This paper is a write-up for the tutorial on "Fine-grained Interpretation and Causation Analysis in Deep NLP Models" that we are presenting at NAACL 2021. We present and discuss the research work on interpreting fine-grained components of a model from two perspectives, i) fine-grained interpretation, ii) causation analysis. The former introduces methods to analyze individual neurons and a group of neurons with respect to a language property or a task. The latter studies the role of neurons and input features in explaining decisions made by the model. We also discuss application of neuron analysis such as network manipulation and domain adaptation. Moreover, we present two toolkits namely NeuroX and Captum, that support functionalities discussed in this tutorial.
UT Austin（德克萨斯大学奥斯汀分校）；University of Michigan（密歇根大学）；Carnegie Mellon University（卡内基梅隆大学）；UC Berkeley（加州大学伯克利分校）；ICSI（国际计算机科学研究所）；NYU（纽约大学）；UC San Diego（加州大学圣地亚哥分校）
One weakness of machine-learned NLP models is that they typically perform poorly on out-of-domain data. In this work, we study the task of identifying products being bought and sold in online cybercrime forums, which exhibits particularly challenging cross-domain effects. We formulate a task that represents a hybrid of slot-filling information extraction and named entity recognition and annotate data from four different forums. Each of these forums constitutes its own "fine-grained domain" in that the forums cover different market sectors with different properties, even though all forums are i…
Performance prediction, the task of estimating a system's performance without performing experiments, allows us to reduce the experimental burden caused by the combinatorial explosion of different datasets, languages, tasks, and models. In this paper, we make two contributions to improving performance prediction for NLP tasks. First, we examine performance predictors not only for holistic measures of accuracy like F1 or BLEU but also fine-grained performance measures such as accuracy over individual classes of examples. Second, we propose methods to understand the reliability of a performance …
While there is increasing concern about the interpretability of neural models, the evaluation of interpretability remains an open problem, due to the lack of proper evaluation datasets and metrics. In this paper, we present a novel benchmark to evaluate the interpretability of both neural models and saliency methods. This benchmark covers three representative NLP tasks: sentiment analysis, textual similarity and reading comprehension, each provided with both English and Chinese annotated data. In order to precisely evaluate the interpretability, we provide token-level rationales that are caref…
Qatar Computing Research Institute, HBKU（哈马德·本·哈利法大学卡塔尔计算研究所）；Università di Bologna（博洛尼亚大学）
We present the shared task on Fine-Grained Propaganda Detection, which was organized as part of the NLP4IF workshop at EMNLP-IJCNLP 2019. There were two subtasks. FLC is a fragment-level task that asks for the identification of propagandist text fragments in a news article and also for the prediction of the specific propaganda technique used in each such fragment (18-way classification task). SLC is a sentence-level binary classification task asking to detect the sentences that contain propaganda. A total of 12 teams submitted systems for the FLC task, 25 teams did so for the SLC task, and 14 …
Broad-coverage meaning representations in NLP mostly focus on explicitly expressed content. More importantly, the scarcity of datasets annotating diverse implicit roles limits empirical studies into their linguistic nuances. For example, in the web review "Great service!", the provider and consumer are implicit arguments of different types. We examine an annotated corpus of fine-grained implicit arguments (Cui and Hershcovich, 2020) by carefully re-annotating it, resolving several inconsistencies. Subsequently, we present the first transition-based neural parser that can handle implicit argume…
Building Part-of-Speech (POS) taggers for code-mixed Indian languages is a particularly challenging problem in computational linguistics due to a dearth of accurately annotated training corpora. ICON, as part of its NLP tools contest has organized this challenge as a shared task for the second consecutive year to improve the state-of-the-art. This paper describes the POS tagger built at Surukam to predict the coarse-grained and fine-grained POS tags for three language pairs - Bengali-English, Telugu-English and Hindi-English, with the text spanning three popular social media platforms - Facebo…
While cultural backgrounds have been shown to affect linguistic expressions, existing natural language processing (NLP) research on culture modeling is overly coarse-grained and does not examine cultural differences among speakers of the same language. To address this problem and augment NLP models with cultural background features, we collect, annotate, manually validate, and benchmark EnCBP, a finer-grained news-based cultural background prediction dataset in English. Through language modeling (LM) evaluations and manual analyses, we confirm that there are noticeable differences in linguisti…
Detecting fine-grained differences in content conveyed in different languages matters for cross-lingual NLP and multilingual corpora analysis, but it is a challenging machine learning problem since annotation is expensive and hard to scale. This work improves the prediction and annotation of fine-grained semantic divergences. We introduce a training strategy for multilingual BERT models by learning to rank synthetic divergent examples of varying granularity. We evaluate our models on the Rationalized English-French Semantic Divergences, a new dataset released with this work, consisting of Engl…
Peking University（北京大学）；Harbin Institute of Technology（哈尔滨工业大学）；University of California, Santa Barbara（加州大学圣巴巴拉分校）
Building explainable systems is a critical problem in the field of Natural Language Processing (NLP), since most machine learning models provide no explanations for the predictions. Existing approaches for explainable machine learning systems tend to focus on interpreting the outputs or the connections between inputs and outputs. However, the fine-grained information is often ignored, and the systems do not explicitly generate the human-readable explanations. To better alleviate this problem, we propose a novel generative explanation framework that learns to make classification decisions and g…
China University of Petroleum (East China)（中国石油大学（华东））；Tsinghua University（清华大学）；Beijing National Research Center for Information Science and Technology（北京信息科学与技术国家研究中心）；Tsinghua Space Center（清华大学航天航空学院航天中心）；Linyi University（临沂大学）
Natural language processing (NLP) task has achieved excellent performance in many fields, including semantic understanding, automatic summarization, image recognition and so on. However, most of the neural network models for NLP extract the text in a fine-grained way, which is not conducive to grasp the meaning of the text from a global perspective. To alleviate the problem, the combination of the traditional statistical method and deep learning model as well as a novel model based on multi model nonlinear fusion are proposed in this paper. The model uses the Jaccard coefficient based on part …
Identifying semantically equivalent sentences is important for many cross-lingual and mono-lingual NLP tasks. Current approaches to semantic equivalence take a loose, sentence-level approach to "equivalence," despite previous evidence that fine-grained differences and implicit content have an effect on human understanding (Roth and Anthonio, 2021) and system performance (Briakou and Carpuat, 2021). In this work, we introduce a novel, more sensitive method of characterizing semantic equivalence that leverages Abstract Meaning Representation graph structures. We develop an approach, which can be…
Westlake University（西湖大学）；Westlake Institute for Advanced Study（西湖高等研究院）；Delft University of Technology（代尔夫特理工大学）；University College London（伦敦大学学院）
Understanding causality is key to the success of NLP applications, especially in high-stakes domains. Causality comes in various perspectives such as enable and prevent that, despite their importance, have been largely ignored in the literature. This paper introduces a novel fine-grained causal reasoning dataset and presents a series of novel predictive tasks in NLP, such as causality detection, event causality extraction, and Causal QA. Our dataset contains human annotations of 25K cause-effect event pairs and 24K question-answering pairs within multi-sentence samples, where each can have mul…
Brazilian Network Information Center (NIC.br)（巴西网络信息中心）；Mackenzie Presbyterian University（麦肯齐长老会大学）；Jusbrasil
Affective Computing is the study of how computers can recognize, interpret and simulate human affects. Sentiment Analysis is a common task inNLP related to this topic, but it focuses only on emotion valence (positive, negative, neutral). An emerging approach in NLP is Emotion Recognition, which relies on fined-grained classification. This research describes an approach to create a lexical-based weakly supervised corpus for fine-grained emotion in Portuguese. We evaluated our dataset by fine-tuning a transformer-based language model (BERT) and validating it on a Gold Standard annotated validati…
Fine-Grained Named Entity Typing (FG-NET) is a key component in Natural Language Processing (NLP). It aims at classifying an entity mention into a wide range of entity types. Due to a large number of entity types, distant supervision is used to collect training data for this task, which noisily assigns type labels to entity mentions irrespective of the context. In order to alleviate the noisy labels, existing approaches on FGNET analyze the entity mentions entirely independent of each other and assign type labels solely based on mention sentence-specific context. This is inadequate for highly …
ChiMDQA: Towards Comprehensive Chinese Document QA with Fine-grained Evaluation
Beijing Jiaotong University（北京交通大学）；Beijing University of Posts and Telecommunications（北京邮电大学）；Beijing University of Technology（北京理工大学）；Foxit Software Co. Ltd（Foxit软件有限公司）
We present SetExpander, a corpus-based system for expanding a seed set of terms into amore complete set of terms that belong to the same semantic class. SetExpander implements an iterative end-to-end workflow. It enables users to easily select a seed set of terms, expand it, view the expanded set, validate it, re-expand the validated set and store it, thus simplifying the extraction of domain-specific fine-grained semantic classes.SetExpander has been used successfully in real-life use cases including integration into an automated recruitment system and an issues and defects resolution system.…
EmoS: A High-Fidelity Multimodal Benchmark for Fine-grained Streaming Emotional Understanding
NLP（自然语言处理）；CT Lab, Department of Computer and Information Science, University of Macau（计算机与信息科学学院，澳门大学CT实验室）；School of Computer Science, Central China Normal University（Central China Normal University计算机科学学院）
Tongji University（同济大学）；Shanghai University of Electric Power（上海电力大学）
Story generation has emerged as an interesting yet challenging NLP task in recent years. Some existing studies aim at generating fluent and coherent stories from keywords and outlines; while others attempt to control the global features of the story, such as emotion, style and topic. However, these works focus on coarse-grained control on the story, neglecting control on the details of the story, which is also crucial for the task. To fill the gap, this paper proposes a model for fine-grained control on the story, which allows the generation of customized stories with characters, corresponding…
Interacting Minds Centre（互动心智中心）；Center for Humanities Computing Aarhus（奥胡斯人文计算中心）；Aarhus University（奥胡斯大学）；Department of Clinical Medicine（临床医学系）
Danish natural language processing (NLP) has in recent years obtained considerable improvements with the addition of multiple new datasets and models. However, at present, there is no coherent framework for applying state-of-the-art models for Danish. We present DaCy: a unified framework for Danish NLP built on SpaCy. DaCy uses efficient multitask models which obtain state-of-the-art performance on named entity recognition, part-of-speech tagging, and dependency parsing. DaCy contains tools for easy integration of existing models such as for polarity, emotion, or subjectivity detection. In add…
Veritas Technologies；Xerox Research Centre Europe（欧洲施乐研究院）；Accenture Centre for Innovation（埃森哲创新中心）
Understanding expressions of emotions in support forums has considerable value and NLP methods are key to automating this. Many approaches understandably use subjective categories which are more fine-grained than a straightforward polarity-based spectrum. However, the definition of such categories is non-trivial and, in fact, we argue for a need to incorporate communicative elements even beyond subjectivity. To support our position, we report experiments on a sentiment-labelled corpus of posts taken from a medical support forum. We argue that not only is a more fine-grained approach to text an…
FAID: Fine-Grained AI-Generated Text Detection Using Multi-Task Auxiliary and Multi-Level Contrastive Learning
BKAI Research Center, Hanoi University of Science and Technology（河内科学技术大学BKAI研究中心）；MBZUAI；INSAIT, Sofia University "St. Kliment Ohridski"（索菲亚大学"圣克莱门特·奥赫里德斯"INSAIT）
Carnegie Mellon University（卡内基梅隆大学）；University of Chicago（芝加哥大学）
Although models using contextual word embeddings have achieved state-of-the-art results on a host of NLP tasks, little is known about exactly what information these embeddings encode about the context words that they are understood to reflect. To address this question, we introduce a suite of probing tasks that enable fine-grained testing of contextual embeddings for encoding of information about surrounding words. We apply these tasks to examine the popular BERT, ELMo and GPT contextual encoders, and find that each of our tested information types is indeed encoded as contextual information ac…
Evaluating Neuron Interpretation Methods of NLP Models
The Chinese University of Hong Kong（香港中文大学）；Qatar Computing Research Institute, HBKU（卡塔尔计算研究所，哈马德·本·哈利法大学）；Faculty of Computer Science, Dalhousie University（达尔豪斯大学计算机科学学院）
Fine-Grained and Multi-Dimensional Metrics for Document-Level Machine Translation
Digital Twin Institute, Eastern Institute of Technology, Ningbo, China（数字孪生研究所，东部技术研究所，宁波，中国）；Saarland University（萨尔兰州大学）；Department of Computing, The Hong Kong Polytechnic University（计算系，香港理工大学）；The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））
Tsinghua University（清华大学）；Alibaba Group（阿里巴巴集团）；Seoul National University（首尔国立大学）
As an effective approach to tune pre-trained language models (PLMs) for specific tasks, prompt-learning has recently attracted much attention from researchers. By using \textit{cloze}-style language prompts to stimulate the versatile knowledge of PLMs, prompt-learning can achieve promising results on a series of NLP tasks, such as natural language inference, sentiment classification, and knowledge probing. In this work, we investigate the application of prompt-learning on fine-grained entity typing in fully supervised, few-shot and zero-shot scenarios. We first develop a simple and effective p…
Improving Few-shot and Zero-shot Entity Linking with Coarse-to-Fine Lexicon-based Retriever
Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳））；Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies（广东省新型安全智能技术重点实验室）；Central South University（中南大学）
The growth of cross-lingual pre-trained models has enabled NLP tools to rapidly generalize to new languages. While these models have been applied to tasks involving entities, their ability to explicitly predict typological features of these entities across languages has not been established. In this paper, we present a unified cross-lingual fine-grained entity typing model capable of handling over 100 languages and analyze this model's ability to generalize to languages and entities unseen during training. We train this model on cross-lingual training data collected from Wikipedia hyperlinks i…
While sadness is a human emotion that people experience at certain times throughout their lives, inflicting them with emotional disappointment and pain, depression is a longer term mental illness which impairs social, occupational, and other vital regions of functioning making it a much more serious issue and needs to be catered to at the earliest. NLP techniques can be utilized for the detection and subsequent diagnosis of these emotions. Most of the open sourced data on the web deal with sadness as a part of depression, as an emotion even though the difference in severity of both is huge. Th…
Computer vision has benefited from initializing multiple deep layers with weights pretrained on large supervised training sets like ImageNet. Natural language processing (NLP) typically sees initialization of only the lowest layer of deep models with pretrained word vectors. In this paper, we use a deep LSTM encoder from an attentional sequence-to-sequence model trained for machine translation (MT) to contextualize word vectors. We show that adding these context vectors (CoVe) improves performance over using only unsupervised word and character vectors on a wide variety of common NLP tasks: se…
Automated Data Enrichment using Confidence-Aware Fine-Grained Debate among Open-Source LLMs for Mental Health and Online Safety
University of Southampton, UK（英国南安普顿大学）；Queen Mary University of London, UK（伦敦大学玛丽女王学院）；The Alan Turing Institute, UK（阿兰·图灵研究所）；Bar Ilan University, Israel（巴伊兰大学）
