Discourse & Dialogue
Lexico-semantic and affective modelling of Spanish poetry: A semi-supervised learning approach
Barbado, Alberto, González, María Dolores, Carrera, Débora
Text classification tasks have improved substantially during the last years by the usage of transformers. However, the majority of researches focus on prose texts, with poetry receiving less attention, specially for Spanish language. In this paper, we propose a semi-supervised learning approach for inferring 21 psychological categories evoked by a corpus of 4572 sonnets, along with 10 affective and lexico-semantic multiclass ones. The subset of poems used for training an evaluation includes 270 sonnets. With our approach, we achieve an AUC beyond 0.7 for 76% of the psychological categories, and an AUC over 0.65 for 60% on the multiclass ones. The sonnets are modelled using transformers, through sentence embeddings, along with lexico-semantic and affective features, obtained by using external lexicons. Consequently, we see that this approach provides an AUC increase of up to 0.12, as opposed to using transformers alone.
End-to-End Conversational Search for Online Shopping with Utterance Transfer
Xiao, Liqiang, Ma2, Jun, Dong, Xin Luna, Martinez-Gomez, Pascual, Zalmout, Nasser, Chen, Wei, Zhao, Tong, He, Hao, Jin, Yaohui
Successful conversational search systems can present natural, adaptive and interactive shopping experience for online shopping customers. However, building such systems from scratch faces real word challenges from both imperfect product schema/knowledge and lack of training dialog data.In this work we first propose ConvSearch, an end-to-end conversational search system that deeply combines the dialog system with search. It leverages the text profile to retrieve products, which is more robust against imperfect product schema/knowledge compared with using product attributes alone. We then address the lack of data challenges by proposing an utterance transfer approach that generates dialogue utterances by using existing dialog from other domains, and leveraging the search behavior data from e-commerce retailer. With utterance transfer, we introduce a new conversational search dataset for online shopping. Experiments show that our utterance transfer method can significantly improve the availability of training dialogue data without crowd-sourcing, and the conversational search system significantly outperformed the best tested baseline.
Microbiome subcommunity learning with logistic-tree normal latent Dirichlet allocation
Mixed-membership (MM) models such as Latent Dirichlet Allocation (LDA) have been applied to microbiome compositional data to identify latent subcommunities of microbial species. However, microbiome compositional data, especially those collected from the gut, typically display substantial cross-sample heterogeneities in the subcommunity composition which current MM methods do not account for. To address this limitation, we incorporate the logistic-tree normal (LTN) model -- using the phylogenetic tree structure -- into the LDA model to form a new MM model. This model allows variation in the composition of each subcommunity around some ``centroid'' composition. Incorporation of auxiliary P\'olya-Gamma variables enables a computationally efficient collapsed blocked Gibbs sampler to carry out Bayesian inference under this model. We compare the new model and LDA and show that in the presence of large cross-sample heterogeneity, under the LDA model the resulting inference can be extremely sensitive to the specification of the total number of subcommunities as it does not account for cross-sample heterogeneity. As such, the popular strategy in other applications of MM models of overspecifying the number of subcommunities -- and hoping that some meaningful subcommunities will emerge among artificial ones -- can lead to highly misleading conclusions in the microbiome context. In contrast, by accounting for such heterogeneity, our MM model restores the robustness of the inference in the specification of the number of subcommunities and again allows meaningful subcommunities to be identified under this strategy.
Sentiment Analysis: Types, How it Works & Why it is Difficult?
Understanding the sentiments of the people is not easy unless they express their feelings, opinions and perspective anything. But if you have such platforms where people are freely speaking up about their thoughts and concerns, you can easily find out their sentiments. Here where Cogito comes in the facility of sentiment analysis. Sentiment Analysis is the process of determining the conceptions, judgments, feelings, opinions, viewpoints, conclusions, and other notions towards anything. It is a technique to analyze texts, images, emojis and various other actions to know what other people think about a product, service, company, brand name, or a reaction to a specific event, social movement, etc. Sentiment analysis is playing an enormous role in understanding people belonging to different groups and their sentiments.
Fusing task-oriented and open-domain dialogues in conversational agents
Young, Tom, Xing, Frank, Pandelea, Vlad, Ni, Jinjie, Cambria, Erik
The goal of building intelligent dialogue systems has largely been \textit{separately} pursued under two paradigms: task-oriented dialogue (TOD) systems, which perform goal-oriented functions, and open-domain dialogue (ODD) systems, which focus on non-goal-oriented chitchat. The two dialogue modes can potentially be intertwined together seamlessly in the same conversation, as easily done by a friendly human assistant. Such ability is desirable in conversational agents, as the integration makes them more accessible and useful. Our paper addresses this problem of fusing TODs and ODDs in multi-turn dialogues. Based on the popular TOD dataset MultiWOZ, we build a new dataset FusedChat, by rewriting the existing TOD turns and adding new ODD turns. This procedure constructs conversation sessions containing exchanges from both dialogue modes. It features inter-mode contextual dependency, i.e., the dialogue turns from the two modes depend on each other. Rich dependency patterns including co-reference and ellipsis are features. The new dataset, with 60k new human-written ODD turns and 5k re-written TOD turns, offers a benchmark to test a dialogue model's ability to perform inter-mode conversations. This is a more challenging task since the model has to determine the appropriate dialogue mode and generate the response based on the inter-mode context. But such models would better mimic human-level conversation capabilities. We evaluate baseline models on this task, including \textit{classification-based} two-stage models and \textit{two-in-one} fused models. We publicly release FusedChat and the baselines to propel future work on inter-mode dialogue systems https://github.com/tomyoung903/FusedChat.
Improving Multimodal fusion via Mutual Dependency Maximisation
Colombo, Pierre, Chapuis, Emile, Labeau, Matthieu, Clavel, Chloe
Multimodal sentiment analysis is a trending area of research, and the multimodal fusion is one of its most active topic. Acknowledging humans communicate through a variety of channels (i.e visual, acoustic, linguistic), multimodal systems aim at integrating different unimodal representations into a synthetic one. So far, a consequent effort has been made on developing complex architectures allowing the fusion of these modalities. However, such systems are mainly trained by minimising simple losses such as $L_1$ or cross-entropy. In this work, we investigate unexplored penalties and propose a set of new objectives that measure the dependency between modalities. We demonstrate that our new penalties lead to a consistent improvement (up to $4.3$ on accuracy) across a large variety of state-of-the-art models on two well-known sentiment analysis datasets: \texttt{CMU-MOSI} and \texttt{CMU-MOSEI}. Our method not only achieves a new SOTA on both datasets but also produces representations that are more robust to modality drops. Finally, a by-product of our methods includes a statistical network which can be used to interpret the high dimensional representations learnt by the model.
Code-switched inspired losses for generic spoken dialog representations
Chapuis, Emile, Colombo, Pierre, Labeau, Matthieu, Clavel, Chloe
While there has been a growing interest in pretraining for dialog A crucial step in conversational AI is the identification (Mehri et al., 2019; Zhang et al., 2019d), the focus of underlying information of the user's utterance has mainly been on English datasets. Thus, these (e.g communicative intent or dialog acts, and works can not be directly applied to our multilingual emotions). This requires modeling utterance-level setting. Additionally, available multilingual information (Mitkov, 2014; Williams et al., 2014), pretraining objectives (Lample and Conneau, 2019; to capture immediate nuances of the user utterance; Liu et al., 2020; Xue et al., 2020; Qi et al., 2021) and discourse-level features (Thornbury and Slade, face two main limitations when applied to dialog 2006), to capture patterns over long ranges of the modeling: (1) they are a generalization of monolingual conversation. An added difficulty to this modeling objectives that use flat input text, whereas problem is that most people in the world are bilingual hierarchy has been shown to be a powerful prior (Grosjean and Li, 2013): therefore, progress for dialog modeling. This is a reflection of a dialog on these systems is limited by their inability to process itself, for example, context plays an essential role more than one language (English being the in the labeling of dialog acts.
Effective Sequence-to-Sequence Dialogue State Tracking
Zhao, Jeffrey, Mahdieh, Mahdis, Zhang, Ye, Cao, Yuan, Wu, Yonghui
Sequence-to-sequence models have been applied to a wide variety of NLP tasks, but how to properly use them for dialogue state tracking has not been systematically investigated. In this paper, we study this problem from the perspectives of pre-training objectives as well as the formats of context representations. We demonstrate that the choice of pre-training objective makes a significant difference to the state tracking quality. In particular, we find that masked span prediction is more effective than auto-regressive language modeling. We also explore using Pegasus, a span prediction-based pre-training objective for text summarization, for the state tracking model. We found that pre-training for the seemingly distant summarization task works surprisingly well for dialogue state tracking. In addition, we found that while recurrent state context representation works also reasonably well, the model may have a hard time recovering from earlier mistakes. We conducted experiments on the MultiWOZ 2.1-2.4, WOZ 2.0, and DSTC2 datasets with consistent observations.
A beginner's guide to OCTIS: Optimizing and Comparing Topic Models Is Simple
Topic models are promising generative statistical methods that aim to extract the hidden topics underlying a collection of documents. Typically, topic models have two matrices as output. Then, the top-n words from this matrix with the highest probability are then used to represent a topic. The most popular topic modeling method is Latent Dirichlet Allocation, and many articles are written about its workings and implementations. However, focusing on LDA only is restrictive and might be suboptimal for a given corpus.
Hybrid Contrastive Learning of Tri-Modal Representation for Multimodal Sentiment Analysis
Mai, Sijie, Zeng, Ying, Zheng, Shuangjia, Hu, Haifeng
The wide application of smart devices enables the availability of multimodal data, which can be utilized in many tasks. In the field of multimodal sentiment analysis (MSA), most previous works focus on exploring intra- and inter-modal interactions. However, training a network with cross-modal information (language, visual, audio) is still challenging due to the modality gap, and existing methods still cannot ensure to sufficiently learn intra-/inter-modal dynamics. Besides, while learning dynamics within each sample draws great attention, the learning of inter-class relationships is neglected. Moreover, the size of datasets limits the generalization ability of existing methods. To address the afore-mentioned issues, we propose a novel framework HyCon for hybrid contrastive learning of tri-modal representation. Specifically, we simultaneously perform intra-/inter-modal contrastive learning and semi-contrastive learning (that is why we call it hybrid contrastive learning), with which the model can fully explore cross-modal interactions, preserve inter-class relationships and reduce the modality gap. Besides, a refinement term is devised to prevent the model falling into a sub-optimal solution. Moreover, HyCon can naturally generate a large amount of training pairs for better generalization and reduce the negative effect of limited datasets. Extensive experiments on public datasets demonstrate that our proposed method outperforms existing works.