We propose a method for natural language generation, choosing the most representative output rather than the most likely output. By viewing the language generation process from the voting theory perspective, we define representativeness using range voting and a similarity measure. The proposed method can be applied when generating from any probabilistic language model, including n-gram models and neural network models. We evaluate different similarity measures on an image captioning task and a machine translation task, and show that our method generates longer and more diverse sentences, providing a solution to the common problem of short outputs being preferred over longer and more informative ones. The generated sentences obtain higher BLEU scores, particularly when the beam size is large. We also perform a human evaluation on both tasks and find that the outputs generated using our method are rated higher.
The Hong Kong Polytechnic University（香港理工大学）；Peking University（北京大学）
Unsupervised extractive summarization aims to extract salient sentences from a document as the summary without labeled data. Recent literatures mostly research how to leverage sentence similarity to rank sentences in the order of salience. However, sentence similarity estimation using pre-trained language models mostly takes little account of document-level information and has a weak correlation with sentence salience ranking. In this paper, we proposed two novel strategies to improve sentence similarity estimation for unsupervised extractive summarization. We use contrastive learning to optim…
Measuring Sentence Textual Similarity (STS) is a classic task that can be applied to many downstream NLP applications such as text generation and retrieval. In this paper, we focus on unsupervised STS that works on various domains but only requires minimal data and computational resources. Theoretically, we propose a light-weighted Expectation-Correction (EC) formulation for STS computation. EC formulation unifies unsupervised STS approaches including the cosine similarity of Additively Composed (AC) sentence embeddings, Optimal Transport (OT), and Tree Kernels (TK). Moreover, we propose the R…
University of Tehran（德黑兰大学）；Emory University（埃默里大学）
Text coherence is a fundamental problem in natural language generation and understanding. Organizing sentences into an order that maximizes coherence is known as sentence ordering. This paper is proposing a new approach based on the graph neural network approach to encode a set of sentences and learn orderings of short stories. We propose a new method for constructing sentence-entity graphs of short stories to create the edges between sentences and reduce noise in our graph by replacing the pronouns with their referring entities. We improve the sentence ordering by introducing an aggregation m…
Graph-based extractive document summarization relies on the quality of the sentence similarity graph. Bag-of-words or tf-idf based sentence similarity uses exact word matching, but fails to measure the semantic similarity between individual words or to consider the semantic structure of sentences. In order to improve the similarity measure between sentences, we employ off-the-shelf deep embedding features and tf-idf features, and introduce a new text similarity metric. An improved sentence similarity graph is built and used in a submodular objective function for extractive summarization, which…
University of Michigan（密歇根大学）；School of Information（信息学院）
We introduce a stochastic graph-based method for computing relative importance of textual units for Natural Language Processing. We test the technique on the problem of Text Summarization (TS). Extractive TS relies on the concept of sentence salience to identify the most important sentences in a document or set of documents. Salience is typically defined in terms of the presence of particular important words or in terms of similarity to a centroid pseudo-sentence. We consider a new approach, LexRank, for computing sentence importance based on the concept of eigenvector centrality in a graph re…
Unsupervised approaches to extractive summarization usually rely on a notion of sentence importance defined by the semantic similarity between a sentence and the document. We propose new metrics of relevance and redundancy using pointwise mutual information (PMI) between sentences, which can be easily computed by a pre-trained language model. Intuitively, a relevant sentence allows readers to infer the document content (high PMI with the document), and a redundant sentence can be inferred from the summary (high PMI with the summary). We then develop a greedy sentence selection algorithm to max…
CICS, University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校信息与计算机科学学院）
Most unsupervised NLP models represent each word with a single point or single region in semantic space, while the existing multi-sense word embeddings cannot represent longer word sequences like phrases or sentences. We propose a novel embedding method for a text sequence (a phrase or a sentence) where each sequence is represented by a distinct set of multi-mode codebook embeddings to capture different semantic facets of its meaning. The codebook embeddings can be viewed as the cluster centers which summarize the distribution of possibly co-occurring words in a pre-trained word embedding spac…
Calculating the semantic similarity between sentences is a long dealt problem in the area of natural language processing. The semantic analysis field has a crucial role to play in the research related to the text analytics. The semantic similarity differs as the domain of operation differs. In this paper, we present a methodology which deals with this issue by incorporating semantic similarity and corpus statistics. To calculate the semantic similarity between words and sentences, the proposed method follows an edge-based approach using a lexical database. The methodology can be applied in a v…
Shan-Si Elementary School（山寺小学）；University of Washington（华盛顿大学）
This paper describes a neural-network model which performed competitively (top 6) at the SemEval 2017 cross-lingual Semantic Textual Similarity (STS) task. Our system employs an attention-based recurrent neural network model that optimizes the sentence similarity. In this paper, we describe our participation in the multilingual STS task which measures similarity across English, Spanish, and Arabic.
Sentence encoders, which produce sentence embeddings using neural networks, are typically evaluated by how well they transfer to downstream tasks. This includes semantic similarity, an important task in natural language understanding. Although there has been much work dedicated to building sentence encoders, the accompanying transfer learning techniques have received relatively little attention. In this paper, we propose a transfer learning setting specialized for semantic similarity, which we refer to as direct network transfer. Through experiments on several standard text similarity datasets…
Measuring sentence similarity is a key research area nowadays as it allows machines to better understand human languages. In this paper, we proposed a Cross-Attention Siamese Network (CATsNet) to carry out the task of learning the semantic meanings of Chinese sentences and comparing the similarity between two sentences. This novel model is capable of catching non-local features. Additionally, we also tried to apply the long short-term memory (LSTM) network in the model to improve its performance. The experiments were conducted on the LCQMC dataset and the results showed that our model could ac…
Center for Information and Language Processing, LMU Munich（慕尼黑大学信息与语言处理中心）；Siemens AG（西门子股份公司）
We address the task of unsupervised Semantic Textual Similarity (STS) by ensembling diverse pre-trained sentence encoders into sentence meta-embeddings. We apply, extend and evaluate different meta-embedding methods from the word embedding literature at the sentence level, including dimensionality reduction (Yin and Schütze, 2016), generalized Canonical Correlation Analysis (Rastogi et al., 2015) and cross-view auto-encoders (Bollegala and Bao, 2018). Our sentence meta-embeddings set a new unsupervised State of The Art (SoTA) on the STS Benchmark and on the STS12-STS16 datasets, with gains of …
LIMSI, CNRS（法国国家科学研究中心机械与工程计算机科学实验室）；Univ. Paris Sud（巴黎第十一大学）；Université Paris-Saclay（巴黎-萨克雷大学）；LLF, CNRS（法国国家科学研究中心语言形式实验室）；Univ. Paris Diderot（巴黎狄德罗大学）
Usage similarity estimation addresses the semantic proximity of word instances in different contexts. We apply contextualized (ELMo and BERT) word and sentence embeddings to this task, and propose supervised models that leverage these representations for prediction. Our models are further assisted by lexical substitute annotations automatically assigned to word instances by context2vec, a neural model that relies on a bidirectional LSTM. We perform an extensive comparison of existing word and sentence representations on benchmark datasets addressing both graded and binary similarity. The best …
Chinese Academy of Sciences（中国科学院）；Zhejiang University（浙江大学）；Nanyang Technological University（南洋理工大学）；Peking University（北京大学）；Peng Cheng Laboratory（鹏城实验室）；ICT（中国科学院计算技术研究所）
Existing methods to measure sentence similarity are faced with two challenges: (1) labeled datasets are usually limited in size, making them insufficient to train supervised neural models; (2) there is a training-test gap for unsupervised language modeling (LM) based models to compute semantic scores between sentences, since sentence-level semantics are not explicitly modeled at training. This results in inferior performances in this task. In this work, we propose a new framework to address these two issues. The proposed framework is based on the core idea that the meaning of a sentence should…
IBM T.J. Watson Research Center（IBM T.J. Watson 研究中心）
Most conventional sentence similarity methods only focus on similar parts of two input sentences, and simply ignore the dissimilar parts, which usually give us some clues and semantic meanings about the sentences. In this work, we propose a model to take into account both the similarities and dissimilarities by decomposing and composing lexical semantics over sentences. The model represents each word as a vector, and calculates a semantic matching vector for each word based on all words in the other sentence. Then, each word vector is decomposed into a similar component and a dissimilar compon…
Japan Advanced Institute of Science and Technology (JAIST)（日本先进科学技术学院（JAIST））；Toshiba Research & Development Center, Japan（日本东芝研发中心）
Different word embedding models capture different aspects of linguistic properties. This inspired us to propose a model (M-MaxLSTM-CNN) for employing multiple sets of word embeddings for evaluating sentence similarity/relation. Representing each word by multiple word embeddings, the MaxLSTM-CNN encoder generates a novel sentence embedding. We then learn the similarity/relation between our sentence embeddings via Multi-level comparison. Our method M-MaxLSTM-CNN consistently shows strong performances in several tasks (i.e., measure textual similarity, identify paraphrase, recognize textual entai…
University of Toronto（多伦多大学）；University of Waterloo（滑铁卢大学）
Measuring sentence semantic similarity using pre-trained language models such as BERT generally yields unsatisfactory zero-shot performance, and one main reason is ineffective token aggregation methods such as mean pooling. In this paper, we demonstrate under a Bayesian framework that distance between primitive statistics such as the mean of word embeddings are fundamentally flawed for capturing sentence-level semantic similarity. To remedy this issue, we propose to learn a categorical variational autoencoder (VAE) based on off-the-shelf pre-trained language models. We theoretically prove that…
University of Southern California（南加州大学）；National University of Singapore（新加坡国立大学）
Word Mover's Distance (WMD) computes the distance between words and models text similarity with the moving cost between words in two text sequences. Yet, it does not offer good performance in sentence similarity evaluation since it does not incorporate word importance and fails to take inherent contextual and structural information in a sentence into account. An improved WMD method using the syntactic parse tree, called Syntax-aware Word Mover's Distance (SynWMD), is proposed to address these two shortcomings in this work. First, a weighted graph is built upon the word co-occurrence statistics…
Semantic Similarity between two sentences can be defined as a way to determine how related or unrelated two sentences are. The task of Semantic Similarity in terms of distributed representations can be thought to be generating sentence embeddings (dense vectors) which take both context and meaning of sentence in account. Such embeddings can be produced by multiple methods, in this paper we try to evaluate LSTM auto encoders for generating these embeddings. Unsupervised algorithms (auto encoders to be specific) just try to recreate their inputs, but they can be forced to learn order (and some i…
Determining the sentence similarity between Short Message Service (SMS) texts/sentences plays a significant role in mobile device industry. Gauging the similarity between SMS data is thus necessary for various applications like enhanced searching and navigation, clubbing together SMS of similar type when given a custom label or tag is provided by user irrespective of their sender etc. The problem faced with SMS data is its incomplete structure and grammatical inconsistencies. In this paper, we propose a unique pipeline for evaluating the text similarity between SMS texts. We use Part of Speech…
Université d’Avignon et des Pays de Vaucluse（阿维尼翁大学）；Universidade Federal do Ceará（塞阿拉联邦大学）；École Polytechnique de Montréal（蒙特利尔综合理工学院）
Semantic Textual Similarity (STS) is the basis of many applications in Natural Language Processing (NLP). Our system combines convolution and recurrent neural networks to measure the semantic similarity of sentences. It uses a convolution network to take account of the local context of words and an LSTM to consider the global context of sentences. This combination of networks helps to preserve the relevant information of sentences and improves the calculation of the similarity between sentences. Our model has achieved good results and is competitive with the best state-of-the-art systems.
In order to combat the COVID-19 pandemic, society can benefit from various natural language processing applications, such as dialog medical diagnosis systems and information retrieval engines calibrated specifically for COVID-19. These applications rely on the ability to measure semantic textual similarity (STS), making STS a fundamental task that can benefit several downstream applications. However, existing STS datasets and models fail to translate their performance to a domain-specific environment such as COVID-19. To overcome this gap, we introduce CORD19STS dataset which includes 13,710 a…
Toyota Technological Institute at Chicago（芝加哥丰田工业大学）
We present Charagram embeddings, a simple approach for learning character-based compositional models to embed textual sequences. A word or sentence is represented using a character n-gram count vector, followed by a single nonlinear transformation to yield a low-dimensional embedding. We use three tasks for evaluation: word similarity, sentence similarity, and part-of-speech tagging. We demonstrate that Charagram embeddings outperform more complex architectures based on character-level recurrent and convolutional neural networks, achieving new state-of-the-art performance on several similarity…
BACKGROUND: In this study, we investigated the efficacy of current state-of-the-art neural sentence embedding models for semantic similarity estimation of sentences from biomedical literature. We trained different neural embedding models on 1.7 million articles from the PubMed Open Access dataset, and evaluated them based on a biomedical benchmark set containing 100 sentence pairs annotated by human experts and a smaller contradiction subset derived from the original benchmark set. RESULTS: With a Pearson correlation of 0.819, our best unsupervised model based on the Paragraph Vector Distribut…
Semantically meaningful sentence embeddings are important for numerous tasks in natural language processing. To obtain such embeddings, recent studies explored the idea of utilizing synthetically generated data from pretrained language models (PLMs) as a training corpus. However, PLMs often generate sentences much different from the ones written by human. We hypothesize that treating all these synthetic examples equally for training deep neural networks can have an adverse effect on learning semantically meaningful embeddings. To analyze this, we first train a classifier that identifies machin…
This study is to review the approaches used for measuring sentences similarity. Measuring similarity between natural language sentences is a crucial task for many Natural Language Processing applications such as text classification, information retrieval, question answering, and plagiarism detection. This survey classifies approaches of calculating sentences similarity based on the adopted methodology into three categories. Word-to-word based, structure based, and vector-based are the most widely used approaches to find sentences similarity. Each approach measures relatedness between short tex…
Document alignment techniques based on multilingual sentence representations have recently shown state of the art results. However, these techniques rely on unsupervised distance measurement techniques, which cannot be fined-tuned to the task at hand. In this paper, instead of these unsupervised distance measurement techniques, we employ Metric Learning to derive task-specific distance measurements. These measurements are supervised, meaning that the distance measurement metric is trained using a parallel dataset. Using a dataset belonging to English, Sinhala, and Tamil, which belong to three …
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 …
In this paper we introduce vSTS, a new dataset for measuring textual similarity of sentences using multimodal information. The dataset is comprised by images along with its respectively textual captions. We describe the dataset both quantitatively and qualitatively, and claim that it is a valid gold standard for measuring automatic multimodal textual similarity systems. We also describe the initial experiments combining the multimodal information.
Measuring the semantic similarity between two sentences (or Semantic Textual Similarity - STS) is fundamental in many NLP applications. Despite the remarkable results in supervised settings with adequate labeling, little attention has been paid to this task in low-resource languages with insufficient labeling. Existing approaches mostly leverage machine translation techniques to translate sentences into rich-resource language. These approaches either beget language biases, or be impractical in industrial applications where spoken language scenario is more often and rigorous efficiency is requi…
Sri Lanka Institute of Information Technology（斯里兰卡信息技术学院）
Similarity is a comparative-subjective measure that varies with the domain within which it is considered. In several NLP applications such as document classification, pattern recognition, chatbot question-answering, sentiment analysis, etc., identifying an accurate similarity score for sentence pairs has become a crucial area of research. In the existing models that assess similarity, the limitation of effectively computing this similarity based on contextual comparisons, the localization due to the centering theory, and the lack of non-semantic textual comparisons have proven to be drawbacks.…
This study addresses the question whether visually grounded speech recognition (VGS) models learn to capture sentence semantics without access to any prior linguistic knowledge. We produce synthetic and natural spoken versions of a well known semantic textual similarity database and show that our VGS model produces embeddings that correlate well with human semantic similarity judgements. Our results show that a model trained on a small image-caption database outperforms two models trained on much larger databases, indicating that database size is not all that matters. We also investigate the i…
In this paper, we enhance the traditional confusion network system combination approach with an additional model trained by a neural network. This work is motivated by the fact that the commonly used binary system voting models only assign each input system a global weight which is responsible for the global impact of each input system on all translations. This prevents individual systems with low system weights from having influence on the system combination output, although in some situations this could be helpful. Further, words which have only been seen by one or few systems rarely have a …
Sentence similarity is considered the basis of many natural language tasks such as information retrieval, question answering and text summarization. The semantic meaning between compared text fragments is based on the words semantic features and their relationships. This article reviews a set of word and sentence similarity measures and compares them on benchmark datasets. On the studied datasets, results showed that hybrid semantic measures perform better than both knowledge and corpus based measures.
We advance a novel explanation of similarity-based interference effects in subject-verb and reflexive pronoun agreement processing, grounded in surprisal values computed from a pretrained large-scale Transformer model, GPT-2. Specifically, we show that surprisal of the verb or reflexive pronoun predicts facilitatory interference effects in ungrammatical sentences, where a distractor noun that matches in number with the verb or pronoun leads to faster reading times, despite the distractor not participating in the agreement relation. We review the human empirical evidence for such effects, inclu…
Sentence embedding methods using natural language inference (NLI) datasets have been successfully applied to various tasks. However, these methods are only available for limited languages due to relying heavily on the large NLI datasets. In this paper, we propose DefSent, a sentence embedding method that uses definition sentences from a word dictionary, which performs comparably on unsupervised semantics textual similarity (STS) tasks and slightly better on SentEval tasks than conventional methods. Since dictionaries are available for many languages, DefSent is more broadly applicable than met…
Harbin University（哈尔滨学院）；University of Washington（华盛顿大学）
This work improves monolingual sentence alignment for text simplification, specifically for text in standard and simple Wikipedia. We introduce a convolutional neural network structure to model similarity between two sentences. Due to the limitation of available parallel corpora, the model is trained in a semi-supervised way, by using the output of a knowledge-based high performance aligning system. We apply the resulting similarity score to rescore the knowledge-based output, and adapt the model by a small hand-aligned dataset. Experiments show that both rescoring and adaptation improve the p…
The University of Tokyo（东京大学）；Ochanomizu University（御茶水女子大学）；Artificial Intelligence Research Center, AIST（产业技术综合研究所人工智能研究中心）
Determining semantic textual similarity is a core research subject in natural language processing. Since vector-based models for sentence representation often use shallow information, capturing accurate semantics is difficult. By contrast, logical semantic representations capture deeper levels of sentence semantics, but their symbolic nature does not offer graded notions of textual similarity. We propose a method for determining semantic textual similarity by combining shallow features with features extracted from natural deduction proofs of bidirectional entailment relations between sentence …
Semantic textual similarity is one of the open research challenges in the field of Natural Language Processing. Extensive research has been carried out in this field and near-perfect results are achieved by recent transformer-based models in existing benchmark datasets like the STS dataset and the SICK dataset. In this paper, we study the sentences in these datasets and analyze the sensitivity of various word embeddings with respect to the complexity of the sentences. We build a complex sentences dataset comprising of 50 sentence pairs with associated semantic similarity values provided by 15 …
Previous works have demonstrated the effectiveness of utilising pre-trained sentence encoders based on their sentence representations for meaning comparison tasks. Though such representations are shown to capture hidden syntax structures, the direct similarity comparison between them exhibits weak sensitivity to word order and structural differences in given sentences. A single similarity score further makes the comparison process hard to interpret. Therefore, we here propose to combine sentence encoders with an alignment component by representing each sentence as a list of predicate-argument …
While the problem of hallucinations in neural machine translation has long been recognized, so far the progress on its alleviation is very little. Indeed, recently it turned out that without artificially encouraging models to hallucinate, previously existing methods fall short and even the standard sequence log-probability is more informative. It means that characteristics internal to the model can give much more information than we expect, and before using external models and measures, we first need to ask: how far can we go if we use nothing but the translation model itself ? We propose to u…
Low-resource languages, such as Baltic languages, benefit from Large Multilingual Models (LMs) that possess remarkable cross-lingual transfer performance capabilities. This work is an interpretation and analysis study into cross-lingual representations of Multilingual LMs. Previous works hypothesized that these LMs internally project representations of different languages into a shared cross-lingual space. However, the literature produced contradictory results. In this paper, we revisit the prior work claiming that "BERT is not an Interlingua" and show that different languages do converge to a…
The ALTA Institute（ALTA研究所）；Computer Laboratory（计算机实验室）；University of Cambridge（剑桥大学）
We investigate the task of assessing sentence-level prompt relevance in learner essays. Various systems using word overlap, neural embeddings and neural compositional models are evaluated on two datasets of learner writing. We propose a new method for sentence-level similarity calculation, which learns to adjust the weights of pre-trained word embeddings for a specific task, achieving substantially higher accuracy compared to other relevant baselines.
There have been many successful applications of sentence embedding methods. However, it has not been well understood what properties are captured in the resulting sentence embeddings depending on the supervision signals. In this paper, we focus on two types of sentence embedding methods with similar architectures and tasks: one fine-tunes pre-trained language models on the natural language inference task, and the other fine-tunes pre-trained language models on word prediction task from its definition sentence, and investigate their properties. Specifically, we compare their performances on sem…
Toyota Technological Institute at Chicago（芝加哥丰田理工学院）
We propose a generative model for a sentence that uses two latent variables, with one intended to represent the syntax of the sentence and the other to represent its semantics. We show we can achieve better disentanglement between semantic and syntactic representations by training with multiple losses, including losses that exploit aligned paraphrastic sentences and word-order information. We also investigate the effect of moving from bag-of-words to recurrent neural network modules. We evaluate our models as well as several popular pretrained embeddings on standard semantic similarity tasks a…
L3Cube-MahaSTS: A Marathi Sentence Similarity Dataset and Models
Pune Institute of Computer Technology（普那计算机技术学院）；Indian Institute of Technology Madras（印度理工学院马德拉斯分校）；MKSSS’ Cummins College of Engineering for Women（MKSSS’ 女子工程学院）；L3Cube Labs（L3Cube实验室）
