Recent works show that learning contextualized embeddings for words is beneficial for downstream tasks. BERT is one successful example of this approach. It learns embeddings by solving two tasks, which are masked language model (masked LM) and the next sentence prediction (NSP). The pre-training of BERT can also be framed as a multitask learning problem. In this work, we adopt hierarchical multitask learning approaches for BERT pre-training. Pre-training tasks are solved at different layers instead of the last layer, and information from the NSP task is transferred to the masked LM task. Also, we propose a new pre-training task bigram shift to encode word order information. We choose two downstream tasks, one of which requires sentence-level embeddings (textual entailment), and the other requires contextualized embeddings of words (question answering). Due to computational restrictions, we use the downstream task data instead of a large dataset for the pre-training to see the performance of proposed models when given a restricted dataset. We test their performance on several probing tasks to analyze learned embeddings. Our results show that imposing a task hierarchy in pre-training improves the performance of embeddings.
Clinical notes contain an abundance of important but not-readily accessible information about patients. Systems to automatically extract this information rely on large amounts of training data for which their exists limited resources to create. Furthermore, they are developed dis-jointly; meaning that no information can be shared amongst task-specific systems. This bottle-neck unnecessarily complicates practical application, reduces the performance capabilities of each individual solution and associates the engineering debt of managing multiple information extraction systems. We address these …
A BERT-based Hierarchical Classification Model with Applications in Chinese Commodity Classification
School of Statistics and Mathematics, Central University of Finance and Economics（中央财经大学统计与数学学院）；Reigning Capital Co., Ltd.（Reigning Capital有限公司）；Center for Applied Statistics and School of Statistics, Renmin University of China（中国人民大学应用统计中心与统计学院）
University of British Columbia（不列颠哥伦比亚大学）；University of Pennsylvania（宾夕法尼亚大学）
Prediction of language varieties and dialects is an important language processing task, with a wide range of applications. For Arabic, the native tongue of ~ 300 million people, most varieties remain unsupported. To ease this bottleneck, we present a very large scale dataset covering 319 cities from all 21 Arab countries. We introduce a hierarchical attention multi-task learning (HA-MTL) approach for dialect identification exploiting our data at the city, state, and country levels. We also evaluate use of BERT on the three tasks, comparing it to the MTL approach. We benchmark and release our d…
Zhejiang University City College（浙江大学城市学院）；Zhejiang University（浙江大学）；Tsinghua University（清华大学）
Recently multimodal named entity recognition (MNER) has utilized images to improve the accuracy of NER in tweets. However, most of the multimodal methods use attention mechanisms to extract visual clues regardless of whether the text and image are relevant. Practically, the irrelevant text-image pairs account for a large proportion in tweets. The visual clues that are unrelated to the texts will exert uncertain or even negative effects on multimodal model learning. In this paper, we introduce a method of text-image relation propagation into the multimodal BERT model. We integrate soft or hard …
Multitask learning often helps improve the performance of related tasks as these often have inter-dependence on each other and perform better when solved in a joint framework. In this paper, we present a deep multitask learning framework that jointly performs polarity and subjective detection. We propose an attention-based multitask model for predicting polarity and subjectivity. The input sentences are transformed into vectors using pre-trained BERT and Glove embeddings, and the results depict that BERT embedding based model works better than the Glove based model. We compare our approach wit…
Information extraction is an important task in NLP, enabling the automatic extraction of data for relational database filling. Historically, research and data was produced for English text, followed in subsequent years by datasets in Arabic, Chinese (ACE/OntoNotes), Dutch, Spanish, German (CoNLL evaluations), and many others. The natural tendency has been to treat each language as a different dataset and build optimized models for each. In this paper we investigate a single Named Entity Recognition model, based on a multilingual BERT, that is trained jointly on many languages simultaneously, a…
Natural language processing (NLP) has been applied to various fields including text classification and sentiment analysis. In the shared task of sentiment analysis of code-mixed tweets, which is a part of the SemEval-2020 competition~\cite{patwa2020sentimix}, we preprocess datasets by replacing emoji and deleting uncommon characters and so on, and then fine-tune the Bidirectional Encoder Representation from Transformers(BERT) to perform the best. After exhausting top3 submissions, Our team MeisterMorxrc achieves an averaged F1 score of 0.730 in this task, and and our codalab username is Meiste…
Given the massive market of advertising and the sharply increasing online multimedia content (such as videos), it is now fashionable to promote advertisements (ads) together with the multimedia content. It is exhausted to find relevant ads to match the provided content manually, and hence, some automatic advertising techniques are developed. Since ads are usually hard to understand only according to its visual appearance due to the contained visual metaphor, some other modalities, such as the contained texts, should be exploited for understanding. To further improve user experience, it is nece…
Many natural language processing and information retrieval problems can be formalized as the task of semantic matching. Existing work in this area has been largely focused on matching between short texts (e.g., question answering), or between a short and a long text (e.g., ad-hoc retrieval). Semantic matching between long-form documents, which has many important applications like news recommendation, related article recommendation and document clustering, is relatively less explored and needs more research effort. In recent years, self-attention based models like Transformers and BERT have ach…
University of Virginia（弗吉尼亚大学）；Microsoft Research（微软研究院）；Microsoft Bing Ads（微软必应广告）
This paper examines the challenging problem of learning representations of entities and relations in a complex multi-relational knowledge graph. We propose HittER, a Hierarchical Transformer model to jointly learn Entity-relation composition and Relational contextualization based on a source entity's neighborhood. Our proposed model consists of two different Transformer blocks: the bottom block extracts features of each entity-relation pair in the local neighborhood of the source entity and the top block aggregates the relational information from outputs of the bottom block. We further design …
University of Massachusetts, Amherst（马萨诸塞大学阿默斯特分校）；TTI-Chicago（芝加哥丰田技术研究所）
Previous work has shown that neural encoder-decoder speech recognition can be improved with hierarchical multitask learning, where auxiliary tasks are added at intermediate layers of a deep encoder. We explore the effect of hierarchical multitask learning in the context of connectionist temporal classification (CTC)-based speech recognition, and investigate several aspects of this approach. Consistent with previous work, we observe performance improvements on telephone conversational speech recognition (specifically the Eval2000 test sets) when training a subword-level CTC model with an auxili…
FI Group（FI集团）；Université Sorbonne Paris Nord（索邦巴黎北大学）
The task of Named Entity Recognition (NER) is an important component of many natural language processing systems, such as relation extraction and knowledge graph construction. In this work, we present a simple and effective approach for Named Entity Recognition. The main idea of our approach is to encode the input subword sequence with a pre-trained transformer such as BERT, and then, instead of directly classifying the word labels, another layer of transformer is added to the subword representation to better encode the word-level interaction. We evaluate our approach on three benchmark datase…
One of the most crucial challenges in question answering (QA) is the scarcity of labeled data, since it is costly to obtain question-answer (QA) pairs for a target text domain with human annotation. An alternative approach to tackle the problem is to use automatically generated QA pairs from either the problem context or from large amount of unstructured texts (e.g. Wikipedia). In this work, we propose a hierarchical conditional variational autoencoder (HCVAE) for generating QA pairs given unstructured texts as contexts, while maximizing the mutual information between generated QA pairs to ens…
We introduce a novel approach to transformers that learns hierarchical representations in multiparty dialogue. First, three language modeling tasks are used to pre-train the transformers, token- and utterance-level language modeling and utterance order prediction, that learn both token and utterance embeddings for better understanding in dialogue contexts. Then, multi-task learning between the utterance prediction and the token span prediction is applied to fine-tune for span-based question answering (QA). Our approach is evaluated on the FriendsQA dataset and shows improvements of 3.8% and 1.…
Transformer language models (TLMs) are critical for most NLP tasks, but they are difficult to create for low-resource languages because of how much pretraining data they require. In this work, we investigate two techniques for training monolingual TLMs in a low-resource setting: greatly reducing TLM size, and complementing the masked language modeling objective with two linguistically rich supervised tasks (part-of-speech tagging and dependency parsing). Results from 7 diverse languages indicate that our model, MicroBERT, is able to produce marked improvements in downstream task evaluations re…
pluszero Inc.（pluszero公司）；The University of Tokyo（东京大学）
With the advent of FrameNet and PropBank, many semantic role labeling (SRL) systems have been proposed in English. Although research on Japanese predicate argument structure analysis (PASA) has been conducted, most studies focused on surface cases. There are only few previous works on Japanese SRL for deep cases, and their models' accuracies are low. Therefore, we propose a hierarchical multitask learning method with dependency parsing (DP) and show that our model achieves state-of-the-art results in Japanese SRL. Also, we conduct experiments with a joint model that performs both argument iden…
This work aims at hierarchical multi-label patents classification for patents disclosing technologies related to green plastics. This is an emerging field for which there is currently no classification scheme, and hence, no labeled data is available, making this task particularly challenging. We first propose a classification scheme for this technology and a way to learn a machine learning model to classify patents into the proposed classification scheme. To achieve this, we come up with a strategy to automatically assign labels to patents in order to create a labeled training dataset that can…
FlexCare: Leveraging Cross-Task Synergy for Flexible Multimodal Healthcare Prediction
Institute of Information Science, Beijing Jiaotong University（北京交通大学信息科学研究所）；Medical Big Data Research Center, Chinese PLA General Hospital（中国人民解放军总医院医学大数据中心）
School of Foreign Languages and Cultures, Xiamen University（厦门大学外文学院）；DeepAI Tech Co., Ltd（深湃信息科技（深圳）有限公司）
The automatic classification is a process of automatically assigning text documents to predefined categories. An accurate automatic patent classifier is crucial to patent inventors and patent examiners in terms of intellectual property protection, patent management, and patent information retrieval. We present BERT-CNN, a hierarchical patent classifier based on pre-trained language model by training the national patent application documents collected from the State Information Center, China. The experimental results show that BERT-CNN achieves 84.3% accuracy, which is far better than the two c…
Unstructured clinical text in EHRs contains crucial information for applications including decision support, trial matching, and retrospective research. Recent work has applied BERT-based models to clinical information extraction and text classification, given these models' state-of-the-art performance in other NLP domains. However, BERT is difficult to apply to clinical notes because it doesn't scale well to long sequences of text. In this work, we propose a novel fine-tuning approach called SnipBERT. Instead of using entire notes, SnipBERT identifies crucial snippets and then feeds them into…
University of Arizona（亚利桑那大学）；University of Birmingham（伯明翰大学）
Prior work has demonstrated that question classification (QC), recognizing the problem domain of a question, can help answer it more accurately. However, developing strong QC algorithms has been hindered by the limited size and complexity of annotated data available. To address this, we present the largest challenge dataset for QC, containing 7,787 science exam questions paired with detailed classification labels from a fine-grained hierarchical taxonomy of 406 problem domains. We then show that a BERT-based model trained on this dataset achieves a large (+0.12 MAP) gain compared with previous…
Relation extraction is a key task in Natural Language Processing (NLP), which aims to extract relations between entity pairs from given texts. Recently, relation extraction (RE) has achieved remarkable progress with the development of deep neural networks. Most existing research focuses on constructing explicit structured features using external knowledge such as knowledge graph and dependency tree. In this paper, we propose a novel method to extract multi-granularity features based solely on the original input sentences. We show that effective structured features can be attained even without …
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络空间安全学院）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）
Document-level RE requires reading, inferring and aggregating over multiple sentences. From our point of view, it is necessary for document-level RE to take advantage of multi-granularity inference information: entity level, sentence level and document level. Thus, how to obtain and aggregate the inference information with different granularity is challenging for document-level RE, which has not been considered by previous work. In this paper, we propose a Hierarchical Inference Network (HIN) to make full use of the abundant information from entity level, sentence level and document level. Tra…
Pune Institute of Computer Technology（浦那计算机技术学院）；Indian Institute of Technology Madras（印度理工学院马德拉斯分校）
Text classification algorithms investigate the intricate relationships between words or phrases and attempt to deduce the document's interpretation. In the last few years, these algorithms have progressed tremendously. Transformer architecture and sentence encoders have proven to give superior results on natural language processing tasks. But a major limitation of these architectures is their applicability for text no longer than a few hundred words. In this paper, we explore hierarchical transfer learning approaches for long document classification. We employ pre-trained Universal Sentence En…
This paper describes the system submitted by ANA Team for the SemEval-2019 Task 3: EmoContext. We propose a novel Hierarchical LSTMs for Contextual Emotion Detection (HRLCE) model. It classifies the emotion of an utterance given its conversational context. The results show that, in this task, our HRCLE outperforms the most recent state-of-the-art text classification framework: BERT. We combine the results generated by BERT and HRCLE to achieve an overall score of 0.7709 which ranked 5th on the final leader board of the competition among 165 Teams.
Osaka University（大阪大学）；The University of Electro-Communications（电气通信大学）
Recently, the bidirectional encoder representations from transformers (BERT) model has attracted much attention in the field of natural language processing, owing to its high performance in language understanding-related tasks. The BERT model learns language representation that can be adapted to various tasks via pre-training using a large corpus in an unsupervised manner. This study proposes the language and action learning using multimodal BERT (lamBERT) model that enables the learning of language and actions by 1) extending the BERT model to multimodal representation and 2) integrating it w…
The Hong Kong Polytechnic University（香港理工大学）；Xidian University（西安电子科技大学）
Most current extractive summarization models generate summaries by selecting salient sentences. However, one of the problems with sentence-level extractive summarization is that there exists a gap between the human-written gold summary and the oracle sentence labels. In this paper, we propose to extract fact-level semantic units for better extractive summarization. We also introduce a hierarchical structure, which incorporates the multi-level of granularities of the textual information into the model. In addition, we incorporate our model with BERT using a hierarchical graph mask. This allows …
Guangdong University of Technology（广东工业大学）；Guangdong Ocean University（广东海洋大学）；University of Surrey（萨里大学）；Tianjin University of Technology（天津理工大学）
Visual storytelling is a creative and challenging task, aiming to automatically generate a story-like description for a sequence of images. The descriptions generated by previous visual storytelling approaches lack coherence because they use word-level sequence generation methods and do not adequately consider sentence-level dependencies. To tackle this problem, we propose a novel hierarchical visual storytelling framework which separately models sentence-level and word-level semantics. We use the transformer-based BERT to obtain embeddings for sentences and words. We then employ a hierarchica…
How and to what extent does BERT encode syntactically-sensitive hierarchical information or positionally-sensitive linear information? Recent work has shown that contextual representations like BERT perform well on tasks that require sensitivity to linguistic structure. We present here two studies which aim to provide a better understanding of the nature of BERT's representations. The first of these focuses on the identification of structurally-defined elements using diagnostic classifiers, while the second explores BERT's representation of subject-verb agreement and anaphor-antecedent depende…
University College Dublin（都柏林大学）；Teagasc Agriculture and Food Development Authority（爱尔兰农业与食品发展局）；ADAPT Research Centre（ADAPT研究中心）
Training deep learning models with limited labelled data is an attractive scenario for many NLP tasks, including document classification. While with the recent emergence of BERT, deep learning language models can achieve reasonably good performance in document classification with few labelled instances, there is a lack of evidence in the utility of applying BERT-like models on long document classification. This work introduces a long-text-specific model -- the Hierarchical BERT Model (HBM) -- that learns sentence-level features of the text and works well in scenarios with limited labelled data…
Indraprastha Institute of Information Technology, Delhi（德里英德拉普拉斯塔信息技术学院）；Extramarks Education pvt. ltd.（Extramarks教育私人有限公司）
Online education platforms are powered by various NLP pipelines, which utilize models like BERT to aid in content curation. Since the inception of the pre-trained language models like BERT, there have also been many efforts toward adapting these pre-trained models to specific domains. However, there has not been a model specifically adapted for the education domain (particularly K-12) across subjects to the best of our knowledge. In this work, we propose to train a language model on a corpus of data curated by us across multiple subjects from various sources for K-12 education. We also evaluat…
The success of interactive dialog systems is usually associated with the quality of the spoken language understanding (SLU) task, which mainly identifies the corresponding dialog acts and slot values in each turn. By treating utterances in isolation, most SLU systems often overlook the semantic context in which a dialog act is expected. The act dependency between turns is non-trivial and yet critical to the identification of the correct semantic representations. Previous works with limited context awareness have exposed the inadequacy of dealing with complexity in multiproned user intents, whi…
Medical document understanding has gained much attention recently. One representative task is the International Classification of Disease (ICD) diagnosis code assignment. Existing work adopts either RNN or CNN as the backbone network because the vanilla BERT cannot handle well long documents (>2000 to kens). One issue shared across all these approaches is that they are over specific to the ICD code assignment task, losing generality to give the whole document-level and sentence-level embedding. As a result, it is not straight-forward to direct them to other downstream NLU tasks. Motivated by t…
Queen’s University（女王大学）；University of Science and Technology of China（中国科学技术大学）；iFLYTEK Research（科大讯飞研究院）
Disentanglement is a problem in which multiple conversations occur in the same channel simultaneously, and the listener should decide which utterance is part of the conversation he will respond to. We propose a new model, named Dialogue BERT (DialBERT), which integrates local and global semantics in a single stream of messages to disentangle the conversations that mixed together. We employ BERT to capture the matching information in each utterance pair at the utterance-level, and use a BiLSTM to aggregate and incorporate the context-level information. With only a 3% increase in parameters, a 1…
Hierarchical Section Matching Prediction (HSMP) BERT for Fine-Grained Extraction of Structured Data from Hebrew Free-Text Radiology Reports in Crohn's Disease
Faculty of Data and Decision Sciences, Technion – Israel Institute of Technology（1 数据与决策科学学院，技术离子-以色列理工学院）；Faculty of Biomedical Engineering, Technion – Israel Institute of Technology（2 生物医学工程学院，技术离子-以色列理工学院）；Juliet Keidan Institute of Pediatric Gastroenterology, Hepatology and Nutrition, The Eisenberg R&D Authority, Shaare Zedek Medical Center, The Hebrew University School of Medicine（3 肝胆营养研究所，Eisenberg R&D机构，Shaare Zedek医疗中心，希伯来大学医学院）；Pediatric Radiology Unit, Radiology Department, The Eisenberg R&D Authority, Shaare Zedek Medical Center, The Hebrew University of Jerusalem（4 儿童放射科单位，放射科部门，Eisenberg R&D机构，Shaare Zedek医疗中心，希伯来大学杰里科分校）
Allen Institute for Artificial Intelligence（艾伦人工智能研究所）；University of California, Irvine（加州大学欧文分校）；University of Washington（华盛顿大学）
Contextual word representations, typically trained on unstructured, unlabeled text, do not contain any explicit grounding to real world entities and are often unable to remember facts about those entities. We propose a general method to embed multiple knowledge bases (KBs) into large scale models, and thereby enhance their representations with structured, human-curated knowledge. For each KB, we first use an integrated entity linker to retrieve relevant entity embeddings, then update contextual word representations via a form of word-to-entity attention. In contrast to previous approaches, the…
Institute of Informatics & Telecommunications, NCSR “Demokritos”（德谟克利特国家科学研究中心信息与电信研究所）；Department of Informatics, Athens University of Economics and Business（雅典经济与商业大学信息学系）
Although BERT is widely used by the NLP community, little is known about its inner workings. Several attempts have been made to shed light on certain aspects of BERT, often with contradicting conclusions. A much raised concern focuses on BERT's over-parameterization and under-utilization issues. To this end, we propose o novel approach to fine-tune BERT in a structured manner. Specifically, we focus on Large Scale Multilabel Text Classification (LMTC) where documents are assigned with one or more labels from a large predefined set of hierarchically organized labels. Our approach guides specifi…
Center for Language and Speech Processing, Johns Hopkins University（约翰斯·霍普金斯大学语言与语音处理中心）；Avaya Conversational Intelligence（亚美亚对话智能部门）
BERT, which stands for Bidirectional Encoder Representations from Transformers, is a recently introduced language representation model based upon the transfer learning paradigm. We extend its fine-tuning procedure to address one of its major limitations - applicability to inputs longer than a few hundred words, such as transcripts of human call conversations. Our method is conceptually simple. We segment the input into smaller chunks and feed each of them into the base model. Then, we propagate each output through a single recurrent layer, or another transformer, followed by a softmax activati…
IQVIA（艾昆纬）；Georgia Institute of Technology（佐治亚理工学院）；IBM Research AI（IBM人工智能研究院）
Medication recommendation is an important healthcare application. It is commonly formulated as a temporal prediction task. Hence, most existing works only utilize longitudinal electronic health records (EHRs) from a small number of patients with multiple visits ignoring a large number of patients with a single visit (selection bias). Moreover, important hierarchical knowledge such as diagnosis hierarchy is not leveraged in the representation learning process. To address these challenges, we propose G-BERT, a new model to combine the power of Graph Neural Networks (GNNs) and BERT (Bidirectional…
University of Southern California（南加州大学）；Fudan University（复旦大学）
The impressive performance of neural networks on natural language processing tasks attributes to their ability to model complicated word and phrase compositions. To explain how the model handles semantic compositions, we study hierarchical explanation of neural network predictions. We identify non-additivity and context independent importance attributions within hierarchies as two desirable properties for highlighting word and phrase compositions. We show some prior efforts on hierarchical explanations, e.g. contextual decomposition, do not satisfy the desired properties mathematically, leadin…
Huawei Technologies Co., Ltd.（华为技术有限公司）；ByteDance（字节跳动）；Huawei Noah’s Ark Lab（华为诺亚方舟实验室）；Shanghai AI Laboratory（上海人工智能实验室）
Incorporating factual knowledge into pre-trained language models (PLM) such as BERT is an emerging trend in recent NLP studies. However, most of the existing methods combine the external knowledge integration module with a modified pre-training loss and re-implement the pre-training process on the large-scale corpus. Re-pretraining these models is usually resource-consuming, and difficult to adapt to another domain with a different knowledge graph (KG). Besides, those works either cannot embed knowledge context dynamically according to textual context or struggle with the knowledge ambiguity i…
Alibaba Group（阿里巴巴集团）；Beijing Jiaotong University（北京交通大学）；University of Edinburgh（爱丁堡大学）
Recently, a variety of probing tasks are proposed to discover linguistic properties learned in contextualized word embeddings. Many of these works implicitly assume these embeddings lay in certain metric spaces, typically the Euclidean space. This work considers a family of geometrically special spaces, the hyperbolic spaces, that exhibit better inductive biases for hierarchical structures and may better reveal linguistic hierarchies encoded in contextualized representations. We introduce a Poincare probe, a structural probe projecting these embeddings into a Poincare subspace with explicitly …
Generating explanations for neural networks has become crucial for their applications in real-world with respect to reliability and trustworthiness. In natural language processing, existing methods usually provide important features which are words or phrases selected from an input text as an explanation, but ignore the interactions between them. It poses challenges for humans to interpret an explanation and connect it to model prediction. In this work, we build hierarchical explanations by detecting feature interactions. Such explanations visualize how words and phrases are combined at differ…
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（加利福尼亚大学）；Google Research（谷歌研究院）
Numerical reasoning over text (NRoT) presents unique challenges that are not well addressed by existing pre-training objectives. We explore five sequential training schedules that adapt a pre-trained T5 model for NRoT. Our final model is adapted from T5, but further pre-trained on three datasets designed to strengthen skills necessary for NRoT and general reading comprehension before being fine-tuned on the Discrete Reasoning over Text (DROP) dataset. The training improves DROP's adjusted F1 performance (a numeracy-focused score) from 45.90 to 70.83. Our model closes in on GenBERT (72.4), a cu…
How to obtain hierarchical representations with an increasing level of abstraction becomes one of the key issues of learning with deep neural networks. A variety of RNN models have recently been proposed to incorporate both explicit and implicit hierarchical information in modeling languages in the literature. In this paper, we propose a novel approach called the latent indicator layer to identify and learn implicit hierarchical information (e.g., phrases), and further develop an EM algorithm to handle the latent indicator layer in training. The latent indicator layer further simplifies a text…
Black-box probing models can reliably extract linguistic features like tense, number, and syntactic role from pretrained word representations. However, the manner in which these features are encoded in representations remains poorly understood. We present a systematic study of the linear geometry of contextualized word representations in ELMO and BERT. We show that a variety of linguistic features (including structured dependency relationships) are encoded in low-dimensional subspaces. We then refine this geometric picture, showing that there are hierarchical relations between the subspaces en…
Comparing representations of long clinical texts for the task of patient note-identification
Inria（法国国家信息与自动化研究所）；Inserm（法国国家健康与医学研究院）；Data Science Platform, Imagine Institute（伊马金研究所数据科学平台）；Hôpital Universitaire Necker-Enfants Malades（内克尔-恩范茨-马拉德大学医院）；Assistance Publique - Hôpitaux de Paris (APHP)（巴黎公共医疗援助医院集团）；Université de Lorraine（洛林大学）；CNRS（法国国家科学研究中心）；LORIA（洛林计算机科学与应用实验室）；INESC-ID（里斯本大学学院计算机与系统工程研究中心）；Instituto Superior Técnico（里斯本高等技术学院）；Universidade de Lisboa（里斯本大学）
Conversation structure is useful for both understanding the nature of conversation dynamics and for providing features for many downstream applications such as summarization of conversations. In this work, we define the problem of conversation structure modeling as identifying the parent utterance(s) to which each utterance in the conversation responds to. Previous work usually took a pair of utterances to decide whether one utterance is the parent of the other. We believe the entire ancestral history is a very important information source to make accurate prediction. Therefore, we design a no…
