While BERT is an effective method for learning monolingual sentence embeddings for semantic similarity and embedding based transfer learning (Reimers and Gurevych, 2019), BERT based cross-lingual sentence embeddings have yet to be explored. We systematically investigate methods for learning multilingual sentence embeddings by combining the best methods for learning monolingual and cross-lingual representations including: masked language modeling (MLM), translation language modeling (TLM) (Conneau and Lample, 2019), dual encoder translation ranking (Guo et al., 2018), and additive margin softmax (Yang et al., 2019a). We show that introducing a pre-trained multilingual language model dramatically reduces the amount of parallel training data required to achieve good performance by 80%. Composing the best of these methods produces a model that achieves 83.7% bi-text retrieval accuracy over 112 languages on Tatoeba, well above the 65.5% achieved by Artetxe and Schwenk (2019b), while still performing competitively on monolingual transfer learning benchmarks (Conneau and Kiela, 2018). Parallel data mined from CommonCrawl using our best model is shown to train competitive NMT models for en-zh and en-de. We publicly release our best multilingual sentence embedding model for 109+ languages at https://tfhub.dev/google/LaBSE.
Linguistic Acceptability is the task of determining whether a sentence is grammatical or ungrammatical. It has applications in several use cases like Question-Answering, Natural Language Generation, Neural Machine Translation, where grammatical correctness is crucial. In this paper we aim to understand the decision-making process of BERT (Devlin et al., 2019) in distinguishing between Linguistically Acceptable sentences (LA) and Linguistically Unacceptable sentences (LUA). We leverage Layer Integrated Gradients Attribution Scores (LIG) to explain the Linguistic Acceptability criteria that are …
Multilingual sentence encoders have seen much success in cross-lingual model transfer for downstream NLP tasks. Yet, we know relatively little about the properties of individual languages or the general patterns of linguistic variation that they encode. We propose methods for probing sentence representations from state-of-the-art multilingual encoders (LASER, M-BERT, XLM and XLM-R) with respect to a range of typological properties pertaining to lexical, morphological and syntactic structure. In addition, we investigate how this information is distributed across all layers of the models. Our re…
In this paper we focus on constructing useful embeddings of textual information in vacancies and resumes, which we aim to incorporate as features into job to job seeker matching models alongside other features. We explain our task where noisy data from parsed resumes, heterogeneous nature of the different sources of data, and crosslinguality and multilinguality present domain-specific challenges. We address these challenges by fine-tuning a Siamese Sentence-BERT (SBERT) model, which we call conSultantBERT, using a large-scale, real-world, and high quality dataset of over 270,000 resume-vacancy…
Detecting Redundant Health Survey Questions Using Language-agnostic BERT Sentence Embedding (LaBSE)
College of Natural Sciences, Seoul National University（首尔大学自然科学学院）；College of Nursing, Seoul National University（首尔大学护理学院）；The Research Institute of Nursing Science, Seoul National University（首尔大学护理科学研究所）；Samsung Medical Center（三星医疗中心）；David Geffen School of Medicine, University of California Los Angeles（加州大学洛杉矶分校大卫·格芬医学院）
Pronouns are important determinants of a text's meaning but difficult to translate. This is because pronoun choice can depend on entities described in previous sentences, and in some languages pronouns may be dropped when the referent is inferrable from the context. These issues can lead Neural Machine Translation (NMT) systems to make critical errors on pronouns that impair intelligibility and even reinforce gender bias. We investigate the severity of this pronoun issue, showing that (1) in some domains, pronoun choice can account for more than half of a NMT systems' errors, and (2) pronouns …
We propose a simple method to align multilingual contextual embeddings as a post-pretraining step for improved zero-shot cross-lingual transferability of the pretrained models. Using parallel data, our method aligns embeddings on the word level through the recently proposed Translation Language Modeling objective as well as on the sentence level via contrastive learning and random input shuffling. We also perform sentence-level code-switching with English when finetuning on downstream tasks. On XNLI, our best model (initialized from mBERT) improves over mBERT by 4.7% in the zero-shot setting a…
BERT (Devlin et al., 2018) and RoBERTa (Liu et al., 2019) has set a new state-of-the-art performance on sentence-pair regression tasks like semantic textual similarity (STS). However, it requires that both sentences are fed into the network, which causes a massive computational overhead: Finding the most similar pair in a collection of 10,000 sentences requires about 50 million inference computations (~65 hours) with BERT. The construction of BERT makes it unsuitable for semantic similarity search as well as for unsupervised tasks like clustering. In this publication, we present Sentence-BERT …
Université de Montréal（蒙特利尔大学）；School of Information, Renmin University of China（中国人民大学信息学院）；Mila - Québec Artificial Intelligence Institute（米拉-魁北克人工智能研究所）
Sentence ordering aims to arrange the sentences of a given text in the correct order. Recent work frames it as a ranking problem and applies deep neural networks to it. In this work, we propose a new method, named BERT4SO, by fine-tuning BERT for sentence ordering. We concatenate all sentences and compute their representations by using multiple special tokens and carefully designed segment (interval) embeddings. The tokens across multiple sentences can attend to each other which greatly enhances their interactions. We also propose a margin-based listwise ranking loss based on ListMLE to facili…
Beihang University（北京航空航天大学）；Microsoft（微软）；Zhongguancun Laboratory（中关村实验室）；Institute of Artificial Intelligence, Beihang University（北京航空航天大学人工智能研究院）
We propose PromptBERT, a novel contrastive learning method for learning better sentence representation. We firstly analyze the drawback of current sentence embedding from original BERT and find that it is mainly due to the static token embedding bias and ineffective BERT layers. Then we propose the first prompt-based sentence embeddings method and discuss two prompt representing methods and three prompt searching methods to make BERT achieve better sentence embeddings. Moreover, we propose a novel unsupervised training objective by the technology of template denoising, which substantially shor…
Named entity recognition (NER) is frequently addressed as a sequence classification task where each input consists of one sentence of text. It is nevertheless clear that useful information for the task can often be found outside of the scope of a single-sentence context. Recently proposed self-attention models such as BERT can both efficiently capture long-distance relationships in input as well as represent inputs consisting of several sentences, creating new opportunitites for approaches that incorporate cross-sentence information in natural language processing tasks. In this paper, we prese…
Aspect-based sentiment analysis (ABSA), which aims to identify fine-grained opinion polarity towards a specific aspect, is a challenging subtask of sentiment analysis (SA). In this paper, we construct an auxiliary sentence from the aspect and convert ABSA to a sentence-pair classification task, such as question answering (QA) and natural language inference (NLI). We fine-tune the pre-trained model from BERT and achieve new state-of-the-art results on SentiHood and SemEval-2014 Task 4 datasets.
Part AI Research Center（Part人工智能研究中心）；Amirkabir University of Technology（阿米尔卡比尔理工大学）
This paper presents a deep neural architecture, for Natural Language Sentence Matching (NLSM) by adding a deep recursive encoder to BERT so called BERT with Deep Recursive Encoder (BERT-DRE). Our analysis of model behavior shows that BERT still does not capture the full complexity of text, so a deep recursive encoder is applied on top of BERT. Three Bi-LSTM layers with residual connection are used to design a recursive encoder and an attention module is used on top of this encoder. To obtain the final vector, a pooling layer consisting of average and maximum pooling is used. We experiment our …
National Center for Biotechnology Information (NCBI), National Library of Medicine (NLM), National Institutes of Health (NIH)（美国国家生物技术信息中心（NCBI）、美国国家医学图书馆（NLM）、美国国立卫生研究院（NIH））
A biomedical relation statement is commonly expressed in multiple sentences and consists of many concepts, including gene, disease, chemical, and mutation. To automatically extract information from biomedical literature, existing biomedical text-mining approaches typically formulate the problem as a cross-sentence n-ary relation-extraction task that detects relations among n entities across multiple sentences, and use either a graph neural network (GNN) with long short-term memory (LSTM) or an attention mechanism. Recently, Transformer has been shown to outperform LSTM on many natural language…
Recently, BERT has become an essential ingredient of various NLP deep models due to its effectiveness and universal-usability. However, the online deployment of BERT is often blocked by its large-scale parameters and high computational cost. There are plenty of studies showing that the knowledge distillation is efficient in transferring the knowledge from BERT into the model with a smaller size of parameters. Nevertheless, current BERT distillation approaches mainly focus on task-specified distillation, such methodologies lead to the loss of the general semantic knowledge of BERT for universal…
Leveraging large amounts of unlabeled data using Transformer-like architectures, like BERT, has gained popularity in recent times owing to their effectiveness in learning general representations that can then be further fine-tuned for downstream tasks to much success. However, training these models can be costly both from an economic and environmental standpoint. In this work, we investigate how to effectively use unlabeled data: by exploring the task-specific semi-supervised approach, Cross-View Training (CVT) and comparing it with task-agnostic BERT in multiple settings that include domain a…
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…
Recently, BERT realized significant progress for sentence matching via word-level cross sentence attention. However, the performance significantly drops when using siamese BERT-networks to derive two sentence embeddings, which fall short in capturing the global semantic since the word-level attention between two sentences is absent. In this paper, we propose a Dual-view distilled BERT~(DvBERT) for sentence matching with sentence embeddings. Our method deals with a sentence pair from two distinct views, i.e., Siamese View and Interaction View. Siamese View is the backbone where we generate sent…
MKSSS’ Cummins College of Engineering for Women（MKSSS卡明斯女子工程学院）；L3Cube；Indian Institute of Technology Madras（印度理工学院马德拉斯分校）
Sentence representation from vanilla BERT models does not work well on sentence similarity tasks. Sentence-BERT models specifically trained on STS or NLI datasets are shown to provide state-of-the-art performance. However, building these models for low-resource languages is not straightforward due to the lack of these specialized datasets. This work focuses on two low-resource Indian languages, Hindi and Marathi. We train sentence-BERT models for these languages using synthetic NLI and STS datasets prepared using machine translation. We show that the strategy of NLI pre-training followed by ST…
Contextualized representations from a pre-trained language model are central to achieve a high performance on downstream NLP task. The pre-trained BERT and A Lite BERT (ALBERT) models can be fine-tuned to give state-ofthe-art results in sentence-pair regressions such as semantic textual similarity (STS) and natural language inference (NLI). Although BERT-based models yield the [CLS] token vector as a reasonable sentence embedding, the search for an optimal sentence embedding scheme remains an active research area in computational linguistics. This paper explores on sentence embedding models fo…
University of Leeds（利兹大学）；Alexandria University（亚历山大大学）
This paper presents an attempt to build a Modern Standard Arabic (MSA) sentence-level simplification system. We experimented with sentence simplification using two approaches: (i) a classification approach leading to lexical simplification pipelines which use Arabic-BERT, a pre-trained contextualised model, as well as a model of fastText word embeddings; and (ii) a generative approach, a Seq2Seq technique by applying a multilingual Text-to-Text Transfer Transformer mT5. We developed our training corpus by aligning the original and simplified sentences from the internationally acclaimed Arabic …
Objective: This work aimed to demonstrate the effectiveness of a hybrid approach based on Sentence BERT model and retrofitting algorithm to compute relatedness between any two biomedical concepts. Materials and Methods: We generated concept vectors by encoding concept preferred terms using ELMo, BERT, and Sentence BERT models. We used BioELMo and Clinical ELMo. We used Ontology Knowledge Free (OKF) models like PubMedBERT, BioBERT, BioClinicalBERT, and Ontology Knowledge Injected (OKI) models like SapBERT, CoderBERT, KbBERT, and UmlsBERT. We trained all the BERT models using Siamese network on …
Tehran Institute for Advanced Studies（德黑兰高级研究所）；Khatam University（哈塔姆大学）；Iran University of Science and Technology（伊朗科技大学）
Several studies have been carried out on revealing linguistic features captured by BERT. This is usually achieved by training a diagnostic classifier on the representations obtained from different layers of BERT. The subsequent classification accuracy is then interpreted as the ability of the model in encoding the corresponding linguistic property. Despite providing insights, these studies have left out the potential role of token representations. In this paper, we provide a more in-depth analysis on the representation space of BERT in search for distinct and meaningful subspaces that can expl…
Seoul National University（首尔国立大学）；NAVER AI Lab（NAVER人工智能实验室）
Although BERT and its variants have reshaped the NLP landscape, it still remains unclear how best to derive sentence embeddings from such pre-trained Transformers. In this work, we propose a contrastive learning method that utilizes self-guidance for improving the quality of BERT sentence representations. Our method fine-tunes BERT in a self-supervised fashion, does not rely on data augmentation, and enables the usual [CLS] token embeddings to function as sentence vectors. Moreover, we redesign the contrastive learning objective (NT-Xent) and apply it to sentence representation learning. We de…
Ant Financial Services Group（蚂蚁金融服务集团）；DAMO, Alibaba Group（阿里巴巴集团达摩院）
The ability of semantic reasoning over the sentence pair is essential for many natural language understanding tasks, e.g., natural language inference and machine reading comprehension. A recent significant improvement in these tasks comes from BERT. As reported, the next sentence prediction (NSP) in BERT, which learns the contextual relationship between two sentences, is of great significance for downstream problems with sentence-pair input. Despite the effectiveness of NSP, we suggest that NSP still lacks the essential signal to distinguish between entailment and shallow correlation. To remed…
A Comprehensive Survey of Sentence Representations: From the BERT Epoch to the ChatGPT Era and Beyond
ASUS Intelligent Cloud Services (AICS)（华硕智能云服务（AICS））；National University of Singapore（新加坡国立大学）；Singapore University of Technology and Design（新加坡科技设计大学）
Graduate School of Information Science and Technology, Hokkaido University（北海道大学信息科学与技术研究生院）；School of Engineering, Hokkaido University（北海道大学工程学院）；Faculty of Information Science and Technology, Hokkaido University（北海道大学信息科学与技术学院）
There are many discussions held during political meetings, and a large number of utterances for various topics is included in their transcripts. We need to read all of them if we want to follow speakers\' intentions or opinions about a given topic. To avoid such a costly and time-consuming process to grasp often longish discussions, NLP researchers work on generating concise summaries of utterances. Summarization subtask in QA Lab-PoliInfo-2 task of the NTCIR-15 addresses this problem for Japanese utterances in assembly minutes, and our team (SKRA) participated in this subtask. As a first step…
In this work, we represent Lex-BERT, which incorporates the lexicon information into Chinese BERT for named entity recognition (NER) tasks in a natural manner. Instead of using word embeddings and a newly designed transformer layer as in FLAT, we identify the boundary of words in the sentences using special tokens, and the modified sentence will be encoded directly by BERT. Our model does not introduce any new parameters and are more efficient than FLAT. In addition, we do not require any word embeddings accompanying the lexicon collection. Experiments on Ontonotes and ZhCrossNER show that our…
We propose BERTScore, an automatic evaluation metric for text generation. Analogously to common metrics, BERTScore computes a similarity score for each token in the candidate sentence with each token in the reference sentence. However, instead of exact matches, we compute token similarity using contextual embeddings. We evaluate using the outputs of 363 machine translation and image captioning systems. BERTScore correlates better with human judgments and provides stronger model selection performance than existing metrics. Finally, we use an adversarial paraphrase detection task to show that BE…
École Normale Supérieure-PSL（巴黎高等师范学院（PSL大学））；CNRS（法国国家科学研究中心）；U. Sorbonne Nouvelle（新索邦大学）；University of Pisa（比萨大学）
Both humans and neural language models are able to perform subject-verb number agreement (SVA). In principle, semantics shouldn't interfere with this task, which only requires syntactic knowledge. In this work we test whether meaning interferes with this type of agreement in English in syntactic structures of various complexities. To do so, we generate both semantically well-formed and nonsensical items. We compare the performance of BERT-base to that of humans, obtained with a psycholinguistic online crowdsourcing experiment. We find that BERT and humans are both sensitive to our semantic man…
In this paper, we present a Modern Standard Arabic (MSA) Sentence difficulty classifier, which predicts the difficulty of sentences for language learners using either the CEFR proficiency levels or the binary classification as simple or complex. We compare the use of sentence embeddings of different kinds (fastText, mBERT , XLM-R and Arabic-BERT), as well as traditional language features such as POS tags, dependency trees, readability scores and frequency lists for language learners. Our best results have been achieved using fined-tuned Arabic-BERT. The accuracy of our 3-way CEFR classificatio…
Huazhong University of Science and Technology（华中科技大学）；Zhejiang University（浙江大学）；Huawei Noah’s Ark Lab（华为诺亚方舟实验室）；Huawei Technologies Co., Ltd.（华为技术有限公司）
Knowledge distillation (KD) which transfers the knowledge from a large teacher model to a small student model, has been widely used to compress the BERT model recently. Besides the supervision in the output in the original KD, recent works show that layer-level supervision is crucial to the performance of the student BERT model. However, previous works designed the layer mapping strategy heuristically (e.g., uniform or last-layer), which can lead to inferior performance. In this paper, we propose to use the genetic algorithm (GA) to search for the optimal layer mapping automatically. To accele…
University of Tehran（德黑兰大学）；University of Rochester（罗切斯特大学）；Emory University（埃默里大学）
Discovering the logical sequence of events is one of the cornerstones in Natural Language Understanding. One approach to learn the sequence of events is to study the order of sentences in a coherent text. Sentence ordering can be applied in various tasks such as retrieval-based Question Answering, document summarization, storytelling, text generation, and dialogue systems. Furthermore, we can learn to model text coherence by learning how to order a set of shuffled sentences. Previous research has relied on RNN, LSTM, and BiLSTM architecture for learning text language models. However, these net…
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 …
This paper describes the system description for the HinglishEval challenge at INLG 2022. The goal of this task was to investigate the factors influencing the quality of the code-mixed text generation system. The task was divided into two subtasks, quality rating prediction and annotators disagreement prediction of the synthetic Hinglish dataset. We attempted to solve these tasks using sentence-level embeddings, which are obtained from mean pooling the contextualized word embeddings for all input tokens in our text. We experimented with various classifiers on top of the embeddings produced for …
Healthy Lifespan Institute（健康寿命研究所）；The University of Sheffield（谢菲尔德大学）
This paper describes our system for SemEval-2022 Task 2 Multilingual Idiomaticity Detection and Sentence Embedding sub-task B. We modify a standard BERT sentence transformer by adding embeddings for each idioms, which are created using BERTRAM and a small number of contexts. We show that this technique increases the quality of idiom representations and leads to better performance on the task. We also perform analysis on our final results and show that the quality of the produced idiom embeddings is highly sensitive to the quality of the input contexts.
In this paper we present a set of experiments carried out with BERT on a number of Italian sentences taken from poetry domain. The experiments are organized on the hypothesis of a very high level of difficulty in predictability at the three levels of linguistic complexity that we intend to monitor: lexical, syntactic and semantic level. To test this hypothesis we ran the Italian version of BERT with 80 sentences for a total of 900 tokens mostly extracted from Italian poetry of the first half of last century. Then we alternated canonical and noncanonical versions of the same sentence before pro…
Domain adaptation or transfer learning using pre-trained language models such as BERT has proven to be an effective approach for many natural language processing tasks. In this work, we propose to formulate word sense disambiguation as a relevance ranking task, and fine-tune BERT on sequence-pair ranking task to select the most probable sense definition given a context sentence and a list of candidate sense definitions. We also introduce a data augmentation technique for WSD using existing example sentences from WordNet. Using the proposed training objective and data augmentation technique, ou…
Tsinghua University（清华大学）；Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）
Task-agnostic knowledge distillation, a teacher-student framework, has been proved effective for BERT compression. Although achieving promising results on NLP tasks, it requires enormous computational resources. In this paper, we propose Extract Then Distill (ETD), a generic and flexible strategy to reuse the teacher's parameters for efficient and effective task-agnostic distillation, which can be applied to students of any size. Specifically, we introduce two variants of ETD, ETD-Rand and ETD-Impt, which extract the teacher's parameters in a random manner and by following an importance metric…
ByteDance AI Lab（字节跳动人工智能实验室）；Carnegie Mellon University（卡内基梅隆大学）
Pre-trained contextual representations like BERT have achieved great success in natural language processing. However, the sentence embeddings from the pre-trained language models without fine-tuning have been found to poorly capture semantic meaning of sentences. In this paper, we argue that the semantic information in the BERT embeddings is not fully exploited. We first reveal the theoretical connection between the masked language model pre-training objective and the semantic similarity task theoretically, and then analyze the BERT sentence embeddings empirically. We find that BERT always ind…
Variants of the BERT architecture specialised for producing full-sentence representations often achieve better performance on downstream tasks than sentence embeddings extracted from vanilla BERT. However, there is still little understanding of what properties of inputs determine the properties of such representations. In this study, we construct several sets of sentences with pre-defined lexical and syntactic structures and show that SOTA sentence transformers have a strong nominal-participant-set bias: cosine similarities between pairs of sentences are more strongly determined by the overlap…
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）；WeChat AI, Tencent Inc（腾讯微信人工智能部）
Recent studies on the lottery ticket hypothesis (LTH) show that pre-trained language models (PLMs) like BERT contain matching subnetworks that have similar transfer learning performance as the original PLM. These subnetworks are found using magnitude-based pruning. In this paper, we find that the BERT subnetworks have even more potential than these studies have shown. Firstly, we discover that the success of magnitude pruning can be attributed to the preserved pre-training performance, which correlates with the downstream transferability. Inspired by this, we propose to directly optimize the s…
Large pre-trained sentence encoders like BERT start a new chapter in natural language processing. A common practice to apply pre-trained BERT to sequence classification tasks (e.g., classification of sentences or sentence pairs) is by feeding the embedding of [CLS] token (in the last layer) to a task-specific classification layer, and then fine tune the model parameters of BERT and classifier jointly. In this paper, we conduct systematic analysis over several sequence classification datasets to examine the embedding values of [CLS] token before the fine tuning phase, and present the biased emb…
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…
Pre-trained contextualized language models such as BERT have shown great effectiveness in a wide range of downstream Natural Language Processing (NLP) tasks. However, the effective representations offered by the models target at each token inside a sequence rather than each sequence and the fine-tuning step involves the input of both sequences at one time, leading to unsatisfying representations of various sequences with different granularities. Especially, as sentence-level representations taken as the full training context in these models, there comes inferior performance on lower-level ling…
City University of Hong Kong Shenzhen Research Institute（香港城市大学深圳研究院）；City University of Hong Kong（香港城市大学）；Peking University（北京大学）
Contrastive learning has shown great potential in unsupervised sentence embedding tasks, e.g., SimCSE. However, We find that these existing solutions are heavily affected by superficial features like the length of sentences or syntactic structures. In this paper, we propose a semantics-aware contrastive learning framework for sentence embeddings, termed Pseudo-Token BERT (PT-BERT), which is able to exploit the pseudo-token space (i.e., latent semantic space) representation of a sentence while eliminating the impact of superficial features such as sentence length and syntax. Specifically, we in…
Pontificia Universidad Católica de Chile（智利天主教大学）；KU Leuven（鲁汶大学）；Universidad Técnica Federico Santa María（费德里科·圣玛丽亚技术大学）
Current language models are usually trained using a self-supervised scheme, where the main focus is learning representations at the word or sentence level. However, there has been limited progress in generating useful discourse-level representations. In this work, we propose to use ideas from predictive coding theory to augment BERT-style language models with a mechanism that allows them to learn suitable discourse-level representations. As a result, our proposed approach is able to predict future sentences using explicit top-down connections that operate at the intermediate layers of the netw…
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…
