modelling requires architectures that go beyond standard language models, and here propose a structured prediction framework that decomposes the task into a word followed by a sense prediction task. To aid sense prediction, we utilise a Graph Attention Network, which encodes definitions and example uses of word senses. Overall, we find that multi-sense language modelling is a highly challenging task, and suggest that future work focus on the creation of more annotated training datasets.
LIAAD - INESC TEC（LIAAD——INESC TEC（葡萄牙系统与计算机工程研究所技术与科学中心））；Faculty of Sciences - University of Porto（波尔图大学理学院）
Contextual embeddings represent a new generation of semantic representations learned from Neural Language Modelling (NLM) that addresses the issue of meaning conflation hampering traditional word embeddings. In this work, we show that contextual embeddings can be used to achieve unprecedented gains in Word Sense Disambiguation (WSD) tasks. Our approach focuses on creating sense-level embeddings with full-coverage of WordNet, and without recourse to explicit knowledge of sense distributions or task-specific modelling. As a result, a simple Nearest Neighbors (k-NN) method using our representatio…
University of Amsterdam（阿姆斯特丹大学）；University of Bristol（布里斯托尔大学）；ILLC, University of Amsterdam（阿姆斯特丹大学语言、逻辑与计算研究所(ILLC)）
Words can have multiple senses. Compositional distributional models of meaning have been argued to deal well with finer shades of meaning variation known as polysemy, but are not so well equipped to handle word senses that are etymologically unrelated, or homonymy. Moving from vectors to density matrices allows us to encode a probability distribution over different senses of a word, and can also be accommodated within a compositional distributional model of meaning. In this paper we present three new neural models for learning density matrices from a corpus, and test their ability to discrimin…
This paper proposes a message-passing mechanism to address language modelling. A new layer type is introduced that aims to substitute self-attention for unidirectional sequence generation tasks. The system is shown to be competitive with existing methods: Given N tokens, the computational complexity is O(N logN) and the memory complexity is O(N) under reasonable assumptions. In the end, the Dispatcher layer is seen to achieve comparable perplexity to prior results while being more efficient.
Subwords have become the standard units of text in NLP, enabling efficient open-vocabulary models. With algorithms like byte-pair encoding (BPE), subword segmentation is viewed as a preprocessing step applied to the corpus before training. This can lead to sub-optimal segmentations for low-resource languages with complex morphologies. We propose a subword segmental language model (SSLM) that learns how to segment words while being trained for autoregressive language modelling. By unifying subword segmentation and language modelling, our model learns subwords that optimise LM performance. We tr…
Language models are the foundation of current neural network-based models for natural language understanding and generation. However, research on the intrinsic performance of language models on African languages has been extremely limited, which is made more challenging by the lack of large or standardised training and evaluation sets that exist for English and other high-resource languages. In this paper, we evaluate the performance of open-vocabulary language models on low-resource South African languages, using byte-pair encoding to handle the rich morphology of these languages. We evaluate…
Neural language models do not scale well when the vocabulary is large. Noise-contrastive estimation (NCE) is a sampling-based method that allows for fast learning with large vocabularies. Although NCE has shown promising performance in neural machine translation, it was considered to be an unsuccessful approach for language modelling. A sufficient investigation of the hyperparameters in the NCE-based neural language models was also missing. In this paper, we showed that NCE can be a successful approach in neural language modelling when the hyperparameters of a neural network are tuned appropri…
Word Sense Disambiguation (WSD), the process of automatically identifying the meaning of a polysemous word in a sentence, is a fundamental task in Natural Language Processing (NLP). Progress in this approach to WSD opens up many promising developments in the field of NLP and its applications. Indeed, improvement over current performance levels could allow us to take a first step towards natural language understanding. Due to the lack of lexical resources it is sometimes difficult to perform WSD for under-resourced languages. This paper is an investigation on how to initiate research in WSD for…
University of Edinburgh（爱丁堡大学）；Pontificia Universidad Católica del Perú（秘鲁天主教大学）
Language modelling is regularly analysed at word, subword or character units, but syllables are seldom used. Syllables provide shorter sequences than characters, they can be extracted with rules, and their segmentation typically requires less specialised effort than identifying morphemes. We reconsider syllables for an open-vocabulary generation task in 20 languages. We use rule-based syllabification methods for five languages and address the rest with a hyphenation tool, which behaviour as syllable proxy is validated. With a comparable perplexity, we show that syllables outperform characters,…
HiTZ Basque Center for Language Technologies（HiTZ巴斯克语言技术中心）；University of the Basque Country UPV/EHU（巴斯克大学（UPV/EHU））
Language Models are the core for almost any Natural Language Processing system nowadays. One of their particularities is their contextualized representations, a game changer feature when a disambiguation between word senses is necessary. In this paper we aim to explore to what extent language models are capable of discerning among senses at inference time. We performed this analysis by prompting commonly used Languages Models such as BERT or RoBERTa to perform the task of Word Sense Disambiguation (WSD). We leverage the relation between word senses and domains, and cast WSD as a textual entail…
University of Edinburgh（爱丁堡大学）；Pontificia Universidad Católica del Perú（秘鲁天主教教皇大学）
Language modelling and machine translation tasks mostly use subword or character inputs, but syllables are seldom used. Syllables provide shorter sequences than characters, require less-specialised extracting rules than morphemes, and their segmentation is not impacted by the corpus size. In this study, we first explore the potential of syllables for open-vocabulary language modelling in 21 languages. We use rule-based syllabification methods for six languages and address the rest with hyphenation, which works as a syllabification proxy. With a comparable perplexity, we show that syllables out…
Formal language techniques have been used in the past to study autonomous dynamical systems. However, for controlled systems, new features are needed to distinguish between information generated by the system and input control. We show how the modelling framework for controlled dynamical systems leads naturally to a formulation in terms of context-dependent grammars. A learning algorithm is proposed for on-line generation of the grammar productions, this formulation being then used for modelling, control and anomaly detection. Practical applications are described for electromechanical drives. …
Automatic speech recognition and spoken dialogue systems have made great advances through the use of deep machine learning methods. This is partly due to greater computing power but also through the large amount of data available in common languages, such as English. Conversely, research in minority languages, including sign languages, is hampered by the severe lack of data. This has led to work on transfer learning methods, whereby a model developed for one language is reused as the starting point for a model on a second language, which is less resourced. In this paper, we examine two transfe…
We present the ongoing NorLM initiative to support the creation and use of very large contextualised language models for Norwegian (and in principle other Nordic languages), including a ready-to-use software environment, as well as an experience report for data preparation and training. This paper introduces the first large-scale monolingual language models for Norwegian, based on both the ELMo and BERT frameworks. In addition to detailing the training process, we present contrastive benchmark results on a suite of NLP tasks for Norwegian. For additional background and access to the data, mode…
Center for Data Science（数据科学中心）；New York University（纽约大学）；Courant Institute of Mathematical Sciences（库朗数学科学研究所）
In this work, we propose a novel method to incorporate corpus-level discourse information into language modelling. We call this larger-context language model. We introduce a late fusion approach to a recurrent language model based on long short-term memory units (LSTM), which helps the LSTM unit keep intra-sentence dependencies and inter-sentence dependencies separate from each other. Through the evaluation on three corpora (IMDB, BBC, and PennTree Bank), we demon- strate that the proposed model improves perplexity significantly. In the experi- ments, we evaluate the proposed approach while va…
This paper presents a scalable method for integrating compositional morphological representations into a vector-based probabilistic language model. Our approach is evaluated in the context of log-bilinear language models, rendered suitably efficient for implementation inside a machine translation decoder by factoring the vocabulary. We perform both intrinsic and extrinsic evaluations, presenting results on a range of languages which demonstrate that our model learns morphological representations that both perform well on word similarity tasks and lead to substantial reductions in perplexity. W…
As a key natural language processing (NLP) task, word sense disambiguation (WSD) evaluates how well NLP models can understand the lexical semantics of words under specific contexts. Benefited from the large-scale annotation, current WSD systems have achieved impressive performances in English by combining supervised learning with lexical knowledge. However, such success is hard to be replicated in other languages, where we only have limited annotations.In this paper, based on the multilingual lexicon BabelNet describing the same set of concepts across languages, we propose building knowledge a…
The Hebrew University of Jerusalem（耶路撒冷希伯来大学）；IBM Research（IBM研究院）
We present models which complete missing text given transliterations of ancient Mesopotamian documents, originally written on cuneiform clay tablets (2500 BCE - 100 CE). Due to the tablets' deterioration, scholars often rely on contextual cues to manually fill in missing parts in the text in a subjective and time-consuming process. We identify that this challenge can be formulated as a masked language modelling task, used mostly as a pretraining objective for contextualized language models. Following, we develop several architectures focusing on the Akkadian language, the lingua franca of the …
École de Technologie Supérieure（高等技术学院）；Johns Hopkins University（约翰斯·霍普金斯大学）；Amazon（亚马逊）；Facebook（脸书）；Google（谷歌）；Microsoft（微软）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；National Research University Higher School of Economics (HSE University)（国立研究型大学高等经济学院（HSE大学））；Indiana University Bloomington（印第安纳大学伯明顿分校）；Carnegie Mellon University（卡内基梅隆大学）
Research in natural language processing commonly assumes that approaches that work well for English and and other widely-used languages are "language agnostic". In high-resource languages, especially those that are analytic, a common approach is to treat morphologically-distinct variants of a common root as completely independent word types. This assumes, that there are limited morphological inflections per root, and that the majority will appear in a large enough corpus, so that the model can adequately learn statistics about each form. Approaches like stemming, lemmatization, or subword segm…
With the further development of informatization, more and more data is stored in the form of text. There are some loss of text during their generation and transmission. The paper aims to establish a language model based on the large-scale corpus to complete the restoration of missing text. In this paper, we introduce a novel measurement to find the missing words, and a way of establishing a comprehensive candidate lexicon to insert the correct choice of words. The paper also introduces some effective optimization methods, which largely improve the efficiency of the text restoration and shorten…
In this paper, we describe an approach for modelling causal reasoning in natural language by detecting counterfactuals in text using multi-head self-attention weights. We use pre-trained transformer models to extract contextual embeddings and self-attention weights from the text. We show the use of convolutional layers to extract task-specific features from these self-attention weights. Further, we describe a fine-tuning approach with a common base model for knowledge sharing between the two closely related sub-tasks for counterfactual detection. We analyze and compare the performance of vario…
In Natural Language Processing (NLP), one traditionally considers a single task (e.g. part-of-speech tagging) for a single language (e.g. English) at a time. However, recent work has shown that it can be beneficial to take advantage of relatedness between tasks, as well as between languages. In this work I examine the concept of relatedness and explore how it can be utilised to build NLP models that require less manually annotated data. A large selection of NLP tasks is investigated for a substantial language sample comprising 60 languages. The results show potential for joint multitask and mu…
University of Oxford（牛津大学）；Massachusetts Institute of Technology（麻省理工学院）；Delft University of Technology（代尔夫特理工大学）
The design of complex engineering systems is an often long and articulated process that highly relies on engineers' expertise and professional judgment. As such, the typical pitfalls of activities involving the human factor often manifest themselves in terms of lack of completeness or exhaustiveness of the analysis, inconsistencies across design choices or documentation, as well as an implicit degree of subjectivity. An approach is proposed to assist systems engineers in the automatic generation of systems diagrams from unstructured natural language text. Natural Language Processing (NLP) tech…
This thesis investigates how the sub-structure of words can be accounted for in probabilistic models of language. Such models play an important role in natural language processing tasks such as translation or speech recognition, but often rely on the simplistic assumption that words are opaque symbols. This assumption does not fit morphologically complex language well, where words can have rich internal structure and sub-word elements are shared across distinct word forms. Our approach is to encode basic notions of morphology into the assumptions of three different types of language models, wi…
Contextual word representation models have shown massive improvements on a multitude of NLP tasks, yet their word sense disambiguation capabilities remain poorly explained. To address this gap, we assess whether contextual word representations extracted from deep pretrained language models create distinguishable representations for different senses of a given word. We analyze the representation geometry and find that most layers of deep pretrained language models create highly anisotropic representations, pointing towards the existence of representation degeneration problem in contextual word …
University of Oxford（牛津大学）；Google DeepMind（谷歌DeepMind）
This paper presents an in-depth investigation on integrating neural language models in translation systems. Scaling neural language models is a difficult task, but crucial for real-world applications. This paper evaluates the impact on end-to-end MT quality of both new and existing scaling techniques. We show when explicitly normalising neural models is necessary and what optimisation tricks one should use in such scenarios. We also focus on scalable training algorithms and investigate noise contrastive estimation and diagonal contexts as sources for further speed improvements. We explore the …
Learning a distinct representation for each sense of an ambiguous word could lead to more powerful and fine-grained models of vector-space representations. Yet while `multi-sense' methods have been proposed and tested on artificial word-similarity tasks, we don't know if they improve real natural language understanding tasks. In this paper we introduce a multi-sense embedding model based on Chinese Restaurant Processes that achieves state of the art performance on matching human word similarity judgments, and propose a pipelined architecture for incorporating multi-sense embeddings into langua…
A word having multiple senses in a text introduces the lexical semantic task to find out which particular sense is appropriate for the given context. One such task is Word sense disambiguation which refers to the identification of the most appropriate meaning of the polysemous word in a given context using computational algorithms. The language processing research in Hindi, the official language of India, and other Indian languages is restricted by unavailability of the standard corpus. For Hindi word sense disambiguation also, the large corpus is not available. In this work, we prepared the t…
Human beings possess the most sophisticated computational machinery in the known universe. We can understand language of rich descriptive power, and communicate in the same environment with astonishing clarity. Two of the many contributors to the interest in natural language - the properties of Compositionality and Structure Dependence, are well documented, and offer a vast space to ask interesting modelling questions. The first step to begin answering these questions is to ground verbal theory in formal terms. Drawing on linguistics and set theory, a formalisation of these ideas is presented …
Faculty of Information Technology, Monash University（莫纳什大学信息技术学院）；Computing and Information Systems, The University of Melbourne（墨尔本大学计算与信息系统系）
Efficient methods for storing and querying are critical for scaling high-order n-gram language models to large corpora. We propose a language model based on compressed suffix trees, a representation that is highly compact and can be easily held in memory, while supporting queries needed in computing language model probabilities on-the-fly. We present several optimisations which improve query runtimes up to 2500x, despite only incurring a modest increase in construction time and memory usage. For large corpora and high Markov orders, our method is highly competitive with the state-of-the-art Ke…
We present a generative model for multitask conditional language generation. Our guiding hypothesis is that a shared set of latent skills underlies many disparate language generation tasks, and that explicitly modelling these skills in a task embedding space can help with both positive transfer across tasks and with efficient adaptation to new tasks. We instantiate this task embedding space as a latent variable in a latent variable sequence-to-sequence model. We evaluate this hypothesis by curating a series of monolingual text-to-text language generation datasets - covering a broad range of ta…
Disambiguation of word senses in context is easy for humans, but is a major challenge for automatic approaches. Sophisticated supervised and knowledge-based models were developed to solve this task. However, (i) the inherent Zipfian distribution of supervised training instances for a given word and/or (ii) the quality of linguistic knowledge representations motivate the development of completely unsupervised and knowledge-free approaches to word sense disambiguation (WSD). They are particularly useful for under-resourced languages which do not have any resources for building either supervised …
Korea Advanced Institute of Science and Technology（韩国科学技术院）；Ulsan National Institute of Science and Technology（蔚山国立科学技术院）
Currently, contextualized word representations are learned by intricate neural network models, such as masked neural language models (MNLMs). The new representations significantly enhanced the performance in automated question answering by reading paragraphs. However, identifying the detailed knowledge trained in the MNLMs is difficult owing to numerous and intermingled parameters. This paper provides empirical but insightful analyses on the pretrained MNLMs with respect to common sense knowledge. First, we propose a test that measures what types of common sense knowledge do pretrained MNLMs u…
We present a completed, publicly available corpus of annotated semantic relations of adpositions and case markers in Hindi. We used the multilingual SNACS annotation scheme, which has been applied to a variety of typologically diverse languages. Building on past work examining linguistic problems in SNACS annotation, we use language models to attempt automatic labelling of SNACS supersenses in Hindi and achieve results competitive with past work on English. We look towards upstream applications in semantic role labelling and extension to related languages such as Gujarati.
A simple machine learning model of pluralisation as a linear regression problem minimising a p-adic metric substantially outperforms even the most robust of Euclidean-space regressors on languages in the Indo-European, Austronesian, Trans New-Guinea, Sino-Tibetan, Nilo-Saharan, Oto-Meanguean and Atlantic-Congo language families. There is insufficient evidence to support modelling distinct noun declensions as a p-adic neighbourhood even in Indo-European languages.
We release to the community six large-scale sense-annotated datasets in multiple language to pave the way for supervised multilingual Word Sense Disambiguation. Our datasets cover all the nouns in the English WordNet and their translations in other languages for a total of millions of sense-tagged sentences. Experiments prove that these corpora can be effectively used as training sets for supervised WSD systems, surpassing the state of the art for low-resourced languages and providing competitive results for English, where manually annotated training sets are accessible. The data is available …
Indian Institute of Technology Bombay（印度理工学院孟买分校）；IBM India Research Lab（IBM印度研究实验室）
Natural language processing (NLP) tasks (e.g. question-answering in English) benefit from knowledge of other tasks (e.g. named entity recognition in English) and knowledge of other languages (e.g. question-answering in Spanish). Such shared representations are typically learned in isolation, either across tasks or across languages. In this work, we propose a meta-learning approach to learn the interactions between both tasks and languages. We also investigate the role of different sampling strategies used during meta-learning. We present experiments on five different tasks and six different la…
University of Hamburg（汉堡大学）；National Research University Higher School of Economics（国立研究型大学高等经济学院）；The Vinogradov Institute of the Russian Language, Russian Academy of Sciences（俄罗斯科学院维诺格拉多夫俄语研究所）；University of Mannheim（曼海姆大学）；Krasovskii Institute of Mathematics and Mechanics（克拉索夫斯基数学与力学研究所）；Scrapinghub（Scrapinghub公司）；Lomonosov Moscow State University（罗蒙诺索夫莫斯科国立大学）；Samsung Moscow Research Center（三星莫斯科研究中心）；ABBYY（ABBYY公司）
The paper describes the results of the first shared task on word sense induction (WSI) for the Russian language. While similar shared tasks were conducted in the past for some Romance and Germanic languages, we explore the performance of sense induction and disambiguation methods for a Slavic language that shares many features with other Slavic languages, such as rich morphology and virtually free word order. The participants were asked to group contexts of a given word in accordance with its senses that were not provided beforehand. For instance, given a word "bank" and a set of contexts for …
Dwarkadas J. Sanghvi College of Engineering（德瓦卡达斯·J·桑格维工程学院）
Social media networks and chatting platforms often use an informal version of natural text. Adversarial spelling attacks also tend to alter the input text by modifying the characters in the text. Normalizing these texts is an essential step for various applications like language translation and text to speech synthesis where the models are trained over clean regular English language. We propose a new robust model to perform text normalization. Our system uses the BERT language model to predict the masked words that correspond to the unnormalized words. We propose two unique masking strategies …
INESC TEC（INESC TEC（系统与计算机工程研究所））；University of Porto（波尔图大学）；Tehran Institute for Advanced Studies（德黑兰高级研究所）；Cardiff University（卡迪夫大学）
Transformer-based language models have taken many fields in NLP by storm. BERT and its derivatives dominate most of the existing evaluation benchmarks, including those for Word Sense Disambiguation (WSD), thanks to their ability in capturing context-sensitive semantic nuances. However, there is still little knowledge about their capabilities and potential limitations in encoding and recovering word senses. In this article, we provide an in-depth quantitative and qualitative analysis of the celebrated BERT model with respect to lexical ambiguity. One of the main conclusions of our analysis is t…
The Chinese University of Hong Kong（香港中文大学）；SpeechX Limited（SpeechX有限公司）
Popular approaches for Natural Language Understanding (NLU) usually rely on a huge amount of annotated data or handcrafted rules, which is laborious and not adaptive to domain extension. We recently proposed a Convex-Polytopic-Model-based framework that shows great potential in automatically extracting semantic patterns by exploiting the raw dialog corpus. The extracted semantic patterns can be used to generate semantic frames, which is essential in assisting NLU tasks. This paper further studies the CPM model in depth and visualizes its high interpretability and transparency at various levels…
University of Mannheim（曼海姆大学）；Ural Federal University（乌拉尔联邦大学）
In this paper, we present Watasense, an unsupervised system for word sense disambiguation. Given a sentence, the system chooses the most relevant sense of each input word with respect to the semantic similarity between the given sentence and the synset constituting the sense of the target word. Watasense has two modes of operation. The sparse mode uses the traditional vector space model to estimate the most similar word sense corresponding to its context. The dense mode, instead, uses synset embeddings to cope with the sparsity problem. We describe the architecture of the present system and al…
This paper is focused on the language modelling for task-oriented domains and presents an accurate analysis of the utterances acquired by the Dialogos spoken dialogue system. Dialogos allows access to the Italian Railways timetable by using the telephone over the public network. The language modelling aspects of specificity and behaviour to rare events are studied. A technique for getting a language model more robust, based on sentences generated by grammars, is presented. Experimental results show the benefit of the proposed technique. The increment of performance between language models crea…
University Pompeu Fabra（庞培法布拉大学）；University of Amsterdam（阿姆斯特丹大学）；University of Osnabrück（奥斯纳布吕克大学）；Facebook AI Research（脸书人工智能研究院）
In this paper, we propose to study language modelling as a multi-task problem, bringing together three strands of research: multi-task learning, linguistics, and interpretability. Based on hypotheses derived from linguistic theory, we investigate whether language models adhere to learning principles of multi-task learning during training. To showcase the idea, we analyse the generalisation behaviour of language models as they learn the linguistic concept of Negative Polarity Items (NPIs). Our experiments demonstrate that a multi-task setting naturally emerges within the objective of the more g…
Allowing users to interact through language borders is an interesting challenge for information technology. For the purpose of a computer assisted language learning system, we have chosen icons for representing meaning on the input interface, since icons do not depend on a particular language. However, a key limitation of this type of communication is the expression of articulated ideas instead of isolated concepts. We propose a method to interpret sequences of icons as complex messages by reconstructing the relations between concepts, so as to build conceptual graphs able to represent meaning…
