Customer service is the lifeblood of any business. Excellent customer service not only generates return business but also creates new customers. Looking at the demanding market to provide a 24/7 service to customers, many organisations are increasingly engaged in popular social media and text messaging platforms such as WhatsApp and Facebook Messenger in providing a 24/7 service to customers in the current demanding market. In this paper, we present an intent matching based customer services chatbot (IMCSC), which is capable of replacing the customer service work of sales personnel, whilst interacting in a more natural and human-like manner through the employment of Natural Language Understanding (NLU). The bot is able to answer the most common frequently asked questions and we have also integrated features for the processing and exporting of customer orders to a Google Sheet.
Measuring text complexity is an essential task in several fields and applications (such as NLP, semantic web, smart education, etc.). The semantic layer of text is more tacit than its syntactic structure and, as a result, calculation of semantic complexity is more difficult than syntactic complexity. While there are famous and powerful academic and commercial syntactic complexity measures, the problem of measuring semantic complexity is still a challenging one. In this paper, we introduce the DAST model, which stands for Deciding About Semantic Complexity of a Text. DAST proposes an intuitionistic approach to semantics that lets us have a well-defined model for the semantics of a text and its complexity: semantic is considered as a lattice of intuitions and, as a result, semantic complexity is defined as the result of a calculation on this lattice. A set theoretic formal definition of semantic complexity, as a 6-tuple formal system, is provided. By using this formal system, a method for measuring semantic complexity is presented. The evaluation of the proposed approach is done by a set of three human-judgment experiments. The results show that DAST model is capable of deciding about semantic complexity of text. Furthermore, the analysis of the results leads us to introduce a Markovian model for the process of common-sense, multiple-steps and semantic-complexity reasoning in people. The results of Experiments demonstrate that our method outperforms the random baseline with improvement in precision and accuracy.
Discourse structure is integral to understanding a text and is helpful in many NLP tasks. Learning latent representations of discourse is an attractive alternative to acquiring expensive labeled discourse data. Liu and Lapata (2018) propose a structured attention mechanism for text classification that derives a tree over a text, akin to an RST discourse tree. We examine this model in detail, and evaluate on additional discourse-relevant tasks and datasets, in order to assess whether the structured attention improves performance on the end task and whether it captures a text's discourse structure. We find the learned latent trees have little to no structure and instead focus on lexical cues; even after obtaining more structured trees with proposed model modifications, the trees are still far from capturing discourse structure when compared to discourse dependency trees from an existing discourse parser. Finally, ablation studies show the structured attention provides little benefit, sometimes even hurting performance.
Goal oriented dialogue systems have become a prominent customer-care interaction channel for most businesses. However, not all interactions are smooth, and customer intent misunderstanding is a major cause of dialogue failure. We show that intent prediction can be improved by training a deep text-to-text neural model to generate successive user utterances from unlabeled dialogue data. For that, we define a multi-task training regime that utilizes successive user-utterance generation to improve the intent prediction. Our approach achieves the reported improvement due to two complementary factors: First, it uses a large amount of unlabeled dialogue data for an auxiliary generation task. Second, it uses the generated user utterance as an additional signal for the intent prediction model. Lastly, we present a novel look-ahead approach that uses user utterance generation to improve intent prediction in inference time. Specifically, we generate counterfactual successive user utterances for conversations with ambiguous predicted intents, and disambiguate the prediction by reassessing the concatenated sequence of available and generated utterances.
Many challenges in natural language processing require generating text, including language translation, dialogue generation, and speech recognition. For all of these problems, text generation becomes more difficult as the text becomes longer. Current language models often struggle to keep track of coherence for long pieces of text. Here, we attempt to have the model construct and use an outline of the text it generates to keep it focused. We find that the usage of an outline improves perplexity. We do not find that using the outline improves human evaluation over a simpler baseline, revealing a discrepancy in perplexity and human perception. Similarly, hierarchical generation is not found to improve human evaluation scores.
Multi-label learning predicts a subset of labels from a given label set for an unseen instance while considering label correlations. A known challenge with multi-label classification is the long-tailed distribution of labels. Many studies focus on improving the overall predictions of the model and thus do not prioritise tail-end labels. Improving the tail-end label predictions in multi-label classifications of medical text enables the potential to understand patients better and improve care. The knowledge gained by one or more infrequent labels can impact the cause of medical decisions and treatment plans. This research presents variations of concatenated domain-specific language models, including multi-BioMed-Transformers, to achieve two primary goals. First, to improve F1 scores of infrequent labels across multi-label problems, especially with long-tail labels; second, to handle long medical text and multi-sourced electronic health records (EHRs), a challenging task for standard transformers designed to work on short input sequences. A vital contribution of this research is new state-of-the-art (SOTA) results obtained using TransformerXL for predicting medical codes. A variety of experiments are performed on the Medical Information Mart for Intensive Care (MIMIC-III) database. Results show that concatenated BioMed-Transformers outperform standard transformers in terms of overall micro and macro F1 scores and individual F1 scores of tail-end labels, while incurring lower training times than existing transformer-based solutions for long input sequences.
The article explores new ways of written language aided by AI technologies, like GPT-2 and GPT-3. The question that is stated in the paper is not about whether these novel technologies will eventually replace authored books, but how to relate to and contextualize such publications and what kind of new tools, processes, and ideas are behind them. For that purpose, a new concept of synthetic books is introduced in the article. It stands for the publications created by deploying AI technology, more precisely autoregressive language models that are able to generate human-like text. Supported by the case studies, the value and reasoning of the synthetic books are discussed. The paper emphasizes that artistic quality is an issue when it comes to AI-generated content. The article introduces projects that demonstrate an interactive input by an artist and/or audience combined with the deep-learning-based language models. In the end, the paper focuses on understanding the neural aesthetics of written language in the art context.
Language Models (LMs) often cannot be deployed because of their potential to harm users in hard-to-predict ways. Prior work identifies harmful behaviors before deployment by using human annotators to hand-write test cases. However, human annotation is expensive, limiting the number and diversity of test cases. In this work, we automatically find cases where a target LM behaves in a harmful way, by generating test cases ("red teaming") using another LM. We evaluate the target LM's replies to generated test questions using a classifier trained to detect offensive content, uncovering tens of thousands of offensive replies in a 280B parameter LM chatbot. We explore several methods, from zero-shot generation to reinforcement learning, for generating test cases with varying levels of diversity and difficulty. Furthermore, we use prompt engineering to control LM-generated test cases to uncover a variety of other harms, automatically finding groups of people that the chatbot discusses in offensive ways, personal and hospital phone numbers generated as the chatbot's own contact info, leakage of private training data in generated text, and harms that occur over the course of a conversation. Overall, LM-based red teaming is one promising tool (among many needed) for finding and fixing diverse, undesirable LM behaviors before impacting users.
Recently, sequence-to-sequence (seq-to-seq) models have been successfully applied in text-to-speech (TTS) to synthesize speech for single-language text. To synthesize speech for multiple languages usually requires multi-lingual speech from the target speaker. However, it is both laborious and expensive to collect high-quality multi-lingual TTS data for the target speakers. In this paper, we proposed to use low-quality code-switched found data from the non-target speakers to achieve cross-lingual voice cloning for the target speakers. Experiments show that our proposed method can generate high-quality code-switched speech in the target voices in terms of both naturalness and speaker consistency. More importantly, we find that our method can achieve a comparable result to the state-of-the-art (SOTA) performance in cross-lingual voice cloning.
Scene text recognition (STR) is still a hot research topic in computer vision field due to its various applications. Existing works mainly focus on learning a general model with a huge number of synthetic text images to recognize unconstrained scene texts, and have achieved substantial progress. However, these methods are not quite applicable in many real-world scenarios where 1) high recognition accuracy is required, while 2) labeled samples are lacked. To tackle this challenging problem, this paper proposes a few-shot adversarial sequence domain adaptation (FASDA) approach to build sequence adaptation between the synthetic source domain (with many synthetic labeled samples) and a specific target domain (with only some or a few real labeled samples). This is done by simultaneously learning each character's feature representation with an attention mechanism and establishing the corresponding character-level latent subspace with adversarial learning. Our approach can maximize the character-level confusion between the source domain and the target domain, thus achieves the sequence-level adaptation with even a small number of labeled samples in the target domain. Extensive experiments on various datasets show that our method significantly outperforms the finetuning scheme, and obtains comparable performance to the state-of-the-art STR methods.