Pre-trained transformer models shine in many natural language processing tasks and therefore are expected to bear the representation of the input sentence or text meaning. These sentence-level embeddings are also important in retrieval-augmented generation. But do commonly used plain averaging or prompt templates sufficiently capture and represent the underlying meaning? After providing a comprehensive review of existing sentence embedding extraction and refinement methods, we thoroughly test different combinations and our original extensions of the most promising ones on pretrained models. Namely, given 110 M parameters, BERT's hidden representations from multiple layers, and many tokens, we try diverse ways to extract optimal sentence embeddings. We test various token aggregation and representation post-processing techniques. We also test multiple ways of using a general Wikitext dataset to complement BERT's sentence embeddings. All methods are tested on eight Semantic Textual Similarity (STS), six short text clustering, and twelve classification tasks. We also evaluate our representation-shaping techniques on other static models, including random token representations. Proposed representation extraction methods improve the performance on STS and clustering tasks for all models considered. Very high improvements for static token-based models, especially random embeddings for STS tasks, almost reach the performance of BERT-derived representations. Our work shows that the representation-shaping techniques significantly improve sentence embeddings extracted from BERT-based and simple baseline models.
TCS Research & Innovation（塔塔咨询服务公司研究与创新部）；Indian Institute of Technology Bombay（印度理工学院孟买分校）
Most of the past work in relation extraction deals with relations occurring within a sentence and having only two entity arguments. We propose a new formulation of the relation extraction task where the relations are more general than intra-sentence relations in the sense that they may span multiple sentences and may have more than two arguments. Moreover, the relations are more specific than corpus-level relations in the sense that their scope is limited only within a document and not valid globally throughout the corpus. We propose a novel sequence representation to characterize instances of…
Toyota Technological Institute at Chicago（芝加哥丰田理工学院）；Tencent AI Lab（腾讯人工智能实验室）；Cornell（康奈尔大学）；University of Pennsylvania（宾夕法尼亚大学）
Remarkable success has been achieved in the last few years on some limited machine reading comprehension (MRC) tasks. However, it is still difficult to interpret the predictions of existing MRC models. In this paper, we focus on extracting evidence sentences that can explain or support the answers of multiple-choice MRC tasks, where the majority of answer options cannot be directly extracted from reference documents. Due to the lack of ground truth evidence sentence labels in most cases, we apply distant supervision to generate imperfect labels and then use them to train an evidence sentence e…
Indiana University Purdue University Indianapolis（印第安纳大学与普渡大学印第安纳波利斯联合分校）
Extracting cause-effect entities from medical literature is an important task in medical information retrieval. A solution for solving this task can be used for compilation of various causality relations, such as, causality between disease and symptoms, between medications and side effects, between genes and diseases, etc. Existing solutions for extracting cause-effect entities work well for sentences where the cause and the effect phrases are name entities, single-word nouns, or noun phrases consisting of two to three words. Unfortunately, in medical literature, cause and effect phrases in a …
National Centre for Text Mining（国家文本挖掘中心）；Manchester Centre for Genomic Medicine（曼彻斯特基因组医学中心）；St Mary’s Hospital（圣玛丽医院）；The University of Manchester（曼彻斯特大学）；Manchester University Hospitals NHS Foundation Trust（曼彻斯特大学医院 NHS 基金会信托）；School of Biological Sciences（生物科学学院）；Faculty of Biology, Medicine and Health（生物、医学与健康学部）；School of Medical Sciences（医学科学学院）；Christie NHS Foundation Trust（克里斯蒂 NHS 基金会信托）
To interpret the genetic profile present in a patient sample, it is necessary to know which mutations have important roles in the development of the corresponding cancer type. Named entity recognition is a core step in the text mining pipeline which facilitates mining valuable cancer information from the scientific literature. However, due to the scarcity of related datasets, previous NER attempts in this domain either suffer from low performance when deep learning based models are deployed, or they apply feature based machine learning models or rule based models to tackle this problem, which …
Sentence-level relation extraction (RE) aims at identifying the relationship between two entities in a sentence. Many efforts have been devoted to this problem, while the best performing methods are still far from perfect. In this paper, we revisit two problems that affect the performance of existing RE models, namely entity representation and noisy or ill-defined labels. Our improved RE baseline, incorporated with entity representations with typed markers, achieves an F1 of 74.6% on TACRED, significantly outperforms previous SOTA methods. Furthermore, the presented new baseline achieves an F1…
University of Electronic Science and Technology of China（电子科技大学）；TROY Information Technology Co., Ltd.（Troy信息技术有限公司）
Relation extraction (RE) has recently moved from the sentence-level to document-level, which requires aggregating document information and using entities and mentions for reasoning. Existing works put entity nodes and mention nodes with similar representations in a document-level graph, whose complex edges may incur redundant information. Furthermore, existing studies only focus on entity-level reasoning paths without considering global interactions among entities cross-sentence. To these ends, we propose a novel document-level RE model with a GRaph information Aggregation and Cross-sentence R…
In this paper, we consider the problem of open information extraction (OIE) for extracting entity and relation level intermediate structures from sentences in open-domain. We focus on four types of valuable intermediate structures (Relation, Attribute, Description, and Concept), and propose a unified knowledge expression form, SAOKE, to express them. We publicly release a data set which contains more than forty thousand sentences and the corresponding facts in the SAOKE format labeled by crowd-sourcing. To our knowledge, this is the largest publicly available human labeled data set for open in…
Kangwon National University（江原大学）；Konkuk University（建国大学）
Relation extraction is a type of information extraction task that recognizes semantic relationships between entities in a sentence. Many previous studies have focused on extracting only one semantic relation between two entities in a single sentence. However, multiple entities in a sentence are associated through various relations. To address this issue, we propose a relation extraction model based on a dual pointer network with a multi-head attention mechanism. The proposed model finds n-to-1 subject-object relations using a forward object decoder. Then, it finds 1-to-n subject-object relatio…
A relation tuple consists of two entities and the relation between them, and often such tuples are found in unstructured text. There may be multiple relation tuples present in a text and they may share one or both entities among them. Extracting such relation tuples from a sentence is a difficult task and sharing of entities or overlapping entities among the tuples makes it more challenging. Most prior work adopted a pipeline approach where entities were identified first followed by finding the relations among them, thus missing the interaction among the relation tuples in a sentence. In this …
David R. Cheriton School of Computer Science, University of Waterloo（滑铁卢大学大卫·切里顿计算机科学学院）；University of Amsterdam（阿姆斯特丹大学）；Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）
The goal of text ranking is to generate an ordered list of texts retrieved from a corpus in response to a query. Although the most common formulation of text ranking is search, instances of the task can also be found in many natural language processing applications. This survey provides an overview of text ranking with neural network architectures known as transformers, of which BERT is the best-known example. The combination of transformers and self-supervised pretraining has been responsible for a paradigm shift in natural language processing (NLP), information retrieval (IR), and beyond. In…
Toyota Technological Institute at Chicago（芝加哥丰田技术研究所）
Many natural language processing (NLP) tasks involve reasoning with textual spans, including question answering, entity recognition, and coreference resolution. While extensive research has focused on functional architectures for representing words and sentences, there is less work on representing arbitrary spans of text within sentences. In this paper, we conduct a comprehensive empirical evaluation of six span representation methods using eight pretrained language representation models across six tasks, including two tasks that we introduce. We find that, although some simple span representa…
Microsoft Research（微软研究院）；Beijing Institute of Technology（北京理工大学）
Multilingual T5 (mT5) pretrains a sequence-to-sequence model on massive monolingual texts, which has shown promising results on many cross-lingual tasks. In this paper, we improve multilingual text-to-text transfer Transformer with translation pairs (mT6). Specifically, we explore three cross-lingual text-to-text pre-training tasks, namely, machine translation, translation pair span corruption, and translation span corruption. In addition, we propose a partially non-autoregressive objective for text-to-text pre-training. We evaluate the methods on eight multilingual benchmark datasets, includi…
Parallel sentence extraction is a task addressing the data sparsity problem found in multilingual natural language processing applications. We propose a bidirectional recurrent neural network based approach to extract parallel sentences from collections of multilingual texts. Our experiments with noisy parallel corpora show that we can achieve promising results against a competitive baseline by removing the need of specific feature engineering or additional external resources. To justify the utility of our approach, we extract sentence pairs from Wikipedia articles to train machine translation…
Question Answering (QA) is in increasing demand as the amount of information available online and the desire for quick access to this content grows. A common approach to QA has been to fine-tune a pretrained language model on a task-specific labeled dataset. This paradigm, however, relies on scarce, and costly to obtain, large-scale human-labeled data. We propose an unsupervised approach to training QA models with generated pseudo-training data. We show that generating questions for QA training by applying a simple template on a related, retrieved sentence rather than the original context sent…
University of Chinese Academy of Sciences（中国科学院大学）；Institute of Software, Chinese Academy of Sciences（中国科学院软件研究所）
Distant supervision (DS) is a promising approach for relation extraction but often suffers from the noisy label problem. Traditional DS methods usually represent an entity pair as a bag of sentences and denoise labels using multi-instance learning techniques. The bag-based paradigm, however, fails to leverage the inter-sentence-level and the entity-level evidence for relation extraction, and their denoising algorithms are often specialized and complicated. In this paper, we propose a new DS paradigm--document-based distant supervision, which models relation extraction as a document-based machi…
Code-switching (CS), a ubiquitous phenomenon due to the ease of communication it offers in multilingual communities still remains an understudied problem in language processing. The primary reasons behind this are: (1) minimal efforts in leveraging large pretrained multilingual models, and (2) the lack of annotated data. The distinguishing case of low performance of multilingual models in CS is the intra-sentence mixing of languages leading to switch points. We first benchmark two sequence labeling tasks -- POS and NER on 4 different language pairs with a suite of pretrained models to identify…
School of Information, The University of Arizona（亚利桑那大学信息学院）；Amazon Alexa AI（亚马逊 Alexa AI）
Current answer sentence selection (AS2) applied in open-domain question answering (ODQA) selects answers by ranking a large set of possible candidates, i.e., sentences, extracted from the retrieved text. In this paper, we present Passage-based Extracting Answer Sentence In-place (PEASI), a novel design for AS2 optimized for Web-scale setting, that, instead, computes such answer without processing each candidate individually. Specifically, we design a Transformer-based framework that jointly (i) reranks passages retrieved for a question and (ii) identifies a probable answer from the top passage…
University of California, Berkeley（加州大学伯克利分校）；Lawrence Berkeley National Laboratory（劳伦斯伯克利国家实验室）
Intelligently extracting and linking complex scientific information from unstructured text is a challenging endeavor particularly for those inexperienced with natural language processing. Here, we present a simple sequence-to-sequence approach to joint named entity recognition and relation extraction for complex hierarchical information in scientific text. The approach leverages a pre-trained large language model (LLM), GPT-3, that is fine-tuned on approximately 500 pairs of prompts (inputs) and completions (outputs). Information is extracted either from single sentences or across sentences in…
Despite the extensive success of pretrained language models as encoders for building NLP systems, they haven't seen prominence as decoders for sequence generation tasks. We explore the question of whether these models can be adapted to be used as universal decoders. To be considered "universal," a decoder must have an implicit representation for any target sentence $s$, such that it can recover that sentence exactly when conditioned on its representation. For large transformer-based language models trained on vast amounts of English text, we investigate whether such representations can be easi…
Most previous studies aim at extracting events from a single sentence, while document-level event extraction still remains under-explored. In this paper, we focus on extracting event arguments from an entire document, which mainly faces two critical problems: a) the long-distance dependency between trigger and arguments over sentences; b) the distracting context towards an event in the document. To address these issues, we propose a Two-Stream Abstract meaning Representation enhanced extraction model (TSAR). TSAR encodes the document from different perspectives by a two-stream encoding module,…
Sentence embeddings encode sentences in fixed dense vectors and have played an important role in various NLP tasks and systems. Methods for building sentence embeddings include unsupervised learning such as Quick-Thoughts and supervised learning such as InferSent. With the success of pretrained NLP models, recent research shows that fine-tuning pretrained BERT on SNLI and Multi-NLI data creates state-of-the-art sentence embeddings, outperforming previous sentence embeddings methods on various evaluation benchmarks. In this paper, we propose a new method to build sentence embeddings by doing su…
The University of Michigan（密歇根大学）；University of Louisiana at Lafayette（路易斯安那大学拉法叶分校）
Predicting the potential success of a book in advance is vital in many applications. This could help both publishers and readers in their decision-making process whether or not a book is worth publishing and reading, respectively. In this paper, we propose a model that leverages pretrained sentence embeddings along with various readability scores for book success prediction. Unlike previous methods, the proposed method requires no count-based, lexical, or syntactic features. Instead, we use a convolutional neural network over pretrained sentence embeddings and leverage different readability sc…
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 …
Recent work on evaluating grammatical knowledge in pretrained sentence encoders gives a fine-grained view of a small number of phenomena. We introduce a new analysis dataset that also has broad coverage of linguistic phenomena. We annotate the development set of the Corpus of Linguistic Acceptability (CoLA; Warstadt et al., 2018) for the presence of 13 classes of syntactic phenomena including various forms of argument alternations, movement, and modification. We use this analysis set to investigate the grammatical knowledge of three pretrained encoders: BERT (Devlin et al., 2018), GPT (Radford…
Traditional approaches to extractive summarization rely heavily on human-engineered features. In this work we propose a data-driven approach based on neural networks and continuous sentence features. We develop a general framework for single-document summarization composed of a hierarchical document encoder and an attention-based extractor. This architecture allows us to develop different classes of summarization models which can extract sentences or words. We train our models on large scale corpora containing hundreds of thousands of document-summary pairs. Experimental results on two summari…
Toyota Technological Institute at Chicago（芝加哥丰田技术研究院）；University of Chicago（芝加哥大学）
Prior work on pretrained sentence embeddings and benchmarks focus on the capabilities of stand-alone sentences. We propose DiscoEval, a test suite of tasks to evaluate whether sentence representations include broader context information. We also propose a variety of training objectives that makes use of natural annotations from Wikipedia to build sentence encoders capable of modeling discourse. We benchmark sentence encoders pretrained with our proposed training objectives, as well as other popular pretrained sentence encoders on DiscoEval and other sentence evaluation tasks. Empirically, we s…
Pretrained text encoders, such as BERT, have been applied increasingly in various natural language processing (NLP) tasks, and have recently demonstrated significant performance gains. However, recent studies have demonstrated the existence of social bias in these pretrained NLP models. Although prior works have made progress on word-level debiasing, improved sentence-level fairness of pretrained encoders still lacks exploration. In this paper, we proposed the first neural debiasing method for a pretrained sentence encoder, which transforms the pretrained encoder outputs into debiased represen…
Indian Institute of Technology Kharagpur（印度理工学院卡哈拉格普尔分校）；Yahoo! India（雅虎印度）
This paper presents a novel two-stage framework to extract opinionated sentences from a given news article. In the first stage, Naive Bayes classifier by utilizing the local features assigns a score to each sentence - the score signifies the probability of the sentence to be opinionated. In the second stage, we use this prior within the HITS (Hyperlink-Induced Topic Search) schema to exploit the global structure of the article and relation between the sentences. In the HITS schema, the opinionated sentences are treated as Hubs and the facts around these opinions are treated as the Authorities.…
In this paper, we establish Fog Index (FI) as a text filter to locate the sentences in texts that contain connected biomedical concepts of interest. To do so, we have used 24 random papers each containing four pairs of connected concepts. For each pair, we categorize sentences based on whether they contain both, any or none of the concepts. We then use FI to measure difficulty of the sentences of each category and find that sentences containing both of the concepts have low readability. We rank sentences of a text according to their FI and select 30 percent of the most difficult sentences. We …
University of Science and Technology of China（中国科学技术大学）；Microsoft Research Asia（微软亚洲研究院）；Beijing University of Posts and Telecommunications（北京邮电大学）
The lack of labeled data is a major obstacle to learning high-quality sentence embeddings. Recently, self-supervised contrastive learning (SCL) is regarded as a promising way to address this problem. However, the existing works mainly rely on hand-crafted data annotation heuristics to generate positive training samples, which not only call for domain expertise and laborious tuning, but are also prone to the following unfavorable cases: 1) trivial positives, 2) coarse-grained positives, and 3) false positives. As a result, the self-supervision's quality can be severely limited in reality. In th…
MIT Computer Science and Artificial Intelligence Laboratory（麻省理工学院计算机科学与人工智能实验室）
Due to their similarity-based learning objectives, pretrained sentence encoders often internalize stereotypical assumptions that reflect the social biases that exist within their training corpora. In this paper, we describe several kinds of stereotypes concerning different communities that are present in popular sentence representation models, including pretrained next sentence prediction and contrastive sentence representation models. We compare such models to textual entailment models that learn language logic for a variety of downstream language understanding tasks. By comparing strong pret…
Classifying Dominant Temporal Orientation without Pretrained Text Embeddings: A Novel Morphosyntactic Inventory Vector Approach
Interdisciplinary Center for Innovative Theory and Empirics, Columbia University（哥伦比亚大学创新理论与实证跨学科中心）；Department of Sociology, Columbia University（哥伦比亚大学社会学系）
University of Tehran（德黑兰大学）；University of Rochester（罗切斯特大学）
Building systems with capability of natural language understanding (NLU) has been one of the oldest areas of AI. An essential component of NLU is to detect logical succession of events contained in a text. The task of sentence ordering is proposed to learn succession of events with applications in AI tasks. The performance of previous works employing statistical methods is poor, while the neural networks-based approaches are in serious need of large corpora for model learning. In this paper, we propose a method for sentence ordering which does not need a training phase and consequently a large…
Department of Computer Science and Engineering（计算机科学与工程系）；Ohio State University（俄亥俄州立大学）
Sentence pair modeling is critical for many NLP tasks, such as paraphrase identification, semantic textual similarity, and natural language inference. Most state-of-the-art neural models for these tasks rely on pretrained word embedding and compose sentence-level semantics in varied ways; however, few works have attempted to verify whether we really need pretrained embeddings in these tasks. In this paper, we study how effective subword-level (character and character n-gram) representations are in sentence pair modeling. Though it is well-known that subword models are effective in tasks with s…
University of Washington（华盛顿大学）；Allen Institute for Artificial Intelligence（艾伦人工智能研究院）
Representation learning for text via pretraining a language model on a large corpus has become a standard starting point for building NLP systems. This approach stands in contrast to autoencoders, also trained on raw text, but with the objective of learning to encode each input as a vector that allows full reconstruction. Autoencoders are attractive because of their latent space structure and generative properties. We therefore explore the construction of a sentence-level autoencoder from a pretrained, frozen transformer language model. We adapt the masked language modeling objective as a gene…
Transformer-based language models (LMs) pretrained on large text collections are proven to store a wealth of semantic knowledge. However, 1) they are not effective as sentence encoders when used off-the-shelf, and 2) thus typically lag behind conversationally pretrained (e.g., via response selection) encoders on conversational tasks such as intent detection (ID). In this work, we propose ConvFiT, a simple and efficient two-stage procedure which turns any pretrained LM into a universal conversational encoder (after Stage 1 ConvFiT-ing) and task-specialised sentence encoder (after Stage 2). We d…
Yangzhou University（扬州大学）；Hefei University of Technology（合肥工业大学）；Mininglamp Academy of Sciences（明略科学院）；Minininglamp Technology（明略科技）
Lexical simplification (LS) aims to replace complex words in a given sentence with their simpler alternatives of equivalent meaning. Recently unsupervised lexical simplification approaches only rely on the complex word itself regardless of the given sentence to generate candidate substitutions, which will inevitably produce a large number of spurious candidates. We present a simple LS approach that makes use of the Bidirectional Encoder Representations from Transformers (BERT) which can consider both the given sentence and the complex word during generating candidate substitutions for the comp…
The number of scientific articles has grown rapidly over the years and there are no signs that this growth will slow down in the near future. Because of this, it becomes increasingly difficult to keep up with the latest developments in a scientific field. To address this problem, we present here an approach to help researchers learn about the latest developments and findings by extracting in a normalized form core claims from scientific articles. This normalized representation is a controlled natural language of English sentences called AIDA, which has been proposed in previous work as a metho…
Institute for Advanced Studies in Basic Sciences (IASBS)（基础科学高级研究所）
Parallel data are an important part of a reliable Statistical Machine Translation (SMT) system. The more of these data are available, the better the quality of the SMT system. However, for some language pairs such as Persian-English, parallel sources of this kind are scarce. In this paper, a bidirectional method is proposed to extract parallel sentences from English and Persian document aligned Wikipedia. Two machine translation systems are employed to translate from Persian to English and the reverse after which an IR system is used to measure the similarity of the translated sentences. Addin…
Allen Institute for Artificial Intelligence（艾伦人工智能研究所）；Arrive Bio（Arrive Bio（阿里夫生物））
Prior work on controllable text generation has focused on learning how to control language models through trainable decoding, smart-prompt design, or fine-tuning based on a desired objective. We hypothesize that the information needed to steer the model to generate a target sentence is already encoded within the model. Accordingly, we explore a different approach altogether: extracting latent vectors directly from pretrained language model decoders without fine-tuning. Experiments show that there exist steering vectors, which, when added to the hidden states of the language model, generate a t…
Center for Information and Language Processing（信息与语言处理中心）；LMU Munich（慕尼黑大学）
To obtain high-quality sentence embeddings from pretrained language models (PLMs), they must either be augmented with additional pretraining objectives or finetuned on a large set of labeled text pairs. While the latter approach typically outperforms the former, it requires great human effort to generate suitable datasets of sufficient size. In this paper, we show how PLMs can be leveraged to obtain high-quality sentence embeddings without the need for labeled data, finetuning or modifications to the pretraining objective: We utilize the generative abilities of large and high-performing PLMs t…
Microsoft Research Asia（微软亚洲研究院）；Tencent Cloud Xiaowei（腾讯云小微）
Extractive methods have been proven effective in automatic document summarization. Previous works perform this task by identifying informative contents at sentence level. However, it is unclear whether performing extraction at sentence level is the best solution. In this work, we show that unnecessity and redundancy issues exist when extracting full sentences, and extracting sub-sentential units is a promising alternative. Specifically, we propose extracting sub-sentential units based on the constituency parsing tree. A neural extractive model which leverages the sub-sentential information and…
Indian Institute of Technology Madras（印度理工学院马德拉斯分校）
Authoring of OWL-DL ontologies is intellectually challenging and to make this process simpler, many systems accept natural language text as input. A text-based ontology authoring approach can be successful only when it is combined with an effective method for extracting ontological axioms from text. Extracting axioms from unrestricted English input is a substantially challenging task due to the richness of the language. Controlled natural languages (CNLs) have been proposed in this context and these tend to be highly restrictive. In this paper, we propose a new CNL called TEDEI (TExtual DEscri…
In English semantic similarity tasks, classic word embedding-based approaches explicitly model pairwise "interactions" between the word representations of a sentence pair. Transformer-based pretrained language models disregard this notion, instead modeling pairwise word interactions globally and implicitly through their self-attention mechanism. In this paper, we hypothesize that introducing an explicit, constrained pairwise word interaction mechanism to pretrained language models improves their effectiveness on semantic similarity tasks. We validate our hypothesis using BERT on four tasks in …
We advance the state of the art in biomolecular interaction extraction with three contributions: (i) We show that deep, Abstract Meaning Representations (AMR) significantly improve the accuracy of a biomolecular interaction extraction system when compared to a baseline that relies solely on surface- and syntax-based features; (ii) In contrast with previous approaches that infer relations on a sentence-by-sentence basis, we expand our framework to enable consistent predictions over sets of sentences (documents); (iii) We further modify and expand a graph kernel learning framework to enable conc…
Beihang University（北京航空航天大学）；Microsoft Research Asia（微软亚洲研究院）；Sun Yat-sen University（中山大学）；Peking University（北京大学）；Microsoft STC Asia（微软亚太研发集团）
Producing the embedding of a sentence in an unsupervised way is valuable to natural language matching and retrieval problems in practice. In this work, we conduct a thorough examination of pretrained model based unsupervised sentence embeddings. We study on four pretrained models and conduct massive experiments on seven datasets regarding sentence semantics. We have there main findings. First, averaging all tokens is better than only using [CLS] vector. Second, combining both top andbottom layers is better than only using top layers. Lastly, an easy whitening-based vector normalization strateg…
Pretrained language models such as BERT, GPT have shown great effectiveness in language understanding. The auxiliary predictive tasks in existing pretraining approaches are mostly defined on tokens, thus may not be able to capture sentence-level semantics very well. To address this issue, we propose CERT: Contrastive self-supervised Encoder Representations from Transformers, which pretrains language representation models using contrastive self-supervised learning at the sentence level. CERT creates augmentations of original sentences using back-translation. Then it finetunes a pretrained langu…
The biological literature is rich with sentences that describe causal relations. Methods that automatically extract such sentences can help biologists to synthesize the literature and even discover latent relations that had not been articulated explicitly. Current methods for extracting causal sentences are based on either machine learning or a predefined database of causal terms. Machine learning approaches require a large set of labeled training data and can be susceptible to noise. Methods based on predefined databases are limited by the quality of their curation and are unable to capture n…
This work presents our contribution in the context of the 6th task of SemEval-2020: Extracting Definitions from Free Text in Textbooks (DeftEval). This competition consists of three subtasks with different levels of granularity: (1) classification of sentences as definitional or non-definitional,(2) labeling of definitional sentences, and (3) relation classification. We use various pretrained language models (i.e., BERT, XLNet, RoBERTa, SciBERT, and ALBERT) to solve each of the three subtasks of the competition. Specifically, for each language model variant, we experiment by both freezing its …
Karlsruhe Institute of Technology (KIT)（卡尔斯鲁厄理工学院）
Argument search aims at identifying arguments in natural language texts. In the past, this task has been addressed by a combination of keyword search and argument identification on the sentence- or document-level. However, existing frameworks often address only specific components of argument search and do not address the following aspects: (1) argument-query matching: identifying arguments that frame the topic slightly differently than the actual search query; (2) argument identification: identifying arguments that consist of multiple sentences; (3) argument clustering: selecting retrieved ar…
