Understanding the intention of the users and recognizing the semantic entities from their sentences, aka natural language understanding (NLU), is the upstream task of many natural language processing tasks. One of the main challenges is to collect a sufficient amount of annotated data to train a model. Existing research about text augmentation does not abundantly consider entity and thus performs badly for NLU tasks. To solve this problem, we propose a novel NLP data augmentation technique, Entity Aware Data Augmentation (EADA), which applies a tree structure, Entity Aware Syntax Tree (EAST), to represent sentences combined with attention on the entity. Our EADA technique automatically constructs an EAST from a small amount of annotated data, and then generates a large number of training instances for intent detection and slot filling. Experimental results on four datasets showed that the proposed technique significantly outperforms the existing data augmentation methods in terms of both accuracy and generalization ability.

The dataset has 25000 positive and negative reviews in the training set and 25000 positive and negative reviews in the test set. The image below shows the number of unique reviews and unique sentiment values in the dataset. The movie reviews are classified as having either a positive sentiment or a negative sentiment. The image below takes a peek at four reviews and their target sentiments. As can be seen from the keywords of the first three reviews – hooked, wonderful, unassuming, wonderful – lend the review a positive connotation.

The challenge of language grounding is to fully understand natural language by grounding language in real-world referents. While AI techniques are available, the widespread adoption and effectiveness of such technologies for human-robot teams relies critically on user trust. This survey provides three contributions relating to the newly emerging field of trust in language grounding, including a) an overview of language grounding research in terms of AI technologies, data sets, and user interfaces; b) six hypothesised trust factors relevant to language grounding, which are tested empirically on a human-robot cleaning team; and c) future research directions for trust in language grounding.

Making chatbots world aware in a conversation like a human is a crucial challenge, where the world may contain dynamic knowledge and spatiotemporal state. Several recent advances have tried to link the dialog system to a static knowledge base or search engine, but they do not contain all the world information needed for conversations. In contrast, we propose a new method to improve the dialogue system using spatiotemporal aware dynamic knowledge. We utilize service information as a way for the dialogue system to link the world. The system actively builds a request according to the dialog context and spatiotemporal state to get service information and then generates world aware responses. To implement this method, we collect DuSinc, an open-domain human-human dialogue dataset, where a participant can access the service to get the information needed for dialogue responses. Through automatic and human evaluations, we found that service information significantly improves the consistency, informativeness, factuality, and engagingness of the dialogue system, making it behave more like a human. Compared to the pre-trained models without spatiotemporal aware dynamic knowledge, the overall session-level score was improved by 60.87\%. The collection dataset and methods will be open-sourced.

Stopwords carry little semantic information and are often removed from text data to reduce dataset size and improve machine learning model performance. Consequently, researchers have sought to develop techniques for generating effective stopword sets. Previous approaches have ranged from qualitative techniques relying upon linguistic experts, to statistical approaches that extract word importance using correlations or frequency-dependent metrics computed on a corpus. We present a novel quantitative approach that employs iterative and recursive feature deletion algorithms to see which words can be deleted from a pre-trained transformer's vocabulary with the least degradation to its performance, specifically for the task of sentiment analysis. Empirically, stopword lists generated via this approach drastically reduce dataset size while negligibly impacting model performance, in one such example shrinking the corpus by 28.4% while improving the accuracy of a trained logistic regression model by 0.25%. In another instance, the corpus was shrunk by 63.7% with a 2.8% decrease in accuracy. These promising results indicate that our approach can generate highly effective stopword sets for specific NLP tasks.

Task-oriented dialogue systems aim to fulfill user goals through natural language interactions. They are ideally evaluated with human users, which however is unattainable to do at every iteration of the development phase. Simulated users could be an alternative, however their development is nontrivial. Therefore, researchers resort to offline metrics on existing human-human corpora, which are more practical and easily reproducible. They are unfortunately limited in reflecting real performance of dialogue systems. BLEU for instance is poorly correlated with human judgment, and existing corpus-based metrics such as success rate overlook dialogue context mismatches. There is still a need for a reliable metric for task-oriented systems with good generalization and strong correlation with human judgements. In this paper, we propose the use of offline reinforcement learning for dialogue evaluation based on a static corpus. Such an evaluator is typically called a critic and utilized for policy optimization. We go one step further and show that offline RL critics can be trained on a static corpus for any dialogue system as external evaluators, allowing dialogue performance comparisons across various types of systems. This approach has the benefit of being corpus- and model-independent, while attaining strong correlation with human judgements, which we confirm via an interactive user trial.

At the peak of the COVID-19 pandemic, numerous countries worldwide sought to mobilize vaccination campaigns in an attempt to curb the spread and number of deaths caused by the virus. One avenue in which information regarding COVID vaccinations is propagated is that of scientific articles, which provide a certain level of credibility regarding this. Hence, this increases the probability that people who view these articles would get vaccinated if the articles convey a positive message on vaccinations and conversely decreases the probability of vaccinations if the articles convey a negative message. This being said, this study aims to investigate the correlation between article sentiments and the corresponding increase or decrease in vaccinations in the United States. To do this, a lexicon-based sentiment analysis was performed in two steps: first, article content was scraped via a Python library called BeautifulSoup, and second, VADER was used to obtain the sentiment analysis scores for each article based on the scraped text content. Results suggest that there was a relatively weak correlation between the average sentiment score of articles and the corresponding increase or decrease in COVID vaccination rates in the US.

Subjective texts have been especially studied by several works as they can induce certain behaviours in their users. Most work focuses on user-generated texts in social networks, but some other texts also comprise opinions on certain topics and could influence judgement criteria during political decisions. In this work, we address the task of Targeted Sentiment Analysis for the domain of news headlines, published by the main outlets during the 2019 Argentinean Presidential Elections. For this purpose, we present a polarity dataset of 1,976 headlines mentioning candidates in the 2019 elections at the target level. Preliminary experiments with state-of-the-art classification algorithms based on pre-trained linguistic models suggest that target information is helpful for this task. We make our data and pre-trained models publicly available.

Multimodal sentiment analysis is an important research task to predict the sentiment score based on the different modality data from a specific opinion video. Many previous pieces of research have proved the significance of utilizing the shared and unique information across different modalities. However, the high-order combined signals from multimodal data would also help extract satisfied representations. In this paper, we propose CMGA, a Cross-Modality Gated Attention fusion model for MSA that tends to make adequate interaction across different modality pairs. CMGA also adds a forget gate to filter the noisy and redundant signals introduced in the interaction procedure. We experiment on two benchmark datasets in MSA, MOSI, and MOSEI, illustrating the performance of CMGA over several baseline models. We also conduct the ablation study to demonstrate the function of different components inside CMGA.

Zero/few-shot transfer to unseen services is a critical challenge in task-oriented dialogue research. The Schema-Guided Dialogue (SGD) dataset introduced a paradigm for enabling models to support any service in zero-shot through schemas, which describe service APIs to models in natural language. We explore the robustness of dialogue systems to linguistic variations in schemas by designing SGD-X - a benchmark extending SGD with semantically similar yet stylistically diverse variants for every schema. We observe that two top state tracking models fail to generalize well across schema variants, measured by joint goal accuracy and a novel metric for measuring schema sensitivity. Additionally, we present a simple model-agnostic data augmentation method to improve schema robustness.