This paper reports our submission under the team name ‘SynthDetectives’ to the ALTA 2023 Shared Task. We use a stacking ensemble of Transformers for the task of AI-generated text detection. Our approach is novel in terms of its choice of models in that we use accessible and lightweight models in the ensemble. We show that ensembling the models results in an improved accuracy in comparison with using them individually. Our approach achieves an accuracy score of 0.9555 on the official test data provided by the shared task organisers.

This paper describes the system architectures and the models submitted by our team “IISERB Brains” to SemEval 2022 Task 6 competition. We contested for all three sub-tasks floated for the English dataset. On the leader-board, we got 19th rank out of 43 teams for sub-task A, 8th rank out of 22 teams for sub-task B, and 13th rank out of 16 teams for sub-task C. Apart from the submitted results and models, we also report the other models and results that we obtained through our experiments after organizers published the gold labels of their evaluation data. All of our code and links to additional resources are present in GitHub for reproducibility.

While fine-tuning pre-trained models for downstream classification is the conventional paradigm in NLP, often task-specific nuances may not get captured in the resultant models. Specifically, for tasks that take two inputs and require the output to be invariant of the order of the inputs, inconsistency is often observed in the predicted labels or confidence scores. We highlight this model shortcoming and apply a consistency loss function to alleviate inconsistency in symmetric classification. Our results show an improved consistency in predictions for three paraphrase detection datasets without a significant drop in the accuracy scores. We examine the classification performance of six datasets (both symmetric and non-symmetric) to showcase the strengths and limitations of our approach.

Cross-domain sentiment analysis (CDSA) helps to address the problem of data scarcity in scenarios where labelled data for a domain (known as the target domain) is unavailable or insufficient. However, the decision to choose a domain (known as the source domain) to leverage from is, at best, intuitive. In this paper, we investigate text similarity metrics to facilitate source domain selection for CDSA. We report results on 20 domains (all possible pairs) using 11 similarity metrics. Specifically, we compare CDSA performance with these metrics for different domain-pairs to enable the selection of a suitable source domain, given a target domain. These metrics include two novel metrics for evaluating domain adaptability to help source domain selection of labelled data and utilize word and sentence-based embeddings as metrics for unlabelled data. The goal of our experiments is a recommendation chart that gives the K best source domains for CDSA for a given target domain. We show that the best K source domains returned by our similarity metrics have a precision of over 50%, for varying values of K.

One of the most common metrics to automatically evaluate opinion summaries is ROUGE, a metric developed for text summarisation. ROUGE counts the overlap of word or word units between a candidate summary against reference summaries. This formulation treats all words in the reference summary equally. In opinion summaries, however, not all words in the reference are equally important. Opinion summarisation requires to correctly pair two types of semantic information: (1) aspect or opinion target; and (2) polarity of candidate and reference summaries. We investigate the suitability of ROUGE for evaluating opin-ion summaries of online reviews. Using three simulation-based experiments, we evaluate the behaviour of ROUGE for opinion summarisation on the ability to match aspect and polarity. We show that ROUGE cannot distinguish opinion summaries of similar or opposite polarities for the same aspect. Moreover,ROUGE scores have significant variance under different configuration settings. As a result, we present three recommendations for future work that uses ROUGE to evaluate opinion summarisation.

Multi-Task Learning (MTL) has been an attractive approach to deal with limited labeled datasets or leverage related tasks, for a variety of NLP problems. We examine the benefit of MTL for three specific pairs of health informatics tasks that deal with: (a) overlapping symptoms for the same classification problem (personal health mention classification for influenza and for a set of symptoms); (b) overlapping medical concepts for related classification problems (vaccine usage and drug usage detection); and, (c) related classification problems (vaccination intent and vaccination relevance detection). We experiment with a simple neural architecture: a shared layer followed by task-specific dense layers. The novelty of this work is that it compares alternatives for shared layers for these pairs of tasks. While our observations agree with the promise of MTL as compared to single-task learning, for health informatics, we show that the benefit also comes with caveats in terms of the choice of shared layers and the relatedness between the participating tasks.

We present an overview of the 2019 ALTA shared task. This is the 10th of the series of shared tasks organised by ALTA since 2010. The task was to detect the target of sarcastic comments posted on social media. We intro- duce the task, describe the data and present the results of baselines and participants. This year’s shared task was particularly challenging and no participating systems improved the re- sults of our baseline.

Research in sarcasm detection spans almost a decade. However a particular form of sarcasm remains unexplored: sarcasm expressed through numbers, which we estimate, forms about 11% of the sarcastic tweets in our dataset. The sentence ‘Love waking up at 3 am’ is sarcastic because of the number. In this paper, we focus on detecting sarcasm in tweets arising out of numbers. Initially, to get an insight into the problem, we implement a rule-based and a statistical machine learning-based (ML) classifier. The rule-based classifier conveys the crux of the numerical sarcasm problem, namely, incongruity arising out of numbers. The statistical ML classifier uncovers the indicators i.e., features of such sarcasm. The actual system in place, however, are two deep learning (DL) models, CNN and attention network that obtains an F-score of 0.93 and 0.91 on our dataset of tweets containing numbers. To the best of our knowledge, this is the first line of research investigating the phenomenon of sarcasm arising out of numbers, culminating in a detector thereof.

Distributed representations of text can be used as features when training a statistical classifier. These representations may be created as a composition of word vectors or as context-based sentence vectors. We compare the two kinds of representations (word versus context) for three classification problems: influenza infection classification, drug usage classification and personal health mention classification. For statistical classifiers trained for each of these problems, context-based representations based on ELMo, Universal Sentence Encoder, Neural-Net Language Model and FLAIR are better than Word2Vec, GloVe and the two adapted using the MESH ontology. There is an improvement of 2-4% in the accuracy when these context-based representations are used instead of word-based representations.

Personal health mention detection deals with predicting whether or not a given sentence is a report of a health condition. Past work mentions errors in this prediction when symptom words, i.e., names of symptoms of interest, are used in a figurative sense. Therefore, we combine a state-of-the-art figurative usage detection with CNN-based personal health mention detection. To do so, we present two methods: a pipeline-based approach and a feature augmentation-based approach. The introduction of figurative usage detection results in an average improvement of 2.21% F-score of personal health mention detection, in the case of the feature augmentation-based approach. This paper demonstrates the promise of using figurative usage detection to improve personal health mention detection.

Vaccination behaviour detection deals with predicting whether or not a person received/was about to receive a vaccine. We present our submission for vaccination behaviour detection shared task at the SMM4H workshop. Our findings are based on three prevalent text classification approaches: rule-based, statistical and deep learning-based. Our final submissions are: (1) an ensemble of statistical classifiers with task-specific features derived using lexicons, language processing tools and word embeddings; and, (2) a LSTM classifier with pre-trained language models.

Sarcasm is a form of verbal irony that is intended to express contempt or ridicule. Motivated by challenges posed by sarcastic text to sentiment analysis, computational approaches to sarcasm have witnessed a growing interest at NLP forums in the past decade. Computational sarcasm refers to automatic approaches pertaining to sarcasm. The tutorial will provide a bird’s-eye view of the research in computational sarcasm for text, while focusing on significant milestones.The tutorial begins with linguistic theories of sarcasm, with a focus on incongruity: a useful notion that underlies sarcasm and other forms of figurative language. Since the most significant work in computational sarcasm is sarcasm detection: predicting whether a given piece of text is sarcastic or not, sarcasm detection forms the focus hereafter. We begin our discussion on sarcasm detection with datasets, touching on strategies, challenges and nature of datasets. Then, we describe algorithms for sarcasm detection: rule-based (where a specific evidence of sarcasm is utilised as a rule), statistical classifier-based (where features are designed for a statistical classifier), a topic model-based technique, and deep learning-based algorithms for sarcasm detection. In case of each of these algorithms, we refer to our work on sarcasm detection and share our learnings. Since information beyond the text to be classified, contextual information is useful for sarcasm detection, we then describe approaches that use such information through conversational context or author-specific context.We then follow it by novel areas in computational sarcasm such as sarcasm generation, sarcasm v/s irony classification, etc. We then summarise the tutorial and describe future directions based on errors reported in past work. The tutorial will end with a demonstration of our work on sarcasm detection.This tutorial will be of interest to researchers investigating computational sarcasm and related areas such as computational humour, figurative language understanding, emotion and sentiment sentiment analysis, etc. The tutorial is motivated by our continually evolving survey paper of sarcasm detection, that is available on arXiv at: Joshi, Aditya, Pushpak Bhattacharyya, and Mark James Carman. “Automatic Sarcasm Detection: A Survey.” arXiv preprint arXiv:1602.03426 (2016).

Sarcasm is a form of verbal irony that is intended to express contempt or ridicule. Often quoted as a challenge to sentiment analysis, sarcasm involves use of words of positive or no polarity to convey negative sentiment. Incongruity has been observed to be at the heart of sarcasm understanding in humans. Our work in sarcasm detection identifies different forms of incongruity and employs different machine learning techniques to capture them. This talk will describe the approach, datasets and challenges in sarcasm detection using different forms of incongruity. We identify two forms of incongruity: incongruity which can be understood based on the target text and common background knowledge, and incongruity which can be understood based on the target text and additional, specific context. The former involves use of sentiment-based features, word embeddings, and topic models. The latter involves creation of author’s historical context based on their historical data, and creation of conversational context for sarcasm detection of dialogue.

Topic Models have been reported to be beneficial for aspect-based sentiment analysis. This paper reports the first topic model for sarcasm detection, to the best of our knowledge. Designed on the basis of the intuition that sarcastic tweets are likely to have a mixture of words of both sentiments as against tweets with literal sentiment (either positive or negative), our hierarchical topic model discovers sarcasm-prevalent topics and topic-level sentiment. Using a dataset of tweets labeled using hashtags, the model estimates topic-level, and sentiment-level distributions. Our evaluation shows that topics such as ‘work’, ‘gun laws’, ‘weather’ are sarcasm-prevalent topics. Our model is also able to discover the mixture of sentiment-bearing words that exist in a text of a given sentiment-related label. Finally, we apply our model to predict sarcasm in tweets. We outperform two prior work based on statistical classifiers with specific features, by around 25%.

Parallel corpora are often injected with bilingual lexical resources for improved Indian language machine translation (MT). In absence of such lexical resources, multilingual topic models have been used to create coarse lexical resources in the past, using a Cartesian product approach. Our results show that for morphologically rich languages like Hindi, the Cartesian product approach is detrimental for MT. We then present a novel ‘sentential’ approach to use this coarse lexical resource from a multilingual topic model. Our coarse lexical resource when injected with a parallel corpus outperforms a system trained using parallel corpus and a good quality lexical resource. As demonstrated by the quality of our coarse lexical resource and its benefit to MT, we believe that our sentential approach to create such a resource will help MT for resource-constrained languages.

Sentiment analysis (SA) using code-mixed data from social media has several applications in opinion mining ranging from customer satisfaction to social campaign analysis in multilingual societies. Advances in this area are impeded by the lack of a suitable annotated dataset. We introduce a Hindi-English (Hi-En) code-mixed dataset for sentiment analysis and perform empirical analysis comparing the suitability and performance of various state-of-the-art SA methods in social media. In this paper, we introduce learning sub-word level representations in our LSTM (Subword-LSTM) architecture instead of character-level or word-level representations. This linguistic prior in our architecture enables us to learn the information about sentiment value of important morphemes. This also seems to work well in highly noisy text containing misspellings as shown in our experiments which is demonstrated in morpheme-level feature maps learned by our model. Also, we hypothesize that encoding this linguistic prior in the Subword-LSTM architecture leads to the superior performance. Our system attains accuracy 4-5% greater than traditional approaches on our dataset, and also outperforms the available system for sentiment analysis in Hi-En code-mixed text by 18%.

Typically, accuracy is used to represent the performance of an NLP system. However, accuracy attainment is a function of investment in annotation. Typically, the more the amount and sophistication of annotation, higher is the accuracy. However, a moot question is """"is the accuracy improvement commensurate with the cost incurred in annotation""""? We present an economic model to assess the marginal benefit accruing from increase in cost of annotation. In particular, as a case in point we have chosen the sentiment analysis (SA) problem. In SA, documents normally are polarity classified by running them through classifiers trained on document vectors constructed from lexeme features, i.e., words. If, however, instead of words, one uses word senses (synset ids in wordnets) as features, the accuracy improves dramatically. But is this improvement significant enough to justify the cost of annotation? This question, to the best of our knowledge, has not been investigated with the seriousness it deserves. We perform a cost benefit study based on a vendor-machine model. By setting up a cost price, selling price and profit scenario, we show that although extra cost is incurred in sense annotation, the profit margin is high, justifying the cost.