Abstract: Embodiments described herein provide natural language processing (NLP) systems and methods that provide a customized summarization of scientific or technical articles, which disentangles background information from new contributions, and summarizes the background information or the new information (or both) based on a user's preference. Specifically, the systems and methods utilize machine learning classifiers to classify portions of sentences within the article as containing background information or as containing a new contribution attributable to the article. The systems and methods then incorporate the background information in the summary or incorporate the new contribution in the summary and output the summary. In this way, the systems and methods can provide summaries of scientific literatures, which largely accelerates literature review in scientific fields.

Abstract: A method, computer system, and a computer program product for natural language processing are provided. A first text corpus that includes semi-structured content that includes hierarchical nodes may be received. Some of the hierarchical nodes may be masked. Node embeddings and level embeddings may be generated from the semi-structured content of the first text corpus and from the masked hierarchical nodes. The node embeddings and the level embeddings may be included in a bi-directional transformer model. The bi-directional transformer model may be trained on the first text corpus by reducing loss from the bi-directional transformer model predicting the masked hierarchical nodes.

Abstract: Mechanisms are provided to implement a fine-grained finding descriptor generation computing tool that automatically generates fine-grained labels for downstream computer system operations. The mechanisms process medical report content based on a core finding lexicon, to extract core finding instances from the medical report content. The mechanisms execute, for each core finding instance, automated computer NLP operations that generate a parse tree for the portion of the medical report content corresponding to the core finding instance, perform phrasal grouping on the parse tree to thereby associate one or more modifiers of core findings specified in the portion of the medical report content with the core finding instance, and generate a fine-grained finding descriptor data structure for the core finding instance based on the association of one or more modifiers of the core finding with the core finding instance.

Abstract: In an embodiment, the disclosed technologies are capable of detecting a tone in text. A detected tone may be used to inform a decision made by and/or output produced by a grammatical error correction system. A set of candidate tones may be presented to a user for feedback. User feedback on the candidate tones may be used to improve subsequent tone detections.

Abstract: Embodiments described herein provide systems and methods for data-to-text generation. The embodiments receive input data that includes a resource description framework (RDF) triples in an RDF graph. A data-to-text generation system generates position aware embeddings, including position embeddings, triple role embeddings, and tree-level embeddings. Using the position aware embeddings and the RDF graph, the data-to-text generation system generates a textual description for the RDF graph.

Abstract: Systems and methods for automatic evaluation of the quality of NLG outputs. In some aspects of the technology, a learned evaluation model may be pretrained first using NLG model pretraining tasks, and then with further pretraining tasks using automatically generated synthetic sentence pairs. In some cases, following pretraining, the evaluation model may be further fine-tuned using a set of human-graded sentence pairs, so that it learns to approximate the grades allocated by the human evaluators. In some cases, following fine-tuning, the learned evaluation model may be distilled into a student model.

Abstract: In an approach to AI explaining for natural language processing, responsive to receiving an input text for a machine learning model, an output is generated from the machine learning model. A plurality of alteration techniques are applied to the input text to generate one or more alternate outputs, where each alternate output corresponds to an alteration technique. A variation rate of the alternate output is calculated for each alteration technique. A preferred technique of generating neighboring data of the input text is generated based on a comparison of the variation rate of the alternate output for each alteration technique.

Abstract: Methods and systems are described for generating dynamic conversational responses using machine learning models. The dynamic conversational responses may be generated in real time and reflect the likely goals and/or intents of a user. The machine learning model may provide these features by monitoring one or more user actions and/or lengths of time between one or more user actions during conversational interactions.

Abstract: A method and a system for generating medical reports based on medical images are provided. The method and system are characterized by carrying out an imaging examination on a target object; visualizing the image or the sequence of images acquired during the execution of the imaging examination; carrying out a report text generation step in parallel with the visualized image or sequence of images by using a speech recognition process; and saving the report text by associating univocally the report text to the visualized image or to the sequence of images.

Abstract: An audio processing method includes: converting a time-domain audio signal into a frequency-domain audio signal; determining a noise reduction gain according to the frequency-domain audio signal; and selecting at least one set of time-domain filter coefficients from a plurality sets of time-domain filter coefficients according to the noise reduction gain; configuring a time-domain filter according to the at least one selected set of time-domain filter coefficients, and filtering the time-domain audio signal with the time-domain filter.

Abstract: A system and method for determining sentiment of natural language text content in a domain independent manner is provided. The method comprises providing an adjective-polarity database having stored therein a list of adjectives and corresponding polarity values. The method further comprises receiving natural language text content related to a first domain with information about corresponding sentiment. The method further comprises identifying nouns and adjectives in the received tagged natural language text content. The method further comprises associating the polarity value to each of the adjectives identified in the received tagged natural language text content. The method further comprises masking the identified nouns and adjectives in the received tagged natural language text content with part-of-speech tags. The method further comprises utilizing the masked natural language text content for training of a model for determining a sentiment score for natural language text content related to a second domain.

Abstract: Systems and methods for automatic evaluation of the quality of NLG outputs. In some aspects of the technology, a learned evaluation model may be pretrained first using NLG model pretraining tasks, and then with further pretraining tasks using automatically generated synthetic sentence pairs. In some cases, following pretraining, the evaluation model may be further fine-tuned using a set of human-graded sentence pairs, so that it learns to approximate the grades allocated by the human evaluators.