Recurrent neural networks (RNNs) have long been an architecture of interest for computational models of human sentence processing. The recently introduced Transformer architecture outperforms RNNs on many natural language processing tasks but little is known about its ability to model human language processing. We compare Transformer- and RNN-based language models' ability to account for measures of human reading effort. Our analysis shows Transformers to outperform RNNs in explaining self-paced reading times and neural activity during reading English sentences, challenging the widely held idea that human sentence processing involves recurrent and immediate processing and provides evidence for cue-based retrieval.
Underutilization of Syntactic Processing by Chinese Learners of English in Comprehending English Sentences, Evidenced from Adapted Garden-Path Ambiguity Experiment
This paper describes SentencePiece, a language-independent subword tokenizer and detokenizer designed for Neural-based text processing, including Neural Machine Translation. It provides open-source C++ and Python implementations for subword units. While existing subword segmentation tools assume that the input is pre-tokenized into word sequences, SentencePiece can train subword models directly from raw sentences, which allows us to make a purely end-to-end and language independent system. We perform a validation experiment of NMT on English-Japanese machine translation, and find that it is po…
The complexity of sentences characteristic to biomedical articles poses a challenge to natural language parsers, which are typically trained on large-scale corpora of non-technical text. We propose a text simplification process, bioSimplify, that seeks to reduce the complexity of sentences in biomedical abstracts in order to improve the performance of syntactic parsers on the processed sentences. Syntactic parsing is typically one of the first steps in a text mining pipeline. Thus, any improvement in performance would have a ripple effect over all processing steps. We evaluated our method usin…
University of California, Los Angeles（加利福尼亚大学洛杉矶分校）；Arizona State University（亚利桑那州立大学）；University of Edinburgh（爱丁堡大学）
Writing and reading are dynamic processes. As an author composes a text, a sequence of words is produced. This sequence is one that, the author hopes, causes a revisitation of certain thoughts and ideas in others. These processes of composition and revisitation by readers are ordered in time. This means that text itself can be investigated under the lens of dynamical systems. A common technique for analyzing the behavior of dynamical systems, known as recurrence quantification analysis (RQA), can be used as a method for analyzing sequential structure of text. RQA treats text as a sequential me…
In this study, we aim to find a method to auto-tag sentences specific to a domain. Our training data comprises short conversational sentences extracted from chat conversations between company's customer representatives and web site visitors. We manually tagged approximately 14 thousand visitor inputs into ten basic categories, which will later be used in a transformer-based language model with attention mechanisms for the ultimate goal of developing a chatbot application that can produce meaningful dialogue. We considered three different state-of-the-art models and reported their auto-tagging …
Most compositional distributional semantic models represent sentence meaning with a single vector. In this paper, we propose a Structured Distributional Model (SDM) that combines word embeddings with formal semantics and is based on the assumption that sentences represent events and situations. The semantic representation of a sentence is a formal structure derived from Discourse Representation Theory and containing distributional vectors. This structure is dynamically and incrementally built by integrating knowledge about events and their typical participants, as they are activated by lexical…
We extend the centering model for the resolution of intra-sentential anaphora and specify how to handle complex sentences. An empirical evaluation indicates that the functional information structure guides the search for an antecedent within the sentence.
This paper is motivated by the automation of neuropsychological tests involving discourse analysis in the retellings of narratives by patients with potential cognitive impairment. In this scenario the task of sentence boundary detection in speech transcripts is important as discourse analysis involves the application of Natural Language Processing tools, such as taggers and parsers, which depend on the sentence as a processing unit. Our aim in this paper is to verify which embedding induction method works best for the sentence boundary detection task, specifically whether it be those which wer…
Isfahan University of Technology（伊斯法罕理工大学）；Shahid Bahonar University of Kerman（克尔曼沙希德·巴霍纳尔大学）；University of Basque Country UPV/EHU（巴斯克大学（UPV/EHU））
In this paper, we develop a compositional vector-based semantics of positive transitive sentences in quantum natural language processing for a non-English language, i.e. Persian, to compare the parametrized quantum circuits of two synonymous sentences in two languages, English and Persian. By considering grammar+meaning of a transitive sentence, we translate DisCoCat diagram via ZX-calculus into quantum circuit form. Also, we use a bigraph method to rewrite DisCoCat diagram and turn into quantum circuit in the semantic side.
The goal of sentence and document modeling is to accurately represent the meaning of sentences and documents for various Natural Language Processing tasks. In this work, we present Dependency Sensitive Convolutional Neural Networks (DSCNN) as a general-purpose classification system for both sentences and documents. DSCNN hierarchically builds textual representations by processing pretrained word embeddings via Long Short-Term Memory networks and subsequently extracting features with convolution operators. Compared with existing recursive neural models with tree structures, DSCNN does not rely …
The main goal of this master's thesis is to introduce Quantum Natural Language Processing (QNLP) in a way understandable by both the NLP engineer and the quantum computing practitioner. QNLP is a recent application of quantum computing that aims at representing sentences' meaning as vectors encoded into quantum computers. To achieve this, the distributional meaning of words is extended by the compositional meaning of sentences (DisCoCat model) : the vectors representing words' meanings are composed through the syntactic structure of the sentence. This is done using an algorithm based on tensor…
Sentence embedding is an important research topic in natural language processing. It is essential to generate a good embedding vector that fully reflects the semantic meaning of a sentence in order to achieve an enhanced performance for various natural language processing tasks, such as machine translation and document classification. Thus far, various sentence embedding models have been proposed, and their feasibility has been demonstrated through good performances on tasks following embedding, such as sentiment analysis and sentence classification. However, because the performances of senten…
The Australian National University（澳大利亚国立大学）；Data61/CSIRO（澳大利亚联邦科学与工业研究组织数据61中心）；University of Turku（图尔库大学）
Sentence compression is a Natural Language Processing (NLP) task aimed at shortening original sentences and preserving their key information. Its applications can benefit many fields e.g. one can build tools for language education. However, current methods are largely based on Recurrent Neural Network (RNN) models which suffer from poor processing speed. To address this issue, in this paper, we propose a token-wise Convolutional Neural Network, a CNN-based model along with pre-trained Bidirectional Encoder Representations from Transformers (BERT) features for deletion-based sentence compressio…
University of Copenhagen（哥本哈根大学）；Vrije Universiteit Amsterdam（阿姆斯特丹自由大学）
Determining the relative importance of the elements in a sentence is a key factor for effortless natural language understanding. For human language processing, we can approximate patterns of relative importance by measuring reading fixations using eye-tracking technology. In neural language models, gradient-based saliency methods indicate the relative importance of a token for the target objective. In this work, we compare patterns of relative importance in English language processing by humans and models and analyze the underlying linguistic patterns. We find that human processing patterns in…
Japan Advanced Institute of Science and Technology（日本北陆先端科学技术大学院大学）；University of Engineering and Technology, VNU（越南国立大学工程技术大学）；National Institute of Informatics（国立信息学研究所）
Ambiguity is a characteristic of natural language, which makes expression ideas flexible. However, in a domain that requires accurate statements, it becomes a barrier. Specifically, a single word can have many meanings and multiple words can have the same meaning. When translating a text into a foreign language, the translator needs to determine the exact meaning of each element in the original sentence to produce the correct translation sentence. From that observation, in this paper, we propose ParaLaw Nets, a pretrained model family using sentence-level cross-lingual information to reduce am…
Duke University（杜克大学）；Stanford University（斯坦福大学）；Microsoft Research（微软研究院）
Vector representations of sentences, trained on massive text corpora, are widely used as generic sentence embeddings across a variety of NLP problems. The learned representations are generally assumed to be continuous and real-valued, giving rise to a large memory footprint and slow retrieval speed, which hinders their applicability to low-resource (memory and computation) platforms, such as mobile devices. In this paper, we propose four different strategies to transform continuous and generic sentence embeddings into a binarized form, while preserving their rich semantic information. The intr…
Particles fullfill several distinct central roles in the Japanese language. They can mark arguments as well as adjuncts, can be functional or have semantic funtions. There is, however, no straightforward matching from particles to functions, as, e.g., GA can mark the subject, the object or an adjunct of a sentence. Particles can cooccur. Verbal arguments that could be identified by particles can be eliminated in the Japanese sentence. And finally, in spoken language particles are often omitted. A proper treatment of particles is thus necessary to make an analysis of Japanese sentences possible…
Google Research（谷歌研究院）；Johns Hopkins University（约翰斯·霍普金斯大学）
This paper describes the Dakshina dataset, a new resource consisting of text in both the Latin and native scripts for 12 South Asian languages. The dataset includes, for each language: 1) native script Wikipedia text; 2) a romanization lexicon; and 3) full sentence parallel data in both a native script of the language and the basic Latin alphabet. We document the methods used for preparation and selection of the Wikipedia text in each language; collection of attested romanizations for sampled lexicons; and manual romanization of held-out sentences from the native script collections. We additio…
Comparing Human and Language Models Sentence Processing Difficulties on Complex Structures
Blavatnik School of Computer Science, Tel Aviv University, Israel（巴尔-艾塔夫大学计算机科学学院）；Department of Linguistics, Tel Aviv University, Israel（巴尔-艾塔夫大学语言学系）；Sagol School of Neuroscience, Tel Aviv University, Israel（巴尔-艾塔夫大学神经科学学院）
Information Sciences Institute（信息科学研究所）；University of Southern California（南加州大学）
News article revision histories have the potential to give us novel insights across varied fields of linguistics and social sciences. In this work, we present, to our knowledge, the first publicly available dataset of news article revision histories, or NewsEdits. Our dataset is multilingual; it contains 1,278,804 articles with 4,609,430 versions from over 22 English- and French-language newspaper sources based in three countries. Across version pairs, we count 10.9 million added sentences; 8.9 million changed sentences and 6.8 million removed sentences. Within the changed sentences, we derive…
Parallel sentence extraction is a task addressing the data sparsity problem found in multilingual natural language processing applications. We propose an end-to-end deep neural network approach to detect translational equivalence between sentences in two different languages. In contrast to previous approaches, which typically rely on multiples models and various word alignment features, by leveraging continuous vector representation of sentences we remove the need of any domain specific feature engineering. Using a siamese bidirectional recurrent neural networks, our results against a strong b…
University of Washington（华盛顿大学）；Allen Institute for Artificial Intelligence（艾伦人工智能研究所）；Carnegie Mellon University（卡内基梅隆大学）
Despite the tremendous empirical success of neural models in natural language processing, many of them lack the strong intuitions that accompany classical machine learning approaches. Recently, connections have been shown between convolutional neural networks (CNNs) and weighted finite state automata (WFSAs), leading to new interpretations and insights. In this work, we show that some recurrent neural networks also share this connection to WFSAs. We characterize this connection formally, defining rational recurrences to be recurrent hidden state update functions that can be written as the Forw…
We provide the first exploration of sentence embeddings from text-to-text transformers (T5). Sentence embeddings are broadly useful for language processing tasks. While T5 achieves impressive performance on language tasks cast as sequence-to-sequence mapping problems, it is unclear how to produce sentence embeddings from encoder-decoder models. We investigate three methods for extracting T5 sentence embeddings: two utilize only the T5 encoder and one uses the full T5 encoder-decoder model. To support our investigation, we establish a new sentence representation transfer benchmark, SentGLUE, wh…
Electroencephalography (EEG) signals recordings when people reading natural languages are commonly used as a cognitive method to interpret human language understanding in neuroscience and psycholinguistics. Previous studies have demonstrated that the human fixation and activation in word reading associated with some brain regions, but it is not clear when and how to measure the brain dynamics across time and frequency domains. In this study, we propose the first analysis of event-related brain potentials (ERPs), and event-related spectral perturbations (ERSPs) on benchmark datasets which consi…
Attention mechanisms have become a standard tool for sequence modeling tasks, in particular by stacking self-attention layers over the entire input sequence as in the Transformer architecture. In this work we introduce a novel attention procedure called staircase attention that, unlike self-attention, operates across the sequence (in time) recurrently processing the input by adding another step of processing. A step in the staircase comprises of backward tokens (encoding the sequence so far seen) and forward tokens (ingesting a new part of the sequence), or an extreme Ladder version with a for…
Duke University（杜克大学）；NEC Laboratories America（美国NEC实验室）
Convolutional neural networks (CNNs) have recently emerged as a popular building block for natural language processing (NLP). Despite their success, most existing CNN models employed in NLP share the same learned (and static) set of filters for all input sentences. In this paper, we consider an approach of using a small meta network to learn context-sensitive convolutional filters for text processing. The role of meta network is to abstract the contextual information of a sentence or document into a set of input-aware filters. We further generalize this framework to model sentence pairs, where…
Sikkim Manipal Institute of Technology（锡金马尼帕尔理工学院）；Tezpur University（特兹普尔大学）
A natural language (or ordinary language) is a language that is spoken, written, or signed by humans for general-purpose communication, as distinguished from formal languages (such as computer-programming languages or the "languages" used in the study of formal logic). The computational activities required for enabling a computer to carry out information processing using natural language is called natural language processing. We have taken Assamese language to check the grammars of the input sentence. Our aim is to produce a technique to check the grammatical structures of the sentences in Ass…
Segmentation is a fundamental step for most Natural Language Processing tasks. The Kurdish language is a multi-dialect, under-resourced language which is written in different scripts. The lack of various segmented corpora is one of the major bottlenecks in Kurdish language processing. We used Punkt, an unsupervised machine learning method, to segment a Kurdish corpus of Sorani dialect, written in Persian-Arabic script. According to the literature, studies on using Punkt on non-Latin data are scanty. In our experiment, we achieved an F1 score of 91.10% and had an Error Rate of 16.32%. The high …
University of California, Los Angeles（加州大学洛杉矶分校）；University of Southern California（南加州大学）；Fudan University（复旦大学）；University of Virginia（弗吉尼亚大学）
Learning distributed sentence representations is one of the key challenges in natural language processing. Previous work demonstrated that a recurrent neural network (RNNs) based sentence encoder trained on a large collection of annotated natural language inference data, is efficient in the transfer learning to facilitate other related tasks. In this paper, we show that joint learning of multiple tasks results in better generalizable sentence representations by conducting extensive experiments and analysis comparing the multi-task and single-task learned sentence encoders. The quantitative ana…
Microsoft Corporation（微软公司）；Center for Theoretical Physics, MIT（麻省理工学院理论物理中心）
Missing sentence generation (or sentence infilling) fosters a wide range of applications in natural language generation, such as document auto-completion and meeting note expansion. This task asks the model to generate intermediate missing sentences that can syntactically and semantically bridge the surrounding context. Solving the sentence infilling task requires techniques in natural language processing ranging from understanding to discourse-level planning to generation. In this paper, we propose a framework to decouple the challenge and address these three aspects respectively, leveraging …
Text classification is a fundamental task in natural language processing (NLP). Several recent studies show the success of deep learning on text processing. Convolutional neural network (CNN), as a popular deep learning model, has shown remarkable success in the task of text classification. In this paper, new baseline models have been studied for text classification using CNN. In these models, documents are fed to the network as a three-dimensional tensor representation to provide sentence-level analysis. Applying such a method enables the models to take advantage of the positional information…
Inferring the probability distribution of sentences or word sequences is a key process in natural language processing. While word-level language models (LMs) have been widely adopted for computing the joint probabilities of word sequences, they have difficulty in capturing a context long enough for sentence probability estimation (SPE). To overcome this, recent studies introduced training methods using sentence-level noise-contrastive estimation (NCE) with recurrent neural networks (RNNs). In this work, we attempt to extend it for contextual SPE, which aims to estimate a conditional sentence p…
University of Information Technology（信息技术大学）；Vietnam National University（越南国立大学）
The development of natural language processing (NLP) in general and machine reading comprehension in particular has attracted the great attention of the research community. In recent years, there are a few datasets for machine reading comprehension tasks in Vietnamese with large sizes, such as UIT-ViQuAD and UIT-ViNewsQA. However, the datasets are not diverse in answers to serve the research. In this paper, we introduce UIT-ViWikiQA, the first dataset for evaluating sentence extraction-based machine reading comprehension in the Vietnamese language. The UIT-ViWikiQA dataset is converted from th…
School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Alibaba AI Labs（阿里巴巴人工智能实验室）
Active learning is able to significantly reduce the annotation cost for data-driven techniques. However, previous active learning approaches for natural language processing mainly depend on the entropy-based uncertainty criterion, and ignore the characteristics of natural language. In this paper, we propose a pre-trained language model based active learning approach for sentence matching. Differing from previous active learning, it can provide linguistic criteria to measure instances and help select more efficient instances for annotation. Experiments demonstrate our approach can achieve great…
