Related papers: Automatic Prediction of Discourse Connectives
Implicit discourse relation classification is one of the most difficult steps in discourse parsing. The difficulty stems from the fact that the coherence relation must be inferred based on the content of the discourse relational arguments.…
Hate speech detection is a common downstream application of natural language processing (NLP) in the real world. In spite of the increasing accuracy, current data-driven approaches could easily learn biases from the imbalanced data…
Detecting factual inconsistency for long document summarization remains challenging, given the complex structure of the source article and long summary length. In this work, we study factual inconsistency errors and connect them with a line…
Text entry is an essential task in our day-to-day digital interactions. Numerous intelligent features have been developed to streamline this process, making text entry more effective, efficient, and fluid. These improvements include…
Discourse relation classification is an especially difficult task without explicit context markers (Prasad et al., 2008). Current approaches to implicit relation prediction solely rely on two neighboring sentences being targeted, ignoring…
This paper addresses the problem of dialogue reasoning with contextualized commonsense inference. We curate CICERO, a dataset of dyadic conversations with five types of utterance-level reasoning-based inferences: cause, subsequent event,…
Recently emerged intelligent assistants on smartphones and home electronics (e.g., Siri and Alexa) can be seen as novel hybrids of domain-specific task-oriented spoken dialogue systems and open-domain non-task-oriented ones. To realize such…
We present DiscoSense, a benchmark for commonsense reasoning via understanding a wide variety of discourse connectives. We generate compelling distractors in DiscoSense using Conditional Adversarial Filtering, an extension of Adversarial…
Machine comprehension question answering, which finds an answer to the question given a passage, involves high-level reasoning processes of understanding and tracking the relevant contents across various semantic units such as words,…
Expressive text encoders such as RNNs and Transformer Networks have been at the center of NLP models in recent work. Most of the effort has focused on sentence-level tasks, capturing the dependencies between words in a single sentence, or…
This paper introduces AFEC, an automatically curated knowledge graph based on people's day-to-day casual conversations. The knowledge captured in this graph bears potential for conversational systems to understand how people offer…
Relation extraction is the problem of classifying the relationship between two entities in a given sentence. Distant Supervision (DS) is a popular technique for developing relation extractors starting with limited supervision. We note that…
We introduce the task of predicting adverbial presupposition triggers such as also and again. Solving such a task requires detecting recurring or similar events in the discourse context, and has applications in natural language generation…
Conversational AI assistants are becoming popular and question-answering is an important part of any conversational assistant. Using relevant utterances as features in question-answering has shown to improve both the precision and recall…
Machine learning algorithms have achieved superhuman performance in specific complex domains. However, learning online from few examples and compositional learning for efficient generalization across domains remain elusive. In humans, such…
Decomposable tasks are complex and comprise of a hierarchy of sub-tasks. Spoken intent prediction, for example, combines automatic speech recognition and natural language understanding. Existing benchmarks, however, typically hold out…
The vast amounts of on-line text now available have led to renewed interest in information extraction (IE) systems that analyze unrestricted text, producing a structured representation of selected information from the text. This paper…
Contextual information plays a crucial role in speech recognition technologies and incorporating it into the end-to-end speech recognition models has drawn immense interest recently. However, previous deep bias methods lacked explicit…
Most human interactions occur in the form of spoken conversations where the semantic meaning of a given utterance depends on the context. Each utterance in spoken conversation can be represented by many semantic and speaker attributes, and…
This paper elaborates on the design of a machine translation evaluation method that aims to determine to what degree the meaning of an original text is preserved in translation, without looking into the grammatical correctness of its…