Abstract: Methods and systems for document summarization include splitting documents into sentences and sorting the sentences by a metric that promotes review opinion prevalence from the documents to generate a ranked list of sentences. Groups of sentences with similar embeddings are formed and a trained generalization encoder-decoder model is applied to output a common generalization of the sentences in each group. Sentences are added to a summary from the generalizations corresponding to the sentences in the ranked list, in rank-order, until a target summary length has been reached. An action is performed responsive to the summary.

Abstract: A computer-implemented method is provided for disentangled data generation. The method includes accessing, by a bidirectional Long Short-Term Memory (LSTM) with a multi-head attention mechanism, a dataset including a plurality of pairs each formed from a given one of a plurality of input text structures and given one of a plurality of style labels for the plurality of input text structures. The method further includes training the bidirectional LSTM as an encoder to disentangle a sequential text input into disentangled representations comprising a content embedding and a style embedding based on a subset of the dataset. The method also includes training a unidirectional LSTM as a decoder to generate a next text structure prediction for the sequential text input based on previously generated text structure information and a current word, from a disentangled representation with the content embedding and the style embedding.

Abstract: A computer-implemented method for counting and extracting opinions in product reviews is provided. The method includes inputting a hypothesis opinion, a product name, and product reviews relating to a product, applying a decontextualization component to the product reviews by using the product name, applying the decontextualization component to the hypothesis opinion by using the product name, applying an entailment model to classify each sentence of the decontextualized product reviews against the decontextualized hypothesis opinion, and outputting one or more sentences classified as entailing the hypothesis opinion and a count of corresponding reviews.

Abstract: Methods and systems for disentangled data generation include accessing a dataset including pairs, each formed from a given input text structure and a given style label for the input text structures. An encoder is trained to disentangle a sequential text input into disentangled representations, including a content embedding and a style embedding, based on a subset of the dataset, using an objective function that includes a regularization term that minimizes mutual information between the content embedding and the style embedding. A generator is trained to generate a text output that includes content from the style embedding, expressed in a style other than that represented by the style embedding of the text input.

Abstract: A method for neural network training is provided. The method inputs a training set of textual claims, lists of evidence including gold evidence chains, and claim labels labelling the evidence with respect to the textual claims. The claim labels include refutes, supports, and not enough information (NEI). The method computes an initial set of document retrievals for each of the textual claims. The method also includes computing an initial set of page element retrievals including sentence retrievals from the initial set of document retrievals for each of the textual claims. The method creates, from the training set of textual claims, a Leave Out Training Set which includes input texts and target texts relating to the labels. The method trains a sequence-to-sequence neural network to generate new target texts from new input texts using the Leave Out Training Set.

Abstract: Systems and methods for matching job descriptions with job applicants is provided. The method includes allocating each of one or more job applicants' curriculum vitae (CV) into sections; applying max pooled word embedding to each section of the job applicants' CVs; using concatenated max-pooling and average-pooling to compose the section embeddings into an applicant's CV representation; allocating each of one or more job position descriptions into specified sections; applying max pooled word embedding to each section of the job position descriptions; using concatenated max-pooling and average-pooling to compose the section embeddings into a job representation; calculating a cosine similarity between each of the job representations and each of the CV representations to perform job-to-applicant matching; and presenting an ordered list of the one or more job applicants or an ordered list of the one or more job position descriptions to a user.

Abstract: Systems and methods for opinion summarization are provided for extracting and counting frequent opinions. The method includes performing a frequency analysis on an inputted list of product reviews for a single item and an inputted corpus of reviews for a product category containing the single item to identify one or more frequent phrases; fine tuning a pretrained transformer model to produce a trained neural network claim generator model, and generating a trained neural network opposing claim generator model based on the trained neural network claim generator model. The method further includes generating a pair of opposing claims for each of the one or more frequent phrases, wherein a generated positive claim is entailed by the product reviews for the single item and a negative claim refutes the positive claim, and outputting a count of sentences entailing the positive claim and a count of sentences entailing the negative claim.

Abstract: Methods and systems for language processing include augmenting an original training dataset to produce an augmented dataset that includes a first example that includes a first scrambled replacement for a first word and a definition of the first word, and a second example that includes a second scrambled replacement for the first word and a definition of an alternative to the first word. A neural network classifier is trained using the augmented dataset.

Abstract: A computer-implemented method and system are provided for teaching syntax for training a neural network based natural language inference model. The method includes selectively performing, by the hardware processor, person reversal on a set of hypothesis sentences, based on person reversal prevention criteria, to obtain a first training data set. The method further includes enhancing, by the hardware processor, a robustness of the neural network based natural language inference model to syntax changes by training the neural network based natural language inference model on original training data combined with the first data set.

Abstract: A method trains an inference model on two-hop NLI problems that include a first and second premise and a hypothesis, and further includes generating, by the model using hypothesis reduction, an explanation from an input premise and an input hypothesis, for an input single hop NLI problem. The learning step determines a distribution over extraction starting positions and lengths from within the first premise and hypothesis of a two-hop NLI problem. The learning step k extraction output slots with combinations of words from the first premise of the two-hop NLI problem and fills another extraction output slots with combinations of words from the hypothesis of the two-hop NLI problem. The learning step trains a sequence model by using the extraction output slots and the other extraction output slots together with the second premise as an input to a single-hop NLI classifier to output a label of the two-hop NLI problem.

Abstract: A computer-implemented method is provided for disentangled data generation. The method includes accessing, by a bidirectional Long Short-Term Memory (LSTM) with a multi-head attention mechanism, a dataset including a plurality of pairs each formed from a given one of a plurality of input text structures and given one of a plurality of style labels for the plurality of input text structures. The method further includes training the bidirectional LSTM as an encoder to disentangle a sequential text input into disentangled representations comprising a content embedding and a style embedding based on a subset of the dataset. The method also includes training a unidirectional LSTM as a decoder to generate a next text structure prediction for the sequential text input based on previously generated text structure information and a current word, from a disentangled representation with the content embedding and the style embedding.

Abstract: Methods and systems for disentangled data generation include accessing a dataset including pairs, each formed from a given input text structure and a given style label for the input text structures. An encoder is trained to disentangle a sequential text input into disentangled representations, including a content embedding and a style embedding, based on a subset of the dataset, using an objective function that includes a regularization term that minimizes mutual information between the content embedding and the style embedding. A generator is trained to generate a text output that includes content from the style embedding, expressed in a style other than that represented by the style embedding of the text input.

Abstract: A computer-implemented method is provided for generating following up questions for multi-hop bridge-type question answering. The method includes retrieving a premise for an input multi-hop bridge-type question. The method further includes assigning, by a three-way neural network based controller, a classification of the premise against the input multi-hop bridge-type question as being any of irrelevant, including a final answer, or including intermediate information. The method also includes outputting the final answer in relation to a first hop of the multi-hop bridge-type question responsive to the classification being including the final answer. The method additionally includes generating a followup question by a neural network and repeating said retrieving, assigning, outputting and generating steps for the followup question, responsive to the classification being including the intermediate information.

Abstract: Aspects of the present disclosure describe improving neural network robustness through neighborhood preserving layers and learning weighted-average neighbor embeddings.

Abstract: A system verifies textual claims using a document corpus. The system includes a memory for storing program code and a processor device for running the code to retrieve documents from the corpus based on Term Frequency Inverse Document Frequency (TFIDF) similarity to a set of textual claims. The processor extracts named entities and capitalized phrases from the textual claims. The processor retrieves documents from the corpus with titles matching any of the extracted named entities and capitalized phrases. The processor extracts premise sentences from the retrieved documents. The processor classifies the premise sentences together with sources of the premises sentences against the textual claims to obtain classifications from among possible classifications including a supported, an unverified, or a contradicted classification.

Abstract: A computer-implemented method and system are provided for teaching syntax for training a neural network based natural language inference model. The method includes selectively performing, by the hardware processor, person reversal on a set of hypothesis sentences, based on person reversal prevention criteria, to obtain a first training data set. The method further includes enhancing, by the hardware processor, a robustness of the neural network based natural language inference model to syntax changes by training the neural network based natural language inference model on original training data combined with the first data set.

Abstract: A system verifies textual claims using a document corpus. The system includes a memory for storing program code and a processor device for running the code to retrieve documents from the corpus based on Term Frequency Inverse Document Frequency (TFIDF) similarity to a set of textual claims. The processor extracts named entities and capitalized phrases from the textual claims. The processor retrieves documents from the corpus with titles matching any of the extracted named entities and capitalized phrases. The processor extracts premise sentences from the retrieved documents. The processor classifies the premise sentences together with sources of the premises sentences against the textual claims to obtain classifications from among possible classifications including a supported, an unverified, or a contradicted classification.

Abstract: Semantic indexing methods and systems are disclosed. One such method is directed to training a semantic indexing model by employing an expanded query. The query can be expanded by merging the query with documents that are relevant to the query for purposes of compensating for a lack of training data. In accordance with another exemplary aspect, time difference features can be incorporated into a semantic indexing model to account for changes in query distributions over time.

Abstract: Systems and methods are disclosed for classifying histological tissues or specimens with two phases. In a first phase, the method includes providing off-line training using a processor during which one or more classifiers are trained based on examples, including: finding a split of features into sets of increasing computational cost, assigning a computational cost to each set; training for each set of features a classifier using training examples; training for each classifier, a utility function that scores a usefulness of extracting the next feature set for a given tissue unit using the training examples.

Abstract: Disclosed is a computer implemented method for fully automated tissue diagnosis that trains a region of interest (ROI) classifier in a supervised manner, wherein labels are given only at a tissue level, the training using a multiple-instance learning variant of backpropagation, and trains a tissue classifier that uses the output of the ROI classifier. For a given tissue, the method finds ROIs, extracts feature vectors in each ROI, applies the ROI classifier to each feature vector thereby obtaining a set of probabilities, provides the probabilities to the tissue classifier and outputs a final diagnosis for the whole tissue.