Temporal Embeddings and Transformer Models for Narrative Text Understanding
Istituto Dalle Molle di Studi sull’Intelligenza Artificiale (IDSIA)（达莱莫勒人工智能研究所）
Vani K, Simone Mellace, Alessandro Antonucci
备注：
Presented at the Third International Workshop on Narrative Extraction from Texts (Text2Story 2020) held in conjunction with the 42nd European Conference on Information Retrieval
We present two deep learning approaches to narrative text understanding for character relationship modelling. The temporal evolution of these relations is described by dynamic word embeddings, that are designed to learn semantic changes over time. An empirical analysis of the corresponding character trajectories shows that such approaches are effective in depicting dynamic evolution. A supervised learning approach based on the state-of-the-art transformer model BERT is used instead to detect static relations between characters. The empirical validation shows that such events (e.g., two characters belonging to the same family) might be spotted with good accuracy, even when using automatically annotated data. This provides a deeper understanding of narrative plots based on the identification of key facts. Standard clustering techniques are finally used for character de-aliasing, a necessary pre-processing step for both approaches. Overall, deep learning models appear to be suitable for narrative text understanding, while also providing a challenging and unexploited benchmark for general natural language understanding.
University of Washington（华盛顿大学）；Allen Institute for Artificial Intelligence（艾伦人工智能研究所）
Human understanding of narrative texts requires making commonsense inferences beyond what is stated explicitly in the text. A recent model, COMET, can generate such implicit commonsense inferences along several dimensions such as pre- and post-conditions, motivations, and mental states of the participants. However, COMET was trained on commonsense inferences of short phrases, and is therefore discourse-agnostic. When presented with each sentence of a multi-sentence narrative, it might generate inferences that are inconsistent with the rest of the narrative. We present the task of discourse-awa…
Image narrative generation is a task to create a story from an image with a subjective viewpoint. Given the importance of the subjective feelings of writers, readers, and characters in storytelling, an image narrative generation method should consider human emotion. In this study, we propose a novel method of image narrative generation called ViNTER (Visual Narrative Transformer with Emotion arc Representation), which takes "emotion arc" as input to capture a sequence of emotional changes. Since emotion arcs represent the trajectory of emotional change, it is expected that we can include detai…
Stanford University（斯坦福大学）；Agency for Science, Technology and Research（新加坡科技研究局）；National University of Singapore（新加坡国立大学）
Attention mechanisms in deep neural networks have achieved excellent performance on sequence-prediction tasks. Here, we show that these recently-proposed attention-based mechanisms---in particular, the Transformer with its parallelizable self-attention layers, and the Memory Fusion Network with attention across modalities and time---also generalize well to multimodal time-series emotion recognition. Using a recently-introduced dataset of emotional autobiographical narratives, we adapt and apply these two attention mechanisms to predict emotional valence over time. Our models perform extremely …
Recent advances in text-to-image synthesis have led to large pretrained transformers with excellent capabilities to generate visualizations from a given text. However, these models are ill-suited for specialized tasks like story visualization, which requires an agent to produce a sequence of images given a corresponding sequence of captions, forming a narrative. Moreover, we find that the story visualization task fails to accommodate generalization to unseen plots and characters in new narratives. Hence, we first propose the task of story continuation, where the generated visual story is condi…
University of Copenhagen（哥本哈根大学）；Pioneer Centre for AI（先锋人工智能中心）；Technical University of Denmark（丹麦技术大学）；Cornell University（康奈尔大学）
Social media platforms give rise to an abundance of posts and comments on every topic imaginable. Many of these posts express opinions on various aspects of society, but their unfalsifiable nature makes them ill-suited to fact-checking pipelines. In this work, we aim to distill such posts into a small set of narratives that capture the essential claims related to a given topic. Understanding and visualizing these narratives can facilitate more informed debates on social media. As a first step towards systematically identifying the underlying narratives on social media, we introduce PAPYER, a f…
Biomedical word embeddings are usually pre-trained on free text corpora with neural methods that capture local and global distributional properties. They are leveraged in downstream tasks using various neural architectures that are designed to optimize task-specific objectives that might further tune such embeddings. Since 2018, however, there is a marked shift from these static embeddings to contextual embeddings motivated by language models (e.g., ELMo, transformers such as BERT, and ULMFiT). These dynamic embeddings have the added benefit of being able to distinguish homonyms and acronyms g…
We consider the problem of embedding character-entity relationships from the reduced semantic space of narratives, proposing and evaluating the assumption that these relationships hold under a reflection operation. We analyze this assumption and compare the approach to a baseline state-of-the-art model with a unique evaluation that simulates efficacy on a downstream clustering task with human-created labels. Although our model creates clusters that achieve Silhouette scores of -.084, outperforming the baseline -.227, our analysis reveals that the models approach the task much differently and p…
Digital Humanities Colab（数字人文合作实验室）；Integrated Program for Humane Studies（人文研究综合项目）；Kenyon College（凯尼恩学院）
SOTA Transformer and DNN short text sentiment classifiers report over 97% accuracy on narrow domains like IMDB movie reviews. Real-world performance is significantly lower because traditional models overfit benchmarks and generalize poorly to different or more open domain texts. This paper introduces SentimentArcs, a new self-supervised time series sentiment analysis methodology that addresses the two main limitations of traditional supervised sentiment analysis: limited labeled training datasets and poor generalization. A large ensemble of diverse models provides a synthetic ground truth for …
This papers revisits the receptive theory in context of computational creativity. It presents a case study of a Paranoid Transformer - a fully autonomous text generation engine with raw output that could be read as the narrative of a mad digital persona without any additional human post-filtering. We describe technical details of the generative system, provide examples of output and discuss the impact of receptive theory, chance discovery and simulation of fringe mental state on the understanding of computational creativity.
University of Florida（佛罗里达大学）；Weill Cornell Medicine（威尔康奈尔医学院）
Social and behavioral determinants of health (SBDoH) have important roles in shaping people's health. In clinical research studies, especially comparative effectiveness studies, failure to adjust for SBDoH factors will potentially cause confounding issues and misclassification errors in either statistical analyses and machine learning-based models. However, there are limited studies to examine SBDoH factors in clinical outcomes due to the lack of structured SBDoH information in current electronic health record (EHR) systems, while much of the SBDoH information is documented in clinical narrati…
Stanford University（斯坦福大学）；University of California San Diego（加州大学圣地亚哥分校）
Word embedding models such as GloVe are widely used in natural language processing (NLP) research to convert words into vectors. Here, we provide a preliminary guide to probe latent emotions in text through GloVe word vectors. First, we trained a neural network model to predict continuous emotion valence ratings by taking linguistic inputs from Stanford Emotional Narratives Dataset (SEND). After interpreting the weights in the model, we found that only a few dimensions of the word vectors contributed to expressing emotions in text, and words were clustered on the basis of their emotional polar…
Multi-Level Narrative Evaluation Outperforms Lexical Features for Mental Health
Institute for Artificial Intelligence（人工智能研究院）；School of Psychological and Cognitive Sciences（心理学与认知科学学院）；School of Intelligence Science and Technology（智能科学与技术学院）；State Key Laboratory of General AI（通用人工智能国家重点实验室）；Beijing Key Laboratory of Behavior and Mental Health（北京行为与心理健康重点实验室）；PKU-Changsha Institute for Computing and Digital Economy（北京大学长沙计算与数字经济研究院）
The problem of determining if a military unit has correctly understood an order and is properly executing on it is one that has bedeviled military planners throughout history. The advent of advanced language models such as OpenAI's GPT-series offers new possibilities for addressing this problem. This paper presents a mechanism to harness the narrative output of large language models and produce diagrams or "maps" of the relationships that are latent in the weights of such models as the GPT-3. The resulting "Neural Narrative Maps" (NNMs), are intended to provide insight into the organization of…
Telefonica Research（西班牙电信研究中心）；Universitat Politecnica de Catalunya (UPC)（加泰罗尼亚理工大学（UPC））
In this work, we propose an effective approach for training unique embedding representations by combining three simultaneous modalities: image and spoken and textual narratives. The proposed methodology departs from a baseline system that spawns a embedding space trained with only spoken narratives and image cues. Our experiments on the EPIC-Kitchen and Places Audio Caption datasets show that introducing the human-generated textual transcriptions of the spoken narratives helps to the training procedure yielding to get better embedding representations. The triad speech, image and words allows f…
In modern NLP applications, word embeddings are a crucial backbone that can be readily shared across a number of tasks. However as the text distributions change and word semantics evolve over time, the downstream applications using the embeddings can suffer if the word representations do not conform to the data drift. Thus, maintaining word embeddings to be consistent with the underlying data distribution is a key problem. In this work, we tackle this problem and propose TransDrift, a transformer-based prediction model for word embeddings. Leveraging the flexibility of transformer, our model a…
The Hong Kong University of Science and Technology（香港科技大学）
One of the current state-of-the-art multilingual document embedding model LASER is based on the bidirectional LSTM neural machine translation model. This paper presents a transformer-based sentence/document embedding model, T-LASER, which makes three significant improvements. Firstly, the BiLSTM layers is replaced by the attention-based transformer layers, which is more capable of learning sequential patterns in longer texts. Secondly, due to the absence of recurrence, T-LASER enables faster parallel computations in the encoder to generate the text embedding. Thirdly, we augment the NMT transl…
Tsinghua University（清华大学）；Guangdong OPPO Mobile Telecommunications Corp., Ltd.（广东OPPO移动通信有限公司）；NetEase Inc.（网易公司）
Despite advances in generating fluent texts, existing pretraining models tend to attach incoherent event sequences to involved entities when generating narratives such as stories and news. We conjecture that such issues result from representing entities as static embeddings of superficial words, while neglecting to model their ever-changing states, i.e., the information they carry, as the text unfolds. Therefore, we extend the Transformer model to dynamically conduct entity state updates and sentence realization for narrative generation. We propose a contrastive framework to learn the state re…
Transformers have been widely applied in text classification. Unfortunately, real-world data contain anomalies and noisy labels that cause challenges for state-of-art Transformers. This paper proposes Protoformer, a novel self-learning framework for Transformers that can leverage problematic samples for text classification. Protoformer features a selection mechanism for embedding samples that allows us to efficiently extract and utilize anomalies prototypes and difficult class prototypes. We demonstrated such capabilities on datasets with diverse textual structures (e.g., Twitter, IMDB, ArXiv)…
In this paper, our main contributions are that embeddings from relatively smaller corpora can outperform ones from larger corpora and we make the new Swedish analogy test set publicly available. To achieve a good network performance in natural language processing (NLP) downstream tasks, several factors play important roles: dataset size, the right hyper-parameters, and well-trained embeddings. We show that, with the right set of hyper-parameters, good network performance can be reached even on smaller datasets. We evaluate the embeddings at both the intrinsic and extrinsic levels. The embeddin…
University of California-Los Angeles（加州大学洛杉矶分校）；UCLA Fielding School of Public Health（加州大学洛杉矶分校菲尔丁公共卫生学院）
There is an escalating need for methods to identify latent patterns in text data from many domains. We introduce a new method to identify topics in a corpus and represent documents as topic sequences. Discourse Atom Topic Modeling draws on advances in theoretical machine learning to integrate topic modeling and word embedding, capitalizing on the distinct capabilities of each. We first identify a set of vectors ("discourse atoms") that provide a sparse representation of an embedding space. Atom vectors can be interpreted as latent topics: Through a generative model, atoms map onto distribution…
We propose a VAE for Transformers by developing a variational information bottleneck regulariser for Transformer embeddings. We formalise the embedding space of Transformer encoders as mixture probability distributions, and use Bayesian nonparametrics to derive a nonparametric variational information bottleneck (NVIB) for such attention-based embeddings. The variable number of mixture components supported by nonparametric methods captures the variable number of vectors supported by attention, and the exchangeability of our nonparametric distributions captures the permutation invariance of atte…
When coping with literary texts such as novels or short stories, the extraction of structured information in the form of a knowledge graph might be hindered by the huge number of possible relations between the entities corresponding to the characters in the novel and the consequent hurdles in gathering supervised information about them. Such issue is addressed here as an unsupervised task empowered by transformers: relational sentences in the original text are embedded (with SBERT) and clustered in order to merge together semantically similar relations. All the sentences in the same cluster ar…
Transformer visualization via dictionary learning: contextualized embedding as a linear superposition of transformer factors
Facebook AI Research（脸书人工智能研究院）；Berkeley AI Research (BAIR), UC Berkeley（加州大学伯克利分校伯克利人工智能研究院（BAIR））；New York University（纽约大学）；Redwood Center for Theoretical Neuroscience, UC Berkeley（加州大学伯克利分校雷德伍德理论神经科学中心）
International Institute of Information Technology - Hyderabad (IIIT-Hyderabad)（海得拉巴国际信息技术学院（IIIT-Hyderabad））
Code-mixing(CM) is a frequently observed phenomenon that uses multiple languages in an utterance or sentence. CM is mostly practiced on various social media platforms and in informal conversations. Sentiment analysis (SA) is a fundamental step in NLP and is well studied in the monolingual text. Code-mixing adds a challenge to sentiment analysis due to its non-standard representations. This paper proposes a meta embedding with a transformer method for sentiment analysis on the Dravidian code-mixed dataset. In our method, we used meta embeddings to capture rich text representations. We used the …
Carnegie Mellon University（卡内基梅隆大学）；University of California San Diego（加州大学圣地亚哥分校）
Semantic sentence embedding models encode natural language sentences into vectors, such that closeness in embedding space indicates closeness in the semantics between the sentences. Bilingual data offers a useful signal for learning such embeddings: properties shared by both sentences in a translation pair are likely semantic, while divergent properties are likely stylistic or language-specific. We propose a deep latent variable model that attempts to perform source separation on parallel sentences, isolating what they have in common in a latent semantic vector, and explaining what is left ove…
We look at how machine learning techniques that derive properties of items in a collection of independent media can be used to automatically embed stories into such collections. To do so, we use models that extract the tempo of songs to make a music playlist follow a narrative arc. Our work specifies an open-source tool that uses pre-trained neural network models to extract the global tempo of a set of raw audio files and applies these measures to create a narrative-following playlist. This tool is available at https://github.com/dylanashley/playlist-story-builder/releases/tag/v1.0.0
Glasgow Caledonian University（格拉斯哥卡里多尼亚大学）；University of the West of Scotland（西苏格兰大学）；Lay Summaries Ltd（Lay Summaries 有限公司）；University of Edinburgh（爱丁堡大学）
Summarisation of research results in plain language is crucial for promoting public understanding of research findings. The use of Natural Language Processing to generate lay summaries has the potential to relieve researchers' workload and bridge the gap between science and society. The aim of this narrative literature review is to describe and compare the different text summarisation approaches used to generate lay summaries. We searched the databases Web of Science, Google Scholar, IEEE Xplore, Association for Computing Machinery Digital Library and arXiv for articles published until 6 May 2…
Singapore University of Technology and Design（新加坡科技设计大学）；ProQod Singapore（新加坡ProQod公司）
Classification of crisis events, such as natural disasters, terrorist attacks and pandemics, is a crucial task to create early signals and inform relevant parties for spontaneous actions to reduce overall damage. Despite crisis such as natural disasters can be predicted by professional institutions, certain events are first signaled by civilians, such as the recent COVID-19 pandemics. Social media platforms such as Twitter often exposes firsthand signals on such crises through high volume information exchange over half a billion tweets posted daily. Prior works proposed various crisis embeddin…
Automatic understanding of domain specific texts in order to extract useful relationships for later use is a non-trivial task. One such relationship would be between railroad accidents' causes and their correspondent descriptions in reports. From 2001 to 2016 rail accidents in the U.S. cost more than $4.6B. Railroads involved in accidents are required to submit an accident report to the Federal Railroad Administration (FRA). These reports contain a variety of fixed field entries including primary cause of the accidents (a coded variable with 389 values) as well as a narrative field which is a …
