Semantic Analysis of Winograd Schema No. 1

The Winograd Schema Challenge is a general test for Artificial Intelligence, based on problems of pronoun reference resolution. I investigate the semantics and interpretation of Winograd Schemas, concentrating on the original and most famous example. This study suggests that a rich ontology, detailed commonsense knowledge as well as special purpose inference mechanisms are all required to resolve just this one example. The analysis supports the view that a key factor in the interpretation and disambiguation of natural language is the preference for coherence. This preference guides the resolution of co-reference in relation to both explicitly mentioned entities and also implicit entities that are required to form an interpretation of what is being described. I suggest that assumed identity of implicit entities arises from the expectation of coherence and provides a key mechanism that underpins natural language understanding. I also argue that conceptual ontologies can play a decisive role not only in directly determining pronoun references but also in identifying implicit entities and implied relationships that bind together components of a sentence.

Revisiting the Boundary between ASR and NLU in the Age of Conversational Dialog Systems

As more users across the world are interacting with dialog agents in their daily life, there is a need for better speech understanding that calls for renewed attention to the dynamics between research in automatic speech recognition (ASR) and natural language understanding (NLU). We briefly review these research areas and lay out the current relationship between them. In light of the observations we make in this paper, we argue that (1) NLU should be cognizant of the presence of ASR models being used upstream in a dialog system’s pipeline, (2) ASR should be able to learn from errors found in NLU, (3) there is a need for end-to-end datasets that provide semantic annotations on spoken input, (4) there should be stronger collaboration between ASR and NLU research communities.

Development of Dialogue Management System for Banking Services

Rapid increase in conversational AI and user chat data lead to intensive development of dialogue management systems (DMS) for various industries. Yet, for low-resource languages, such as Azerbaijani, very little research has been conducted. The main purpose of this work is to experiment with various DMS pipeline set-ups to decide on the most appropriate natural language understanding and dialogue manager settings. In our project, we designed and evaluated different DMS pipelines with respect to the conversational text data obtained from one of the leading retail banks in Azerbaijan. In the work, the main two components of DMS—Natural language Understanding (NLU) and Dialogue Manager—have been investigated. In the first step of NLU, we utilized a language identification (LI) component for language detection. We investigated both built-in LI methods such as fastText and custom machine learning (ML) models trained on the domain-based dataset. The second step of the work was a comparison of the classic ML classifiers (logistic regression, neural networks, and SVM) and Dual Intent and Entity Transformer (DIET) architecture for user intention detection. In these experiments we used different combinations of feature extractors such as CountVectorizer, Term Frequency-Inverse Document Frequency (TF-IDF) Vectorizer, and word embeddings for both word and character n-gram based tokens. To extract important information from the text messages, Named Entity Extraction (NER) component was added to the pipeline. The best NER model was chosen among conditional random fields (CRF) tagger, deep neural networks (DNN), models and build in entity extraction component inside DIET architecture. Obtained entity tags fed to the Dialogue Management module as features. All NLU set-ups were followed by the Dialogue Management module that contains a Rule-based Policy to handle FAQs and chitchats as well as a Transformer Embedding Dialogue (TED) Policy to handle more complex and unexpected dialogue inputs. As a result, we suggest a DMS pipeline for a financial assistant, which is capable of identifying intentions, named entities, and a language of text followed by policies that allow generating a proper response (based on the designed dialogues) and suggesting the best next action.

Ask me in your own words: paraphrasing for multitask question answering

Multitask learning has led to significant advances in Natural Language Processing, including the decaNLP benchmark where question answering is used to frame 10 natural language understanding tasks in a single model. In this work we show how models trained to solve decaNLP fail with simple paraphrasing of the question. We contribute a crowd-sourced corpus of paraphrased questions (PQ-decaNLP), annotated with paraphrase phenomena. This enables analysis of how transformations such as swapping the class labels and changing the sentence modality lead to a large performance degradation. Training both MQAN and the newer T5 model using PQ-decaNLP improves their robustness and for some tasks improves the performance on the original questions, demonstrating the benefits of a model which is more robust to paraphrasing. Additionally, we explore how paraphrasing knowledge is transferred between tasks, with the aim of exploiting the multitask property to improve the robustness of the models. We explore the addition of paraphrase detection and paraphrase generation tasks, and find that while both models are able to learn these new tasks, knowledge about paraphrasing does not transfer to other decaNLP tasks.