In this paper, we propose a novel negotiation agent designed for the online marketplace. Our dialogue agent is integrative in nature i.e, it possesses the capability to negotiate on price as well as other factors, such as the addition or removal of items from a deal bundle, thereby offering a more flexible and comprehensive negotiation experience. To enable this functionality, we create a new dataset called Integrative Negotiation Dataset (IND). For this dataset creation, we introduce a new semi-automated data creation method, which combines defining negotiation intents, actions, and intent-action simulation between users and the agent to generate potential dialogue flows. Finally, the prompting of GPT-J, a state-of-the-art language model, is done to generate dialogues for a given intent, with a human-in-the-loop process for post-editing and refining minor errors to ensure high data quality. We first train a maximum likelihood loss based model on IND, and then employ a set of novel rewards specifically tailored for the negotiation task to train our Integrative Negotiation Agent (INA). These rewards incentivize the agent to learn effective negotiation strategies that can adapt to various contextual requirements and price proposals. We train our model and conduct experiments to evaluate the effectiveness of our reward-based dialogue agent for negotiation. Our results demonstrate that the proposed approach and reward functions significantly enhance the negotiation capabilities of the dialogue agent. The INA successfully engages in integrative negotiations, displaying the ability to dynamically adjust prices and negotiate the inclusion or exclusion of items in a deal bundle.

With the growing popularity of code-mixed data, there is an increasing need for better handling of this type of data, which poses a number of challenges, such as dealing with spelling variations, multiple languages, different scripts, and a lack of resources. Current language models face difficulty in effectively handling code-mixed data as they primarily focus on the semantic representation of words and ignore the auditory phonetic features. This leads to difficulties in handling spelling variations in code-mixed text. In this paper, we propose an effective approach for creating language models for handling code-mixed textual data using auditory information of words from SOUNDEX. Our approach includes a pre-training step based on masked-language-modelling, which includes SOUNDEX representations (SAMLM) and a new method of providing input data to the pre-trained model. Through experimentation on various code-mixed datasets (of different languages) for sentiment, offensive and aggression classification tasks, we establish that our novel language modeling approach (SAMLM) results in improved robustness towards adversarial attacks on code-mixed classification tasks. Additionally, our SAMLM based approach also results in better classification results over the popular baselines for code-mixed tasks. We use the explainability technique, SHAP (SHapley Additive exPlanations) to explain how the auditory features incorporated through SAMLM assist the model to handle the code-mixed text effectively and increase robustness against adversarial attacks.

Although there has been a plethora of work on open-domain conversational systems, most of the systems lack the mechanism of controlling the concept transitions in a dialogue. For activities like switching from casual chit-chat to task-oriented conversation, an agent with the ability to manage the flow of concepts in a conversation might be helpful. The user would find the dialogue more engaging and be more receptive to such transitions if these concept transitions were made while taking into account the user’s persona. Focusing on persona-aware concept transitions, we propose a Reinforced Persona-aware Topic-guiding Conversational System (RPTCS). Due to the lack of a persona-aware topic transition dataset, we propose a novel conversation dataset creation mechanism in which the conversational agent leads the discourse to drift to a set of target concepts depending on the persona of the speaker and the context of the conversation. To avoid scarcely available expensive human resource, the entire data-creation process is mostly automatic with human-in-loop only for quality checks. This created conversational dataset named PTCD is used to develop the RPTCS in two steps. First, a maximum likelihood estimation loss-based conversational model is trained on PTCD. Then this trained model is fine-tuned in a Reinforcement Learning (RL) framework by employing novel reward functions to assure persona, topic, and context consistency with non-repetitiveness in generated responses. Our experimental results demonstrate the strength of the proposed system with respect to strong baselines.

In order to provide personalized interactions in a conversational system, responses must be consistent with the user and agent persona while still being relevant to the context of the conversation. Existing personalized conversational systems increase the consistency of the generated response by leveraging persona descriptions, which sometimes tend to generate irrelevant responses to the context. To solve this problems, we propose to extend the persona-agnostic meta-learning (PAML) framework by adding knowledge from ConceptNet knowledge graph with multi-hop attention mechanism. Knowledge is a concept in a triple form that helps in conversational flow. The multi-hop attention mechanism helps select the most appropriate triples with respect to the conversational context and persona description, as not all triples are beneficial for generating responses. The Meta-Learning (PAML) framework allows quick adaptation to different personas by utilizing only a few dialogue samples from the same user. Our experiments on the Persona-Chat dataset show that our method outperforms in terms of persona-adaptability, resulting in more persona-consistent responses, as evidenced by the entailment (Entl) score in the automatic evaluation and the consistency (Con) score in human evaluation.

Modelling and understanding dialogues in a conversation depends on identifying the user intent from the given text. Unknown or new intent detection is a critical task, as in a realistic scenario a user intent may frequently change over time and divert even to an intent previously not encountered. This task of separating the unknown intent samples from known intents one is challenging as the unknown user intent can range from intents similar to the predefined intents to something completely different. Prior research on intent discovery often consider it as a classification task where an unknown intent can belong to a predefined set of known intent classes. In this paper we tackle the problem of detecting a completely unknown intent without any prior hints about the kind of classes belonging to unknown intents. We propose an effective post-processing method using multi-objective optimization to tune an existing neural network based intent classifier and make it capable of detecting unknown intents. We perform experiments using existing state-of-the-art intent classifiers and use our method on top of them for unknown intent detection. Our experiments across different domains and real-world datasets show that our method yields significant improvements compared with the state-of-the-art methods for unknown intent detection.

Unsupervised style transfer in text has previously been explored through the sentiment transfer task. The task entails inverting the overall sentiment polarity in a given input sentence, while preserving its content. From the Aspect-Based Sentiment Analysis (ABSA) task, we know that multiple sentiment polarities can often be present together in a sentence with multiple aspects. In this paper, the task of aspect-level sentiment controllable style transfer is introduced, where each of the aspect-level sentiments can individually be controlled at the output. To achieve this goal, a BERT-based encoder-decoder architecture with saliency weighted polarity injection is proposed, with unsupervised training strategies, such as ABSA masked-language-modelling. Through both automatic and manual evaluation, we show that the system is successful in controlling aspect-level sentiments.

Automatic extraction of disaster-related events and their arguments from natural language text is vital for building a decision support system for crisis management. Event extraction from various news sources is a well-explored area for this objective. However, extracting events alone, without any context, provides only partial help for this purpose. Extracting related arguments like Time, Place, Casualties, etc., provides a complete picture of the disaster event. In this paper, we create a disaster domain dataset in Hindi by annotating disaster-related event and arguments. We also obtain equivalent datasets for Bengali and English from a collaboration. We build a multi-lingual deep learning model for argument extraction in all the three languages. We also compare our multi-lingual system with a similar baseline mono-lingual system trained for each language separately. It is observed that a single multi-lingual system is able to compensate for lack of training data, by using joint training of dataset from different languages in shared space, thus giving a better overall result.