SKShivani Kumar

Shivani Kumar

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Shivani Kumar has a total of 20 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Dialogue agents 101: a beginner’s guide to critical ingredients for designing effective conversational systems

    by Shivani Kumar, Sumit Bhatia, Milan Aggarwal, Tanmoy Chakraborty

    Sharing ideas through communication with peers is the primary mode of human interaction. Consequently, extensive research has been conducted in the area of conversational AI, leading to an increase in the availability and diversity of conversational tasks, datasets, and methods. However, with numerous tasks being explored simultaneously, the current landscape of conversational AI has become fragmented. Consequently, initiating a well-thought-out model for a dialogue agent can pose significant challenges for a practitioner. Toward highlighting the critical ingredients needed for a practitioner to design a dialogue agent from scratch, the current study provides a comprehensive overview of the primary characteristics of a dialogue agent, the supporting tasks, their corresponding open-domain datasets, and the methods used to benchmark these datasets. We observe that different methods have been used to tackle distinct dialogue tasks. However, building separate models for each task is costly and does not leverage the correlation among the several tasks of a dialogue agent. As a result, recent trends suggest a shift toward building unified foundation models. To this end, we propose Unit, a Unified dialogue dataset constructed from conversations of varying datasets for different dialogue tasks capturing the nuances for each of them. We then train a Unified dialogue foundation model, GPT-2 $^{\textrm{U}}$ and present a concise comparative performance of GPT-2 $^{\textrm{U}}$ against existing large language models. We also examine the evaluation strategies used to measure the performance of dialogue agents and highlight the scope for future research in the area of conversational AI with a thorough discussion of popular models such as ChatGPT.


  • Top Cited Papers
    Open Access

    Exploring the Efficacy of Large Language Models in Summarizing Mental Health Counseling Sessions: Benchmark Study

    by Prottay Kumar Adhikary, Aseem Srivastava, Shivani Kumar, Salam Michael Singh, Puneet Manuja, Jini K Gopinath, Vijay Krishnan, Swati Kedia Gupta, Koushik Sinha Deb, Tanmoy Chakraborty

    Background: Comprehensive session summaries enable effective continuity in mental health counseling, facilitating informed therapy planning. However, manual summarization presents a significant challenge, diverting experts’ attention from the core counseling process. Leveraging advances in automatic summarization to streamline the summarization process addresses this issue because this enables mental health professionals to access concise summaries of lengthy therapy sessions, thereby increasing their efficiency. However, existing approaches often overlook the nuanced intricacies inherent in counseling interactions. Objective: This study evaluates the effectiveness of state-of-the-art large language models (LLMs) in selectively summarizing various components of therapy sessions through aspect-based summarization, aiming to benchmark their performance. Methods: We first created Mental Health Counseling-Component–Guided Dialogue Summaries, a benchmarking data set that consists of 191 counseling sessions with summaries focused on 3 distinct counseling components (also known as counseling aspects). Next, we assessed the capabilities of 11 state-of-the-art LLMs in addressing the task of counseling-component–guided summarization. The generated summaries were evaluated quantitatively using standard summarization metrics and verified qualitatively by mental health professionals. Results: Our findings demonstrated the superior performance of task-specific LLMs such as MentalLlama, Mistral, and MentalBART evaluated using standard quantitative metrics such as Recall-Oriented Understudy for Gisting Evaluation (ROUGE)-1, ROUGE-2, ROUGE-L, and Bidirectional Encoder Representations from Transformers Score across all aspects of the counseling components. Furthermore, expert evaluation revealed that Mistral superseded both MentalLlama and MentalBART across 6 parameters: affective attitude, burden, ethicality, coherence, opportunity costs, and perceived effectiveness. However, these models exhibit a common weakness in terms of room for improvement in the opportunity costs and perceived effectiveness metrics. Conclusions: While LLMs fine-tuned specifically on mental health domain data display better performance based on automatic evaluation scores, expert assessments indicate that these models are not yet reliable for clinical application. Further refinement and validation are necessary before their implementation in practice.


  • Open Access

    Exploring the Efficacy of Large Language Models in Summarizing Mental Health Counseling Sessions: Benchmark Study (Preprint)

    by Prottay Kumar Adhikary, Aseem Srivastava, Shivani Kumar, Salam Michael Singh, Puneet Manuja, Jini K Gopinath, Vijay Krishnan, Swati Kedia Gupta, Koushik Sinha Deb, Tanmoy Chakraborty

    BACKGROUND Comprehensive session summaries enable effective continuity in mental health counseling, facilitating informed therapy planning. However, manual summarization presents a significant challenge, diverting experts’ attention from the core counseling process. Leveraging advances in automatic summarization to streamline the summarization process addresses this issue because this enables mental health professionals to access concise summaries of lengthy therapy sessions, thereby increasing their efficiency. However, existing approaches often overlook the nuanced intricacies inherent in counseling interactions. OBJECTIVE This study evaluates the effectiveness of state-of-the-art large language models (LLMs) in selectively summarizing various components of therapy sessions through aspect-based summarization, aiming to benchmark their performance. METHODS We first created Mental Health Counseling-Component–Guided Dialogue Summaries, a benchmarking data set that consists of 191 counseling sessions with summaries focused on 3 distinct counseling components (also known as counseling aspects). Next, we assessed the capabilities of 11 state-of-the-art LLMs in addressing the task of counseling-component–guided summarization. The generated summaries were evaluated quantitatively using standard summarization metrics and verified qualitatively by mental health professionals. RESULTS Our findings demonstrated the superior performance of task-specific LLMs such as MentalLlama, Mistral, and MentalBART evaluated using standard quantitative metrics such as Recall-Oriented Understudy for Gisting Evaluation (ROUGE)-1, ROUGE-2, ROUGE-L, and Bidirectional Encoder Representations from Transformers Score across all aspects of the counseling components. Furthermore, expert evaluation revealed that Mistral superseded both MentalLlama and MentalBART across 6 parameters: affective attitude, burden, ethicality, coherence, opportunity costs, and perceived effectiveness. However, these models exhibit a common weakness in terms of room for improvement in the opportunity costs and perceived effectiveness metrics. CONCLUSIONS While LLMs fine-tuned specifically on mental health domain data display better performance based on automatic evaluation scores, expert assessments indicate that these models are not yet reliable for clinical application. Further refinement and validation are necessary before their implementation in practice.


  • Open Access

    Harmonizing Code-mixed Conversations: Personality-assisted Code-mixed Response Generation in Dialogues

    by Shivani Kumar, Tanmoy Chakraborty

    Code-mixing, the blending of multiple languages within a single conversation, introduces a distinctive challenge, particularly in the context of response generation. Capturing the intricacies of code-mixing proves to be a formidable task, given the wide-ranging variations influenced by individual speaking styles and cultural backgrounds. In this study, we explore response generation within code-mixed conversations. We introduce a novel approach centered on harnessing the Big Five personality traits acquired in an unsupervised manner from the conversations to bolster the performance of response generation. These inferred personality attributes are seamlessly woven into the fabric of the dialogue context, using a novel fusion mechanism, PA3. It uses an effective two-step attention formulation to fuse the dialogue and personality information. This fusion not only enhances the contextual relevance of generated responses but also elevates the overall performance of the model. Our experimental results, grounded in a dataset comprising of multi-party Hindi-English code-mix conversations, highlight the substantial advantages offered by personality-infused models over their conventional counterparts. This is evident in the increase observed in ROUGE and BLUE scores for the response generation task when the identified personality is seamlessly integrated into the dialogue context. Qualitative assessment for personality identification and response generation aligns well with our quantitative results.

  • Open Access

    Harmonizing Code-mixed Conversations: Personality-assisted Code-mixed Response Generation in Dialogues

    by Shivani Kumar, Tanmoy Chakraborty

    Shivani Kumar, Tanmoy Chakraborty. Findings of the Association for Computational Linguistics: EACL 2024. 2024.


  • Open Access

    From Multilingual Complexity to Emotional Clarity: Leveraging Commonsense to Unveil Emotions in Code-Mixed Dialogues

    by Shivani Kumar, Ramaneswaran S, Shad Akhtar, Tanmoy Chakraborty

    Understanding emotions during conversation is a fundamental aspect of human communication, driving NLP research for Emotion Recognition in Conversation (ERC). While considerable research has focused on discerning emotions of individual speakers in monolingual dialogues, understanding the emotional dynamics in code-mixed conversations has received relatively less attention. This motivates our undertaking of ERC for code-mixed conversations in this study. Recognizing that emotional intelligence encompasses a comprehension of worldly knowledge, we propose an innovative approach that integrates commonsense information with dialogue context to facilitate a deeper understanding of emotions. To achieve this, we devise an efficient pipeline that extracts relevant commonsense from existing knowledge graphs based on the code-mixed input. Subsequently, we develop an advanced fusion technique that seamlessly combines the acquired commonsense information with the dialogue representation obtained from a dedicated dialogue understanding module. Our comprehensive experimentation showcases the substantial performance improvement obtained through the systematic incorporation of commonsense in ERC. Both quantitative assessments and qualitative analyses further corroborate the validity of our hypothesis, reaffirming the pivotal role of commonsense integration in enhancing ERC.

  • Emotion Flip Reasoning in Multiparty Conversations

    by Shivani Kumar, Shubham Dudeja, Shad Akhtar, Tanmoy Chakraborty

    In a conversational dialogue, speakers may have different emotional states and their dynamics play an important role in understanding dialogue's emotional discourse. However, simply detecting emotions is not sufficient to entirely comprehend the speaker-specific changes in emotion that occur during a conversation. To understand the emotional dynamics of speakers in an efficient manner, it is imperative to identify the rationale or instigator behind any changes or flips in emotion expressed by the speaker. In this paper, we explore the task called Instigator based Emotion Flip Reasoning (EFR), which aims to identify the instigator behind a speaker's emotion flip within a conversation. For example, an emotion flip from joy to anger could be caused by an instigator like threat. To facilitate this task, we present MELD-I , a dataset that includes ground-truth EFR instigator labels, which are in line with emotional psychology. To evaluate the dataset, we propose a novel neural architecture called TGIF , which leverages Transformer encoders and stacked GRUs to capture the dialogue context, speaker dynamics, and emotion sequence in a conversation. Our evaluation demonstrates state-of-the-art performance (+4−12% increase in F1-score) against five baselines used for the task. Further, we establish the generalizability of TGIF on an unseen dataset in a zero-shot setting. Additionally, we provide a detailed analysis of the competing models, highlighting the advantages and limitations of our neural architecture.


  • Open Access

    Explaining (Sarcastic) Utterances to Enhance Affect Understanding in Multimodal Dialogues

    by Shivani Kumar, Ishani Mondal, Shad Akhtar, Tanmoy Chakraborty

    Conversations emerge as the primary media for exchanging ideas and conceptions. From the listener’s perspective, identifying various affective qualities, such as sarcasm, humour, and emotions, is paramount for comprehending the true connotation of the emitted utterance. However, one of the major hurdles faced in learning these affect dimensions is the presence of figurative language, viz. irony, metaphor, or sarcasm. We hypothesize that any detection system constituting the exhaustive and explicit presentation of the emitted utterance would improve the overall comprehension of the dialogue. To this end, we explore the task of Sarcasm Explanation in Dialogues, which aims to unfold the hidden irony behind sarcastic utterances. We propose MOSES, a deep neural network which takes a multimodal (sarcastic) dialogue instance as an input and generates a natural language sentence as its explanation. Subsequently, we leverage the generated explanation for various natural language understanding tasks in a conversational dialogue setup, such as sarcasm detection, humour identification, and emotion recognition. Our evaluation shows that MOSES outperforms the state-of-the-art system for SED by an average of ∼2% on different evaluation metrics, such as ROUGE, BLEU, and METEOR. Further, we observe that leveraging the generated explanation advances three downstream tasks for affect classification – an average improvement of ~14% F1-score in the sarcasm detection task and ∼2% in the humour identification and emotion recognition task. We also perform extensive analyses to assess the quality of the results.


  • Open Access

    Emotion Flip Reasoning in Multiparty Conversations

    by Shivani Kumar, Shubham Dudeja, Shad Akhtar, Tanmoy Chakraborty

    In a conversational dialogue, speakers may have different emotional states and their dynamics play an important role in understanding dialogue's emotional discourse. However, simply detecting emotions is not sufficient to entirely comprehend the speaker-specific changes in emotion that occur during a conversation. To understand the emotional dynamics of speakers in an efficient manner, it is imperative to identify the rationale or instigator behind any changes or flips in emotion expressed by the speaker. In this paper, we explore the task called Instigator based Emotion Flip Reasoning (EFR), which aims to identify the instigator behind a speaker's emotion flip within a conversation. For example, an emotion flip from joy to anger could be caused by an instigator like threat. To facilitate this task, we present MELD-I, a dataset that includes ground-truth EFR instigator labels, which are in line with emotional psychology. To evaluate the dataset, we propose a novel neural architecture called TGIF, which leverages Transformer encoders and stacked GRUs to capture the dialogue context, speaker dynamics, and emotion sequence in a conversation. Our evaluation demonstrates state-of-the-art performance (+4-12% increase in F1-score) against five baselines used for the task. Further, we establish the generalizability of TGIF on an unseen dataset in a zero-shot setting. Additionally, we provide a detailed analysis of the competing models, highlighting the advantages and limitations of our neural architecture.

  • Open Access

    Speaker Profiling in Multiparty Conversations

    by Shivani Kumar, Rishabh Gupta, Shad Akhtar, Tanmoy Chakraborty

    In conversational settings, individuals exhibit unique behaviors, rendering a one-size-fits-all approach insufficient for generating responses by dialogue agents. Although past studies have aimed to create personalized dialogue agents using speaker persona information, they have relied on the assumption that the speaker's persona is already provided. However, this assumption is not always valid, especially when it comes to chatbots utilized in industries like banking, hotel reservations, and airline bookings. This research paper aims to fill this gap by exploring the task of Speaker Profiling in Conversations (SPC). The primary objective of SPC is to produce a summary of persona characteristics for each individual speaker present in a dialogue. To accomplish this, we have divided the task into three subtasks: persona discovery, persona-type identification, and persona-value extraction. Given a dialogue, the first subtask aims to identify all utterances that contain persona information. Subsequently, the second task evaluates these utterances to identify the type of persona information they contain, while the third subtask identifies the specific persona values for each identified type. To address the task of SPC, we have curated a new dataset named SPICE, which comes with specific labels. We have evaluated various baselines on this dataset and benchmarked it with a new neural model, SPOT, which we introduce in this paper. Furthermore, we present a comprehensive analysis of SPOT, examining the limitations of individual modules both quantitatively and qualitatively.