Multitask Learning of Negation and Speculation using Transformers

Khandelwal, Aditya; Britto, Benita Kathleen

doi:10.18653/v1/2020.louhi-1.9

Cited by 16 publications

(14 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hence, in future work, we plan to experiment with multitask learning approaches [127,128] to take advantage of existing similar resources such as FiQA [83], SentiFM [88], and Finan-cialPhrasebank [80]. Regarding modeling approaches, we plan to include syntax-level [129,130] and external sentiment resources by information fusion [131] because lexical feature learning is currently not sufficient for implicit fine-grained triplet extraction.…”

Section: Discussionmentioning

confidence: 99%

Fine-Grained Implicit Sentiment in Financial News: Uncovering Hidden Bulls and Bears

Jacobs

Hoste

2021

Electronics

View full text Add to dashboard Cite

The field of sentiment analysis is currently dominated by the detection of attitudes in lexically explicit texts such as user reviews and social media posts. In objective text genres such as economic news, indirect expressions of sentiment are common. Here, a positive or negative attitude toward an entity must be inferred from connotational or real-world knowledge. To capture all expressions of subjectivity, a need exists for fine-grained resources and approaches for implicit sentiment analysis. We present the SENTiVENT corpus of English business news that contains token-level annotations for target spans, polar spans, and implicit polarity (positive, negative, or neutral investor sentiment, respectively). We both directly annotate polar expressions and induce them from existing schema-based event annotations to obtain event-implied implicit sentiment tuples. This results in a large dataset of 12,400 sentiment–target tuples in 288 fully annotated articles. We validate the created resource with an inter-annotator agreement study and a series of coarse- to fine-grained supervised deep-representation-learning experiments. Agreement scores show that our annotations are of substantial quality. The coarse-grained experiments involve classifying the positive, negative, and neutral polarity of known polar expressions and, in clause-based experiments, the detection of positive, negative, neutral, and no-polarity clauses. The gold coarse-grained experiments obtain decent performance (76% accuracy and 63% macro-F1) and clause-based detection shows decreased performance (65% accuracy and 57% macro-F1) with the confusion of neutral and no-polarity. The coarse-grained results demonstrate the feasibility of implicit polarity classification as operationalized in our dataset. In the fine-grained experiments, we apply the grid tagging scheme unified model for <polar span, target span, polarity> triplet extraction, which obtains state-of-the-art performance on explicit sentiment in user reviews. We observe a drop in performance on our implicit sentiment corpus compared to the explicit benchmark (22% vs. 76% F1). We find that the current models for explicit sentiment are not directly portable to our implicit task: the larger lexical variety within implicit opinion expressions causes lexical data scarcity. We identify common errors and discuss several recommendations for implicit fine-grained sentiment analysis. Data and source code are available.

show abstract

Section: Discussionmentioning

confidence: 99%

Fine-Grained Implicit Sentiment in Financial News: Uncovering Hidden Bulls and Bears

Jacobs

Hoste

2021

Electronics

View full text Add to dashboard Cite

show abstract

“…Supervised ML-based solutions such as the LSM Network (Zhao et al, 2021) have learned negative terms while performing sentiment mining automatically from large-scale training data. The current state-of-the-art method, NegBert, is based on ML (Khandelwal and Sawant, 2020;Khandelwal and Britto, 2020). Although this ML approach is the current state-of-the-art, the challenge in using ML approaches is the need for time-consuming labeling of large amounts of training data.…”

Section: Existing Approaches To Negation Detectionmentioning

confidence: 99%

Erforschung von Bewegungsbeschreibungen durch geovisuelle Analytik

Pezanowski

Mitra

MacEachren

2022

KN J. Cartogr. Geogr. Inf.

View full text Add to dashboard Cite

Sensemaking using automatically extracted information from text is a challenging problem. In this paper, we address a specific type of information extraction, namely extracting information related to descriptions of movement. Aggregating and understanding information related to descriptions of movement and lack of movement specified in text can lead to an improved understanding and sensemaking of movement phenomena of various types, e.g., migration of people and animals, impediments to travel due to COVID-19, etc. We present GeoMovement, a system that is based on combining machine learning and rule-based extraction of movement-related information with state-of-the-art visualization techniques. Along with the depiction of movement, our tool can extract and present a lack of movement. Very little prior work exists on automatically extracting descriptions of movement, especially negation and movement. Apart from addressing these, GeoMovement also provides a novel integrated framework for combining these extraction modules with visualization. We include two systematic case studies of GeoMovement that show how humans can derive meaningful geographic movement information. GeoMovement can complement precise movement data, e.g., obtained using sensors, or be used by itself when precise data is unavailable. Supplementary Information The online version contains supplementary material available at 10.1007/s42489-022-00098-3.

show abstract

“…Qian et al [36] proposed a Convolutional Neural Network-based model to address speculation and negation scope detection. Recently, Khandelwal and Britto [37] utilized transformer-based architectures such as BERT, XLNet, and RoBERTa to detect negation and speculation.…”

Section: Spanish Corporamentioning

confidence: 99%

Negation Detection on Mexican Spanish Tweets: The T-MexNeg Corpus

et al. 2021

View full text Add to dashboard Cite

In this paper, we introduce the T-MexNeg corpus of Tweets written in Mexican Spanish. It consists of 13,704 Tweets, of which 4895 contain negation structures. We performed an analysis of negation statements embedded in the language employed on social media. This research paper aims to present the annotation guidelines along with a novel resource targeted at the negation detection task. The corpus was manually annotated with labels of negation cue, scope, and, event. We report the analysis of the inter-annotator agreement for all the components of the negation structure. This resource is freely available. Furthermore, we performed various experiments to automatically identify negation using the T-MexNeg corpus and the SFU ReviewSP-NEG for training a machine learning algorithm. By comparing two different methodologies, one based on a dictionary and the other based on the Conditional Random Fields algorithm, we found that the results of negation identification on Twitter are lower when the model is trained on the SFU ReviewSP-NEG Corpus. Therefore, this paper shows the importance of having resources built specifically to deal with social media language.

show abstract

Multitask Learning of Negation and Speculation using Transformers

Cited by 16 publications

References 13 publications

Fine-Grained Implicit Sentiment in Financial News: Uncovering Hidden Bulls and Bears

Fine-Grained Implicit Sentiment in Financial News: Uncovering Hidden Bulls and Bears

Erforschung von Bewegungsbeschreibungen durch geovisuelle Analytik

Negation Detection on Mexican Spanish Tweets: The T-MexNeg Corpus

Contact Info

Product

Resources

About