What makes a universal sentence encoder universal? The notion of a generic encoder of text appears to be at odds with the inherent contextualization and non-permanence of language use in a dynamic world. However, mapping sentences into generic fixed-length vectors for downstream similarity and retrieval tasks has been fruitful, particularly for multilingual applications. How do we manage this dilemma? In this work we propose Contextual Lensing, a methodology for inducing context-oriented universal sentence vectors. We break the construction of universal sentence vectors into a core, variable length, sentence matrix representation equipped with an adaptable `lens' from which fixed-length vectors can be induced as a function of the lens context. We show that it is possible to focus notions of language similarity into a small number of lens parameters given a core universal matrix representation. For example, we demonstrate the ability to encode translation similarity of sentences across several languages into a single weight matrix, even when the core encoder has not seen parallel data.
We construct a contextual network to represent a document with syntactic and semantic relations between word-sentence pairs, based on which we devise an unsupervised algorithm called CNATAR (Contextual Network And Text Analysis Rank) to score sentences, and rank them through a bi-objective 0-1 knapsack maximization problem over topic analysis and sentence scores. We show that CNATAR outperforms the combined ranking of the three human judges provided on the SummBank dataset under both ROUGE and BLEU metrics, which in term significantly outperforms each individual judge's ranking. Moreover, CNAT…
CINNAMON LAB（肉桂实验室）；Hung Yen University of Technology and Education（兴安技术教育大学）；The University of Queensland（昆士兰大学）
Sentence compression is the task of creating a shorter version of an input sentence while keeping important information. In this paper, we extend the task of compression by deletion with the use of contextual embeddings. Different from prior work usually using non-contextual embeddings (Glove or Word2Vec), we exploit contextual embeddings that enable our model capturing the context of inputs. More precisely, we utilize contextual embeddings stacked by bidirectional Long-short Term Memory and Conditional Random Fields for dealing with sequence labeling. Experimental results on a benchmark Googl…
We propose a novel data augmentation for labeled sentences called contextual augmentation. We assume an invariance that sentences are natural even if the words in the sentences are replaced with other words with paradigmatic relations. We stochastically replace words with other words that are predicted by a bi-directional language model at the word positions. Words predicted according to a context are numerous but appropriate for the augmentation of the original words. Furthermore, we retrofit a language model with a label-conditional architecture, which allows the model to augment sentences w…
Named entity recognition (NER) models are typically based on the architecture of Bi-directional LSTM (BiLSTM). The constraints of sequential nature and the modeling of single input prevent the full utilization of global information from larger scope, not only in the entire sentence, but also in the entire document (dataset). In this paper, we address these two deficiencies and propose a model augmented with hierarchical contextualized representation: sentence-level representation and document-level representation. In sentence-level, we take different contributions of words in a single sentence…
Newsletters and social networks can reflect the opinion about the market and specific stocks from the perspective of analysts and the general public on products and/or services provided by a company. Therefore, sentiment analysis of these texts can provide useful information to help investors trade in the market. In this paper, a hierarchical stack of Transformers model is proposed to identify the sentiment associated with companies and stocks, by predicting a score (of data type real) in a range between -1 and +1. Specifically, we fine-tuned a RoBERTa model to process headlines and microblogs…
Universidad Nacional del Sur（南方国立大学）；Dalhousie University（达尔豪斯大学）
This paper introduces the Ongoing Event Detection (OED) task, which is a specific Event Detection task where the goal is to detect ongoing event mentions only, as opposed to historical, future, hypothetical, or other forms or events that are neither fresh nor current. Any application that needs to extract structured information about ongoing events from unstructured texts can take advantage of an OED system. The main contribution of this paper are the following: (1) it introduces the OED task along with a dataset manually labeled for the task; (2) it presents the design and implementation of a…
We introduce a new task, Contextual Text Style Transfer - translating a sentence into a desired style with its surrounding context taken into account. This brings two key challenges to existing style transfer approaches: ($i$) how to preserve the semantic meaning of target sentence and its consistency with surrounding context during transfer; ($ii$) how to train a robust model with limited labeled data accompanied with context. To realize high-quality style transfer with natural context preservation, we propose a Context-Aware Style Transfer (CAST) model, which uses two separate encoders for e…
Document-level machine translation incorporates inter-sentential dependencies into the translation of a source sentence. In this paper, we propose a new framework to model cross-sentence dependencies by training neural machine translation (NMT) to predict both the target translation and surrounding sentences of a source sentence. By enforcing the NMT model to predict source context, we want the model to learn "contextualized" source sentence representations that capture document-level dependencies on the source side. We further propose two different methods to learn and integrate such contextu…
Imperial College London（帝国理工学院）；University of Cambridge（剑桥大学）；ALTA Institute（ALTA研究所）
We introduce the novel task of detecting sustainability initiatives in company reports. Given a full report, the aim is to automatically identify mentions of practical activities that a company has performed in order to tackle specific societal issues. New methods for identifying continuous sentence spans need to be developed for capturing the multi-sentence structure of individual sustainability initiatives. We release a new dataset of company reports in which the text has been manually annotated with sustainability initiatives. We also evaluate different models for initiative detection, intr…
Shanghai Jiao Tong University（上海交通大学）；National Institute of Information and Communications Technology（日本国立信息通信研究机构）
We present a universal framework to model contextualized sentence representations with visual awareness that is motivated to overcome the shortcomings of the multimodal parallel data with manual annotations. For each sentence, we first retrieve a diversity of images from a shared cross-modal embedding space, which is pre-trained on a large-scale of text-image pairs. Then, the texts and images are respectively encoded by transformer encoder and convolutional neural network. The two sequences of representations are further fused by a simple and effective attention layer. The architecture can be …
A variety of contextualised language models have been proposed in the NLP community, which are trained on diverse corpora to produce numerous Neural Language Models (NLMs). However, different NLMs have reported different levels of performances in downstream NLP applications when used as text representations. We propose a sentence-level meta-embedding learning method that takes independently trained contextualised word embedding models and learns a sentence embedding that preserves the complementary strengths of the input source NLMs. Our proposed method is unsupervised and is not tied to a par…
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…
Many online comments on social media platforms are hateful, humorous, or sarcastic. The sarcastic nature of these comments (especially the short ones) alters their actual implied sentiments, which leads to misinterpretations by the existing sentiment analysis models. A lot of research has already been done to detect sarcasm in the text using user-based, topical, and conversational information but not much work has been done to use inter-sentence contextual information for detecting the same. This paper proposes a new state-of-the-art deep learning architecture that uses a novel Bidirectional I…
We propose an unsupervised method for sentence summarization using only language modeling. The approach employs two language models, one that is generic (i.e. pretrained), and the other that is specific to the target domain. We show that by using a product-of-experts criteria these are enough for maintaining continuous contextual matching while maintaining output fluency. Experiments on both abstractive and extractive sentence summarization data sets show promising results of our method without being exposed to any paired data.
University of Padova（帕多瓦大学）；Fondazione Bruno Kessler（布鲁诺·凯斯勒基金会）；Amazon Alexa（亚马逊Alexa）
An important task for the design of Question Answering systems is the selection of the sentence containing (or constituting) the answer from documents relevant to the asked question. Most previous work has only used the target sentence to compute its score with the question as the models were not powerful enough to also effectively encode additional contextual information. In this paper, we analyze the role of the contextual information in the sentence selection task, proposing a Transformer based architecture that leverages two types of contexts, local and global. The former describes the par…
Google AI Language；Johns Hopkins University（约翰斯·霍普金斯大学）；Swarthmore College（斯沃斯莫尔学院）；New York University（纽约大学）；Brown University（布朗大学）
Contextualized representation models such as ELMo (Peters et al., 2018a) and BERT (Devlin et al., 2018) have recently achieved state-of-the-art results on a diverse array of downstream NLP tasks. Building on recent token-level probing work, we introduce a novel edge probing task design and construct a broad suite of sub-sentence tasks derived from the traditional structured NLP pipeline. We probe word-level contextual representations from four recent models and investigate how they encode sentence structure across a range of syntactic, semantic, local, and long-range phenomena. We find that ex…
We present a novel neural architecture for the Argument Reasoning Comprehension task of SemEval 2018. It is a simple neural network consisting of three parts, collectively judging whether the logic built on a set of given sentences (a claim, reason, and warrant) is plausible or not. The model utilizes contextualized word vectors pre-trained on large machine translation (MT) datasets as a form of transfer learning, which can help to mitigate the lack of training data. Quantitative analysis shows that simply leveraging LSTMs trained on MT datasets outperforms several baselines and non-transferre…
Unsupervised vector representations of sentences or documents are a major building block for many language tasks such as sentiment classification. However, current methods are uninterpretable and slow or require large training datasets. Recent word vector-based proposals implicitly assume that distances in a word embedding space are equally important, regardless of context. We introduce contextual salience (CoSal), a measure of word importance that uses the distribution of context vectors to normalize distances and weights. CoSal relies on the insight that unusual word vectors disproportionate…
Trading Central（交易中心公司）；IRIT（图卢兹计算机研究所）；CNRS（法国国家科学研究中心）；University of Toulouse（图卢兹大学）；L3i（图像、交互与信息实验室）；La Rochelle Université（拉罗谢尔大学）
This paper summarizes the joint participation of the Trading Central Labs and the L3i laboratory of the University of La Rochelle on both sub-tasks of the Shared Task FinSim-4 evaluation campaign. The first sub-task aims to enrich the 'Fortia ESG taxonomy' with new lexicon entries while the second one aims to classify sentences to either 'sustainable' or 'unsustainable' with respect to ESG (Environment, Social and Governance) related factors. For the first sub-task, we proposed a model based on pre-trained Sentence-BERT models to project sentences and concepts in a common space in order to bet…
We introduce Sentence-level Language Modeling, a new pre-training objective for learning a discourse language representation in a fully self-supervised manner. Recent pre-training methods in NLP focus on learning either bottom or top-level language representations: contextualized word representations derived from language model objectives at one extreme and a whole sequence representation learned by order classification of two given textual segments at the other. However, these models are not directly encouraged to capture representations of intermediate-size structures that exist in natural l…
Institute for Artificial Intelligence, University of Leeds（利兹大学人工智能研究所）
We describe a contextual parser for the Robot Commands Treebank, a new crowdsourced resource. In contrast to previous semantic parsers that select the most-probable parse, we consider the different problem of parsing using additional situational context to disambiguate between different readings of a sentence. We show that multiple semantic analyses can be searched using dynamic programming via interaction with a spatial planner, to guide the parsing process. We are able to parse sentences in near linear-time by ruling out analyses early on that are incompatible with spatial context. We report…
National Digital Switching System Engineering and Technological R&D Center（国家数字交换系统工程技术研究中心）；Eindhoven University of Technology（埃因霍温理工大学）
The classification of sentences is very challenging, since sentences contain the limited contextual information. In this paper, we proposed an Attention-Gated Convolutional Neural Network (AGCNN) for sentence classification, which generates attention weights from the feature's context windows of different sizes by using specialized convolution encoders. It makes full use of limited contextual information to extract and enhance the influence of important features in predicting the sentence's category. Experimental results demonstrated that our model can achieve up to 3.1% higher accuracy than s…
George Washington University（乔治华盛顿大学）；AWS AI（AWS人工智能）
In this paper we present an emotion classifier model submitted to the SemEval-2019 Task 3: EmoContext. The task objective is to classify emotion (i.e. happy, sad, angry) in a 3-turn conversational data set. We formulate the task as a classification problem and introduce a Gated Recurrent Neural Network (GRU) model with attention layer, which is bootstrapped with contextual information and trained with a multigenre corpus. We utilize different word embeddings to empirically select the most suited one to represent our features. We train the model with a multigenre emotion corpus to leverage usin…
University of Central Florida（中佛罗里达大学）；Tencent AI Lab（腾讯人工智能实验室）
Emerged as one of the best performing techniques for extractive summarization, determinantal point processes select the most probable set of sentences to form a summary according to a probability measure defined by modeling sentence prominence and pairwise repulsion. Traditionally, these aspects are modelled using shallow and linguistically informed features, but the rise of deep contextualized representations raises an interesting question of whether, and to what extent, contextualized representations can be used to improve DPP modeling. Our findings suggest that, despite the success of deep …
Amazon（亚马逊）；University of Washington（华盛顿大学）；Allen Institute for AI（艾伦人工智能研究所）
We describe an unsupervised method to create pseudo-parallel corpora for machine translation (MT) from unaligned text. We use multilingual BERT to create source and target sentence embeddings for nearest-neighbor search and adapt the model via self-training. We validate our technique by extracting parallel sentence pairs on the BUCC 2017 bitext mining task and observe up to a 24.5 point increase (absolute) in F1 scores over previous unsupervised methods. We then improve an XLM-based unsupervised neural MT system pre-trained on Wikipedia by supplementing it with pseudo-parallel text mined from …
Documents exhibit sequential structure at multiple levels of abstraction (e.g., sentences, paragraphs, sections). These abstractions constitute a natural hierarchy for representing the context in which to infer the meaning of words and larger fragments of text. In this paper, we present CLSTM (Contextual LSTM), an extension of the recurrent neural network LSTM (Long-Short Term Memory) model, where we incorporate contextual features (e.g., topics) into the model. We evaluate CLSTM on three specific NLP tasks: word prediction, next sentence selection, and sentence topic prediction. Results from …
Allen Institute for Artificial Intelligence（艾伦人工智能研究所）；Allen School of Computer Science & Engineering, University of Washington（华盛顿大学艾伦计算机科学与工程学院）
As a step toward better document-level understanding, we explore classification of a sequence of sentences into their corresponding categories, a task that requires understanding sentences in context of the document. Recent successful models for this task have used hierarchical models to contextualize sentence representations, and Conditional Random Fields (CRFs) to incorporate dependencies between subsequent labels. In this work, we show that pretrained language models, BERT (Devlin et al., 2018) in particular, can be used for this task to capture contextual dependencies without the need for …
University of California, Santa Cruz（加州大学圣克鲁兹分校）；Lawrence Berkeley National Laboratory（劳伦斯伯克利国家实验室）；University of California, Berkeley（加州大学伯克利分校）
Research Replication Prediction (RRP) is the task of predicting whether a published research result can be replicated or not. Building an interpretable neural text classifier for RRP promotes the understanding of why a research paper is predicted as replicable or non-replicable and therefore makes its real-world application more reliable and trustworthy. However, the prior works on model interpretation mainly focused on improving the model interpretability at the word/phrase level, which are insufficient especially for long research papers in RRP. Furthermore, the existing methods cannot utili…
University of Washington（华盛顿大学）；Google AI Language（谷歌AI语言团队）；Allen Institute for Artificial Intelligence（艾伦人工智能研究所）
We examine the capabilities of a unified, multi-task framework for three information extraction tasks: named entity recognition, relation extraction, and event extraction. Our framework (called DyGIE++) accomplishes all tasks by enumerating, refining, and scoring text spans designed to capture local (within-sentence) and global (cross-sentence) context. Our framework achieves state-of-the-art results across all tasks, on four datasets from a variety of domains. We perform experiments comparing different techniques to construct span representations. Contextualized embeddings like BERT perform w…
In this paper, we study the importance of context in predicting the citation worthiness of sentences in scholarly articles. We formulate this problem as a sequence labeling task solved using a hierarchical BiLSTM model. We contribute a new benchmark dataset containing over two million sentences and their corresponding labels. We preserve the sentence order in this dataset and perform document-level train/test splits, which importantly allows incorporating contextual information in the modeling process. We evaluate the proposed approach on three benchmark datasets. Our results quantify the bene…
Sentence ordering is one of important tasks in NLP. Previous works mainly focused on improving its performance by using pair-wise strategy. However, it is nontrivial for pair-wise models to incorporate the contextual sentence information. In addition, error prorogation could be introduced by using the pipeline strategy in pair-wise models. In this paper, we propose an end-to-end neural approach to address the sentence ordering problem, which uses the pointer network (Ptr-Net) to alleviate the error propagation problem and utilize the whole contextual information. Experimental results show the …
Social bias in machine learning has drawn significant attention, with work ranging from demonstrations of bias in a multitude of applications, curating definitions of fairness for different contexts, to developing algorithms to mitigate bias. In natural language processing, gender bias has been shown to exist in context-free word embeddings. Recently, contextual word representations have outperformed word embeddings in several downstream NLP tasks. These word representations are conditioned on their context within a sentence, and can also be used to encode the entire sentence. In this paper, w…
Question Generation is the task of automatically creating questions from textual input. In this work we present a new Attentional Encoder--Decoder Recurrent Neural Network model for automatic question generation. Our model incorporates linguistic features and an additional sentence embedding to capture meaning at both sentence and word levels. The linguistic features are designed to capture information related to named entity recognition, word case, and entity coreference resolution. In addition our model uses a copying mechanism and a special answer signal that enables generation of numerous …
Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）
Matching natural language sentences is central for many applications such as information retrieval and question answering. Existing deep models rely on a single sentence representation or multiple granularity representations for matching. However, such methods cannot well capture the contextualized local information in the matching process. To tackle this problem, we present a new deep architecture to match two sentences with multiple positional sentence representations. Specifically, each positional sentence representation is a sentence representation at this position, generated by a bidirect…
Rediscovering Hashed Random Projections for Efficient Quantization of Contextualized Sentence Embeddings
Berlin-Brandenburgische Akademie der Wissenschaften（柏林-勃兰登堡科学院）；Technische Universität Darmstadt（达姆施塔特工业大学）；Hessian Center for AI (hessian.AI)（黑森人工智能中心（hessian.AI））
A short and simple text carrying no emotion can represent some strong emotions when reading along with its context, i.e., the same sentence can express extreme anger as well as happiness depending on its context. In this paper, we propose a Contextual Affect Detection (CAD) framework which learns the inter-dependence of words in a sentence, and at the same time the inter-dependence of sentences in a dialogue. Our proposed CAD framework is based on a Gated Recurrent Unit (GRU), which is further assisted by contextual word embeddings and other diverse hand-crafted feature sets. Evaluation and an…
Sentence embedding is an important research topic in natural language processing (NLP) since it can transfer knowledge to downstream tasks. Meanwhile, a contextualized word representation, called BERT, achieves the state-of-the-art performance in quite a few NLP tasks. Yet, it is an open problem to generate a high quality sentence representation from BERT-based word models. It was shown in previous study that different layers of BERT capture different linguistic properties. This allows us to fusion information across layers to find better sentence representation. In this work, we study the lay…
University of Science and Technology of China（中国科学技术大学）；Ping An Technology (Shenzhen) Co., Ltd（平安科技（深圳）有限公司）
In this paper, we comprehensively study on context-aware generation of Chinese song lyrics. Conventional text generative models generate a sequence or sentence word by word, failing to consider the contextual relationship between sentences. Taking account into the characteristics of lyrics, a hierarchical attention based Seq2Seq (Sequence-to-Sequence) model is proposed for Chinese lyrics generation. With encoding of word-level and sentence-level contextual information, this model promotes the topic relevance and consistency of generation. A large Chinese lyrics corpus is also leveraged for mod…
Huazhong University of Science and Technology（华中科技大学）；Beijing Institute of Technology（北京理工大学）；Inception Institute of Artificial Intelligence（起源人工智能研究院）；Naval University of Engineering（海军工程大学）
Most existing named entity recognition (NER) approaches are based on sequence labeling models, which focus on capturing the local context dependencies. However, the way of taking one sentence as input prevents the modeling of non-sequential global context, which is useful especially when local context information is limited or ambiguous. To this end, we propose a model called Global Context enhanced Document-level NER (GCDoc) to leverage global contextual information from two levels, i.e., both word and sentence. At word-level, a document graph is constructed to model a wider range of dependen…
South China University of Technology（华南理工大学）；Ant Financial Service Group（蚂蚁金融服务集团）
Dialogue act recognition is a fundamental task for an intelligent dialogue system. Previous work models the whole dialog to predict dialog acts, which may bring the noise from unrelated sentences. In this work, we design a hierarchical model based on self-attention to capture intra-sentence and inter-sentence information. We revise the attention distribution to focus on the local and contextual semantic information by incorporating the relative position information between utterances. Based on the found that the length of dialog affects the performance, we introduce a new dialog segmentation m…
Though achieving impressive results on many NLP tasks, the BERT-like masked language models (MLM) encounter the discrepancy between pre-training and inference. In light of this gap, we investigate the contextual representation of pre-training and inference from the perspective of word probability distribution. We discover that BERT risks neglecting the contextual word similarity in pre-training. To tackle this issue, we propose an auxiliary gloss regularizer module to BERT pre-training (GR-BERT), to enhance word semantic similarity. By predicting masked words and aligning contextual embeddings…
Mila（米拉人工智能研究所）；McGill University（麦吉尔大学）；University of Montréal（蒙特利尔大学）；University of Amsterdam（阿姆斯特丹大学）
In this work, we propose a novel method for training neural networks to perform single-document extractive summarization without heuristically-generated extractive labels. We call our approach BanditSum as it treats extractive summarization as a contextual bandit (CB) problem, where the model receives a document to summarize (the context), and chooses a sequence of sentences to include in the summary (the action). A policy gradient reinforcement learning algorithm is used to train the model to select sequences of sentences that maximize ROUGE score. We perform a series of experiments demonstra…
Multilingual Contextualization of Large Language Models for Document-Level Machine Translation
Instituto Superior Técnico, Universidade de Lisboa (ELLIS Unit Lisbon)（里斯本大学理工学院（ELLIS单位里斯本））；Instituto de Telecomunicações（电信研究所）；Carnegie Mellon University（卡内基梅隆大学）；Unbabel
Unsupervised style transfer aims to change the style of an input sentence while preserving its original content without using parallel training data. In current dominant approaches, owing to the lack of fine-grained control on the influence from the target style,they are unable to yield desirable output sentences. In this paper, we propose a novel attentional sequence-to-sequence (Seq2seq) model that dynamically exploits the relevance of each output word to the target style for unsupervised style transfer. Specifically, we first pretrain a style classifier, where the relevance of each input wo…
In recent years, summarizers that incorporate domain knowledge into the process of text summarization have outperformed generic methods, especially for summarization of biomedical texts. However, construction and maintenance of domain knowledge bases are resource-intense tasks requiring significant manual annotation. In this paper, we demonstrate that contextualized representations extracted from the pre-trained deep language model BERT, can be effectively used to measure the similarity between sentences and to quantify the informative content. The results show that our BERT-based summarizer c…
University of Science and Technology of China（中国科学技术大学）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；Sun Yat-sen University（中山大学）；Microsoft Research Asia（微软亚洲研究院）
While data augmentation is an important trick to boost the accuracy of deep learning methods in computer vision tasks, its study in natural language tasks is still very limited. In this paper, we present a novel data augmentation method for neural machine translation. Different from previous augmentation methods that randomly drop, swap or replace words with other words in a sentence, we softly augment a randomly chosen word in a sentence by its contextual mixture of multiple related words. More accurately, we replace the one-hot representation of a word by a distribution (provided by a langua…
